WO2018192352A1 - 一种车道选择方法及目标车辆、计算机存储介质 - Google Patents

一种车道选择方法及目标车辆、计算机存储介质 Download PDF

Info

Publication number
WO2018192352A1
WO2018192352A1 PCT/CN2018/081187 CN2018081187W WO2018192352A1 WO 2018192352 A1 WO2018192352 A1 WO 2018192352A1 CN 2018081187 W CN2018081187 W CN 2018081187W WO 2018192352 A1 WO2018192352 A1 WO 2018192352A1
Authority
WO
WIPO (PCT)
Prior art keywords
lane
target vehicle
vehicle
information
target
Prior art date
Application number
PCT/CN2018/081187
Other languages
English (en)
French (fr)
Inventor
王斌
Original Assignee
腾讯科技（深圳）有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 腾讯科技（深圳）有限公司 filed Critical 腾讯科技（深圳）有限公司
Priority to KR1020197023464A priority Critical patent/KR102212431B1/ko
Priority to JP2019556237A priority patent/JP6808853B2/ja
Priority to EP18787339.3A priority patent/EP3614359A4/en
Publication of WO2018192352A1 publication Critical patent/WO2018192352A1/zh
Priority to US16/460,555 priority patent/US11059485B2/en

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/09—Arrangements for giving variable traffic instructions
    • G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
    • G08G1/0967—Systems involving transmission of highway information, e.g. weather, speed limits
    • G08G1/096708—Systems involving transmission of highway information, e.g. weather, speed limits where the received information might be used to generate an automatic action on the vehicle control
    • G08G1/096725—Systems involving transmission of highway information, e.g. weather, speed limits where the received information might be used to generate an automatic action on the vehicle control where the received information generates an automatic action on the vehicle control
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/18—Propelling the vehicle
    • B60W30/18009—Propelling the vehicle related to particular drive situations
    • B60W30/18163—Lane change; Overtaking manoeuvres
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/14—Adaptive cruise control
    • B60W30/143—Speed control
    • B60W30/146—Speed limiting
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/36—Input/output arrangements for on-board computers
    • G01C21/3626—Details of the output of route guidance instructions
    • G01C21/3658—Lane guidance
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/16—Anti-collision systems
    • G08G1/167—Driving aids for lane monitoring, lane changing, e.g. blind spot detection
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W2050/0062—Adapting control system settings
    • B60W2050/0075—Automatic parameter input, automatic initialising or calibrating means
    • B60W2050/0083—Setting, resetting, calibration
    • B60W2050/0085—Setting or resetting initial positions
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/40—Dynamic objects, e.g. animals, windblown objects
    • B60W2554/404—Characteristics
    • B60W2554/4042—Longitudinal speed
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/80—Spatial relation or speed relative to objects
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/80—Spatial relation or speed relative to objects
    • B60W2554/804—Relative longitudinal speed
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2555/00—Input parameters relating to exterior conditions, not covered by groups B60W2552/00, B60W2554/00
    • B60W2555/60—Traffic rules, e.g. speed limits or right of way

Definitions

  • the invention relates to road selection technology, in particular to a lane selection method and a target vehicle and a computer storage medium.
  • the driver While the vehicle is in motion, the driver will choose the most reasonable lane to drive.
  • the vehicle In an unmanned scene (or a driving scene of an unmanned vehicle), the vehicle must have the same ability to select the optimal lane as the driver in automatic driving, in order to be on a multi-lane highway or city road. Drive, otherwise you will not be able to get on the road.
  • the difference between the two is that the user is semi-automatic in the process of autonomous driving, and the user's own judgment can be added after estimating the route of the automatic navigation, so that a long response time can be allowed; and the driverless is fully automatic. Excessive response times are not allowed and it is necessary to ensure that the response time is as low as possible.
  • selecting the optimal lane involves changing lane change behavior, including Discretionary Lane Change (DLC) and Mandatory Lane Change (MLC).
  • DLC Discretionary Lane Change
  • MLC Mandatory Lane Change
  • the prior art it is necessary to first determine whether the MLC needs to be considered, and then consider the DLC after meeting certain conditions, so as to simulate the driving behavior of the driver through the judgment mechanism.
  • the problem with this judgment mechanism is that there is a big difference between the judgment mechanism for analyzing the DLC and the MLC and the selection of the unmanned scene, especially the lane change.
  • the decision result based on the judgment mechanism is not ideal in practical application, and accurate lane change selection cannot be realized, and thus the requirement that the response time is as low as possible cannot be ensured.
  • the embodiments of the present invention provide a lane selection method, a target vehicle, and a computer storage medium, which at least solve the problems existing in the prior art.
  • a lane selection method includes:
  • a decision model for lane change selection is obtained according to a first model for deciding an intersection change lane and a second model for determining a travel speed;
  • the target information being used to represent driving information of the vehicle surrounding the target vehicle;
  • the target lane is obtained by the decision model according to the target information acquired in real time and the travel information of the target vehicle.
  • the target vehicle includes:
  • a first obtaining unit configured to obtain a decision model for lane change selection according to a first model for determining a roadway change lane and a second model for determining a travel speed
  • a second acquiring unit configured to acquire driving information of the target vehicle and target information related to the target vehicle in real time, the target information being used to represent driving information of the vehicle surrounding the target vehicle;
  • the lane determining unit is configured to obtain the target lane through the decision model according to the target information acquired in real time and the driving information of the target vehicle.
  • a target vehicle of an embodiment of the present invention comprising: a processor and a memory for storing a computer program executable on the processor; wherein the processor is configured to execute the computer program when the computer program is executed A lane selection method as described in any of the aspects.
  • a computer storage medium storing the computer executable instructions for executing the lane selection method according to any one of the above aspects.
  • a lane selection method the method being performed by a target vehicle, the target vehicle including one or more processors and a memory, and one or more programs, wherein the one or more programs
  • the program is stored in a memory, and the program may include one or more units each corresponding to a set of instructions, the one or more processors being configured to execute the instructions; the method comprising:
  • a decision model for lane change selection is obtained according to a first model for deciding an intersection change lane and a second model for determining a travel speed;
  • the target information being used to represent driving information of the vehicle surrounding the target vehicle;
  • the target lane is obtained by the decision model according to the target information acquired in real time and the travel information of the target vehicle.
  • a model for characterizing different decision choices is modeled to obtain a decision model for lane change selection, for example, a decision result obtained by using DLC and MLC to model speed, intersection, etc.
  • a decision model for lane change selection for example, a decision result obtained by using DLC and MLC to model speed, intersection, etc.
  • the situation is fully considered in the unmanned scene, more in line with actual needs, according to the target information related to the target vehicle acquired in real time, the driving information of the target vehicle, the target lane is obtained through the decision model, and the lane selection is performed by the obtained target lane. , to achieve accurate lane change selection, to ensure that the response time is as low as possible.
  • FIG. 1 is a schematic diagram showing an optional hardware structure of an in-vehicle terminal or a mobile terminal held by a user installed on a target vehicle according to various embodiments of the present invention
  • FIG. 2 is a schematic diagram of a communication system of the mobile terminal shown in FIG. 1;
  • FIG. 3 is a schematic diagram of hardware entities of each party performing information interaction in an embodiment of the present invention.
  • FIG. 4 is a schematic flowchart of an implementation process of a method according to an embodiment of the present invention.
  • FIG. 5 is a schematic diagram of a system architecture according to an embodiment of the present invention.
  • FIG. 6 is a schematic diagram of key parameters of a lane change behavior decision according to an embodiment of the present invention.
  • FIG. 7 is a schematic structural diagram of a decision model for lane change selection according to Embodiment 1 of the present invention.
  • FIG. 8 is a schematic diagram of a lane change selection situation in which a sample is applied in an actual application according to an embodiment of the present invention
  • FIG. 9 is a schematic diagram of a process of selecting a lane change according to an embodiment of the present invention.
  • FIG. 10 is a hardware structural diagram of an in-vehicle terminal installed on a target vehicle or a mobile terminal held by a user according to an embodiment of the present invention.
  • module A mobile terminal embodying various embodiments of the present invention will now be described with reference to the accompanying drawings.
  • suffixes such as “module,” “component,” or “unit” used to denote an element are merely illustrative of the embodiments of the present invention, and do not have a specific meaning per se. Therefore, “module” and “component” can be used in combination.
  • first, second, etc. are used herein to describe various elements (or various thresholds or various applications or various instructions or various operations), etc., these elements (or thresholds) Or application or instruction or operation) should not be limited by these terms. These terms are only used to distinguish one element (or threshold or application or instruction or operation) and another element (or threshold or application or instruction or operation).
  • first operation may be referred to as a second operation
  • second operation may also be referred to as a first operation
  • the first operation and the second operation are both operations, but the two are not the same The operation is only.
  • the steps in the embodiment of the present invention are not necessarily processed in the order of the steps described.
  • the steps may be selectively arranged to be reordered according to requirements, or the steps in the embodiment may be deleted, or the steps in the embodiment may be added.
  • the description of the steps in the embodiments of the present invention is only an optional combination of the steps, and does not represent a combination of the steps of the embodiments of the present invention.
  • the order of the steps in the embodiments is not to be construed as limiting the present invention.
  • target vehicle in this article refers to a car that is automatically driven in an unmanned scene, or may be referred to as a self-driving car.
  • the intelligent terminal (such as a mobile terminal) of the embodiment of the present invention can be implemented in various forms.
  • the mobile terminal described in the embodiments of the present invention may include, for example, a mobile phone, a smart phone, a notebook computer, a digital broadcast receiver, a personal digital assistant (PDA, Personal Digital Assistant), a tablet (PAD), a portable multimedia player ( Mobile terminals such as PMP (Portable Media Player), navigation devices, and the like, and fixed terminals such as digital TVs, desktop computers, and the like.
  • PDA Personal Digital Assistant
  • PAD tablet
  • PMP Portable Multimedia Player
  • navigation devices and the like
  • fixed terminals such as digital TVs, desktop computers, and the like.
  • the terminal is a mobile terminal.
  • those skilled in the art will appreciate that configurations in accordance with embodiments of the present invention can be applied to fixed type terminals in addition to components that are specifically for mobile purposes.
  • FIG. 1 is a schematic diagram of an optional hardware structure of a mobile terminal implementing various embodiments of the present invention.
  • the mobile terminal 100 is not limited to an in-vehicle terminal or a mobile phone terminal. In this embodiment, the mobile terminal is placed in a target vehicle.
  • the mobile terminal 100 may include: a GPS positioning unit 111, a wireless communication unit 112, a wireless internet unit 113, an alarm communication unit 114, a map unit 121, a voice unit 122, a user input unit 130, a first acquisition unit 140, The second acquisition unit 141, the lane determination unit 142, the output unit 150, the display unit 151, the audio output unit 152, the storage unit 160, the interface unit 170, the processing unit 180, the power supply unit 190, and the like.
  • Figure 1 illustrates a mobile terminal having various components, but it should be understood that not all illustrated components are required to be implemented. More or fewer components can be implemented instead. The components of the in-vehicle terminal will be described in detail below.
  • the GPS positioning unit 111 is configured to receive information transmitted by the satellite to check or acquire location information of the vehicle-mounted terminal, for example, performing single-star positioning or double-star positioning according to the transmitted information, to determine a position or navigation of the vehicle relative to the navigation path. The location of a lane on the path, etc. Specifically, distance information and accurate time information from three or more satellites are calculated and triangulation is applied to the calculated information to accurately calculate three-dimensional current position information according to longitude, latitude, and altitude. Currently, the method for calculating position and time information uses three satellites and corrects the calculated position and time information errors by using another satellite. Further, the GPS positioning unit 111 can also calculate the speed information by continuously calculating the current position information in real time, and obtain the vehicle speed information of the current vehicle.
  • a wireless communication unit 112 that allows for radio communication between the in-vehicle terminal and a wireless communication system or network.
  • the wireless communication unit can communicate in various forms, and can communicate with the background server in a broadcast form, a Wi-Fi communication form, a mobile communication (2G, 3G, or 4G) format.
  • the broadcast signal and/or the broadcast associated information may be received from the external broadcast management server via the broadcast channel.
  • the broadcast channel can include a satellite channel and/or a terrestrial channel.
  • the broadcast management server may be a server that generates and transmits a broadcast signal and/or broadcast associated information or a server that receives a previously generated broadcast signal and/or broadcast associated information and transmits it to the terminal.
  • the broadcast signal may include a TV broadcast signal, a radio broadcast signal, a data broadcast signal, and the like. Moreover, the broadcast signal may further include a broadcast signal combined with a TV or radio broadcast signal. Broadcast related information can also be provided via a mobile communication network.
  • the broadcast signal may exist in various forms, for example, it may be an Electronic Program Guide (EPG) of Digital Multimedia Broadcasting (DMB), a digital video broadcast handheld (DVB-H, Digital Video Broadcasting-Handheld). ) exists in the form of an ESG (Electronic Service Guide) and the like.
  • EPG Electronic Program Guide
  • DMB Digital Multimedia Broadcasting
  • DVD-H Digital Video Broadcasting-Handheld
  • the broadcast signal and/or broadcast associated information may be stored in storage unit 160 (or other type of storage medium).
  • Wi-Fi is a technology that can connect terminals such as personal computers and mobile terminals (such as car terminals and mobile phone terminals) wirelessly.
  • Wi-Fi hotspots can be accessed to access Wi-Fi.
  • Fi network Wi-Fi hotspots are created by installing an access point on an internet connection. This access point transmits wireless signals over short distances, typically covering 300 feet.
  • a Wi-Fi enabled car terminal encounters a Wi-Fi hotspot, it can be wirelessly connected to the Wi-Fi network.
  • the radio signal is transmitted to and/or received from at least one of a base station (e.g., an access point, a Node B, etc.), an external terminal, and a server.
  • a base station e.g., an access point, a Node B, etc.
  • Such radio signals may include voice call signals, video call signals, or various types of data transmitted and/or received in accordance with text and/or multimedia messages.
  • the wireless internet unit 113 supports various data transmission communication technologies including wireless, of the in-vehicle terminal to access the Internet.
  • the unit can be internally or externally coupled to the vehicle terminal.
  • the wireless Internet access technologies involved in the unit may include Wireless Local Area Networks (WLAN), Wireless Broadband (Wibro), Worldwide Interoperability for Microwave Access (Wimax), and High Speed Downlink Packet Access (HSDPA, High). Speed Downlink Packet Access) and more.
  • the alarm communication unit 114 is configured to send an alarm signal to the background server to notify the vehicle abnormality information.
  • the current vehicle location information obtained by the GPS positioning unit and the vehicle abnormality information are packaged and transmitted to the background server, such as an alarm or monitoring center for processing.
  • the map unit 121 is configured to store map information, and the map information may be map information that is used offline after being downloaded online, or may be map information that is downloaded in real time. Map information can also be up to date.
  • the voice unit 122 is configured to perform a voice operation. On the one hand, the voice command of the user can be received. On the other hand, the voice broadcast can be performed in combination with the current vehicle location and navigation information, and the background processing result of the vehicle abnormality information, to remind the user to pay attention to the road condition, and the like. .
  • the vehicle terminal can apply 2G, 3G or 4G, wireless technology, etc., support high-speed data transmission, transmit sound and data information at the same time, open interface, unlimited applications, and the vehicle terminal can be easily used with various I/O devices.
  • the user input unit 130 can generate key input data according to a command input by the user to control various operations of the in-vehicle terminal.
  • the user input unit 130 allows the user to input various types of information, and may include a keyboard, a mouse, a touch pad (eg, a touch sensitive component that detects changes in resistance, pressure, capacitance, etc. due to contact), a scroll wheel, a shaker. Rod and so on.
  • a touch panel is superimposed on the display unit 151 in the form of a layer, a touch screen can be formed.
  • the first obtaining unit 140 is configured to obtain a decision model for lane change selection according to a first model for determining a roadway change lane and a second model for determining a travel speed; and the second obtaining unit 141 is configured to acquire in real time.
  • Driving information of the target vehicle and target information related to the target vehicle the target information is used to represent driving information of the vehicle surrounding the target vehicle;
  • the lane determining unit 142 is configured to be based on the target information acquired in real time and the driving information of the target vehicle The target lane is obtained by the decision model.
  • the interface unit 170 serves as an interface through which at least one external device can communicate with the in-vehicle terminal.
  • the external device may include a wired or wireless headset port, an external power (or battery charger) port, a wired or wireless data port, a memory card port, a port for connecting a device having an identification unit, and an audio input/output. (I/O) port, video I/O port, headphone port, and more.
  • the identification unit may be stored to verify various information used by the user to use the in-vehicle terminal and may include a User Identification Module (UIM), a Subscriber Identity Module (SIM), and a Universal Customer Identification Unit (USIM, Universal Subscriber). Identity Module) and more.
  • UIM User Identification Module
  • SIM Subscriber Identity Module
  • USB Universal Subscriber
  • the device having the identification unit may take the form of a smart card, and therefore, the identification device may be connected to the vehicle-mounted terminal via a port or other connection device.
  • the interface unit 170 can be configured to receive input from an external device (eg, data information, power, etc.) and transmit the received input to one or more components within the in-vehicle terminal or can be used in the in-vehicle terminal and external device Transfer data between.
  • an external device eg, data information, power, etc.
  • the interface unit 170 may function as a path through which power is supplied from the base to the in-vehicle terminal, or may be used as a mode by which various command signals input from the base are allowed to be transmitted to the in-vehicle terminal path of.
  • Various command signals or electric power input from the base can be used as signals for identifying whether the in-vehicle terminal is accurately mounted on the base.
  • Output unit 150 is configured to provide an output signal (eg, an audio signal, a video signal, a vibration signal, etc.) in a visual, audio, and/or tactile manner.
  • the output unit 150 may include a display unit 151, an audio output unit 152, and the like.
  • the display unit 151 can display information processed in the in-vehicle terminal.
  • the in-vehicle terminal can display a related user interface (UI) or a graphical user interface (GUI).
  • UI related user interface
  • GUI graphical user interface
  • the display unit 151 may display a captured image and/or a received image, a UI or GUI showing a video or image and related functions, and the like.
  • the display unit 151 can function as an input device and an output device.
  • the display unit 151 may include a Liquid Crystal Display (LCD), a Thin Film Transistor (LCD), an Organic Light-Emitting Diode (OLED) display, a flexible display, and a three-dimensional (3D) At least one of a display or the like.
  • LCD Liquid Crystal Display
  • LCD Thin Film Transistor
  • OLED Organic Light-Emitting Diode
  • 3D three-dimensional
  • Some of these displays may be configured to be transparent to allow a user to view from the outside, which may be referred to as a transparent display, and a typical transparent display may be, for example, a transparent organic light emitting diode (TOLED) display or the like.
  • TOLED transparent organic light emitting diode
  • the in-vehicle terminal may include two or more display units (or other display devices), for example, the in-vehicle terminal may include an external display unit (not shown) and an internal display unit (not shown).
  • the touch screen can be used to detect touch input pressure as well as touch input position and touch input area.
  • the audio output unit 152 may convert the audio data received or stored in the storage unit 160 into an audio signal when the vehicle-mounted terminal is in a call signal receiving mode, a call mode, a recording mode, a voice recognition mode, a broadcast receiving mode, and the like.
  • the output is sound.
  • the audio output unit 152 can provide an audio output (eg, a call signal reception sound, a message reception sound, and the like) related to a specific function performed by the in-vehicle terminal.
  • the audio output unit 152 may include a speaker, a buzzer, and the like.
  • the storage unit 160 may store a software program or the like that performs processing and control operations performed by the processing unit 180, or may temporarily store data (for example, a phone book, a message, a still image, a video, and the like) that has been output or is to be output. Moreover, the storage unit 160 may store data regarding various manners of vibration and audio signals that are output when a touch is applied to the touch screen.
  • the storage unit 160 may include at least one type of storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (for example, SD or DX memory, etc.), a random access memory (RAM), Static Random Access Memory (SRAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), Programmable Read Only Memory (EEPROM) PROM, Programmable Read Only Memory), magnetic memory, magnetic disk, optical disk, and the like.
  • the in-vehicle terminal can cooperate with a network storage device that performs a storage function of the storage unit 160 through a network connection.
  • Processing unit 180 typically controls the overall operation of the in-vehicle terminal. For example, processing unit 180 performs the control and processing associated with voice calls, data communications, video calls, and the like. As another example, the processing unit 180 can perform a pattern recognition process to recognize a handwriting input or a picture drawing input performed on the touch screen as a character or an image.
  • the power supply unit 190 receives external power or internal power under the control of the processing unit 180 and provides appropriate power required to operate the various components and components.
  • the various embodiments described herein can be implemented in a computer readable medium using, for example, computer software, hardware, or any combination thereof.
  • the embodiments described herein may use an Application Specific Integrated Circuit (ASIC), a Digital Signal Processing (DSP), a Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), processor, controller, microcontroller, microprocessor, electronics designed to perform the functions described herein At least one of the units is implemented, and in some cases, such an implementation may be implemented in processing unit 180.
  • ASIC Application Specific Integrated Circuit
  • DSP Digital Signal Processing
  • DSPD Digital Signal Processing Device
  • PLD Programmable Logic Device
  • FPGA Field Programmable Gate Array
  • the software code can be implemented by a software application (or program) written in any suitable programming language, which can be stored in storage unit 160 and executed by processing unit 180.
  • the specific hardware entity of the storage unit 160 may be a memory
  • a specific hardware entity of the processing unit 180 may be a controller.
  • the mobile terminal 100 as shown in FIG. 1 may be configured to operate using a communication system such as a wired and wireless communication system and a satellite-based communication system that transmits data via frames or packets.
  • a communication system such as a wired and wireless communication system and a satellite-based communication system that transmits data via frames or packets.
  • a communication system in which the mobile terminal 100 is operable according to an embodiment of the present invention will now be described with reference to FIG.
  • Such communication systems may use different air interfaces and/or physical layers.
  • the air interface used by the communication system includes, for example, Frequency Division Multiple Access (FDMA), Time Division Multiple Access (TDMA), Code Division Multiple Access (CDMA), and General Purpose Code Division Multiple Access (CDMA).
  • FDMA Frequency Division Multiple Access
  • TDMA Time Division Multiple Access
  • CDMA Code Division Multiple Access
  • CDMA General Purpose Code Division Multiple Access
  • UMTS Universal Mobile Telecommunications System
  • LTE Long Term Evolution
  • GSM Global System for Mobile Communications
  • the following description relates to a CDMA communication system, but such teachings are equally applicable to other types of systems.
  • the CDMA wireless communication system may include a plurality of mobile terminals 100, a plurality of base stations (BS) 270, a base station controller (BSC) 275, and a mobile switching center (MSC) 280.
  • the MSC 280 is configured to interface with a Public Switched Telephone Network (PSTN) 290.
  • PSTN Public Switched Telephone Network
  • the MSC 280 is also configured to interface with a BSC 275 that can be coupled to the BS 270 via a backhaul line.
  • the backhaul line can be constructed in accordance with any of a number of known interfaces including, for example, E1/T1, ATM, IP, PPP, Frame Relay, HDSL, ADSL, or xDSL. It will be appreciated that the system as shown in FIG. 2 can include multiple BSCs 275.
  • Each BS 270 can serve one or more partitions (or regions), with each partition covered by a multi-directional antenna or an antenna pointing in a particular direction radially away from the BS 270. Alternatively, each partition may be covered by two or more antennas for diversity reception. Each BS 270 can be configured to support multiple frequency allocations, and each frequency allocation has a particular frequency spectrum (eg, 1.25 MHz, 5 MHz, etc.).
  • BS 270 may also be referred to as a Base Transceiver Subsystem (BTS) or other equivalent terminology.
  • BTS Base Transceiver Subsystem
  • the term "base station” can be used to generally refer to a single BSC 275 and at least one BS 270.
  • a base station can also be referred to as a "cell station.”
  • each partition of a particular BS 270 may be referred to as multiple cellular stations.
  • a broadcast transmitter (BT, Broadcast Transmitter) 295 transmits a broadcast signal to the mobile terminal 100 operating within the system.
  • a broadcast receiving unit 111 as shown in FIG. 1 is provided at the mobile terminal 100 to receive a broadcast signal transmitted by the BT 295.
  • several satellites 300 are shown, for example, a Global Positioning System (GPS) satellite 300 can be employed.
  • GPS Global Positioning System
  • the satellite 300 helps locate at least one of the plurality of mobile terminals 100.
  • a plurality of satellites 300 are depicted, but it is understood that useful positioning information can be obtained using any number of satellites.
  • the location information unit 115 as shown in FIG. 1 is typically configured to cooperate with the satellite 300 to obtain desired positioning information. Instead of GPS tracking technology or in addition to GPS tracking technology, other techniques that can track the location of the mobile terminal can be used. Additionally, at least one GPS satellite 300 can selectively or additionally process satellite DMB transmissions.
  • BS 270 receives reverse link signals from various mobile terminals 100.
  • Mobile terminal 100 typically participates in calls, messaging, and other types of communications.
  • Each reverse link signal received by a particular base station is processed within a particular BS 270.
  • the obtained data is forwarded to the relevant BSC 275.
  • the BSC provides call resource allocation and coordinated mobility management functions including a soft handoff procedure between the BSs 270.
  • the BSC 275 also routes the received data to the MSC 280, which provides additional routing services for interfacing with the PSTN 290.
  • PSTN 290 interfaces with MSC 280, which forms an interface with BSC 275, and BSC 275 controls BS 270 accordingly to transmit forward link signals to mobile terminal 100.
  • the mobile communication unit 112 of the communication unit 110 in the mobile terminal accesses the mobile communication based on necessary data (including user identification information and authentication information) of the mobile communication network (such as 2G/3G/4G mobile communication network) built in the mobile terminal.
  • the network transmits mobile communication data (including uplink mobile communication data and downlink mobile communication data) for mobile terminal users such as web browsing and network multimedia broadcasting.
  • the wireless internet unit 113 of the communication unit 110 implements a function of a wireless hotspot by operating a related protocol function of the wireless hotspot, and the wireless hotspot supports access of a plurality of mobile terminals (any mobile terminal other than the mobile terminal) by multiplexing the mobile communication unit 112.
  • the mobile communication connection with the mobile communication network transmits mobile communication data (including uplink mobile communication data and downlink mobile communication data) for the mobile terminal user's web browsing, network multimedia playback, etc., since the mobile terminal is substantially multiplexed
  • the mobile communication connection between the mobile terminal and the communication network transmits the mobile communication data, so the traffic of the mobile communication data consumed by the mobile terminal is included in the communication tariff of the mobile terminal by the charging entity on the communication network side, thereby consuming the subscription used by the mobile terminal.
  • the data traffic of mobile communication data included in the communication tariff included in the communication tariff.
  • FIG. 3 is a schematic diagram of hardware entities of each party performing information interaction in the embodiment of the present invention, and FIG. 3 includes: a terminal device 1 and a server 2.
  • the terminal device 1 is composed of terminal devices 11-14, and the terminal device performs information interaction with the server through a wired network or a wireless network.
  • the terminal device may be an in-vehicle terminal installed on the target vehicle or a mobile terminal held by the user.
  • the terminal device is configured on the traveling vehicle, and each terminal can be configured with a terminal device to obtain various control information for driverless driving through data interaction between the terminal device and the background server.
  • the user's own judgment can be added, so that a long response time can be allowed; Human driving is fully automated and does not allow for excessive response times. It is necessary to ensure that the response time is as low as possible.
  • selecting the optimal lane involves changing lane change behavior, including DLC and MLC.
  • DLC is to improve the driving speed.
  • MLC is necessary to leave the lane due to the influence of intersections. For example, it is necessary to first determine whether MLC needs to be considered, and then consider DLC after meeting certain conditions, so as to drive the driver through this judgment mechanism. Perform simulations.
  • the problem with this judgment mechanism is that the judgment mechanism for analyzing the DLC and the MLC will completely separate the two models of DLC and MLC.
  • the scene switching will be too natural and may occur.
  • the decision result based on the judgment mechanism is greatly affected by the current vehicle speed in actual application, and the result is not stable enough. For example, when the vehicle speed slightly changes, there may be a situation of switching back and forth, and accuracy cannot be achieved.
  • the choice of lane change also does not ensure that the response time is as low as possible.
  • the existing judgment mechanism is equally treated for all lanes, and it is not possible to adopt the demand for overtaking from the left lane.
  • the processing logic 10 of the terminal device includes: S1, acquiring target information related to the target vehicle, where the target information is used to represent driving information of the vehicle surrounding the target vehicle; S2: acquiring target vehicle information; S3, obtaining a decision model for lane change selection according to a first model for determining a roadway change lane and a second model for determining a travel speed; S4, data to be acquired in real time, including a target
  • the vehicle information and target information related to the target vehicle such as information of the current vehicle and information of the vehicle associated with the current vehicle, are input into the decision model to obtain a control command, and lane selection is performed according to the control command.
  • the operation logic used can generate and execute corresponding processing on the vehicle-mounted terminal installed on the target vehicle or the mobile terminal held by the user, and the server is used to provide various data sources required by the target vehicle, including the current vehicle and the current vehicle.
  • Other vehicles may store these data in an in-vehicle terminal installed on the target vehicle or a mobile terminal held by the user, and perform lane selection by a control command.
  • the embodiment of the present invention is not limited to the operation logic in the server, after the server receives the request, the operation logic is executed, and the control instruction is sent to the vehicle in real time for performing lane selection according to the control instruction, but due to multiple risks of network interaction
  • the operation logic is placed on the server, which may result in an increase in response time in the unmanned scene of the present embodiment due to the data interaction delay caused by the network interaction, thereby increasing the risk of driverless driving, which is not conducive to risk control.
  • the operation logic is placed on the vehicle terminal installed on the target vehicle or the mobile terminal held by the user, although the processing difficulty is increased to some extent, but the release of the control command is not affected by the network data interaction, and the lane change selection of the vehicle can be controlled in real time. Therefore, the response time in the driverless scene can be largely ensured, and the accuracy of the lane change selection can be ensured.
  • FIG. 3 is only a system architecture example for implementing the embodiment of the present invention.
  • the embodiment of the present invention is not limited to the system structure described in FIG. 3 above. According to the system architecture described in FIG. 3, various embodiments of the method of the present invention are proposed. .
  • a lane selection method includes: obtaining a decision for lane change selection according to a first model for determining a roadway change lane and a second model for determining a travel speed Model (101).
  • a first model is MLC, which is used to evaluate whether the time t required for the current vehicle to travel to the intersection is greater than the time required to change the lane.
  • the MLC is used to make decisions on the intersection change, such as the current intersection. The impact must leave the driveway.
  • the second model is DLC. The decision of the DLC is divided into two steps: lane selection and lane acceptance.
  • the lane selection it is determined whether the adjacent lanes need to be changed according to the comprehensive information such as the speed of the vehicle and the speed limit of the lane.
  • the comprehensive information such as the speed of the vehicle and the speed limit of the lane.
  • Gap acceptance it is judged according to the distance between the front and rear lanes of the adjacent lanes, and whether there is a total lane change. space. Only when these two conditions are met at the same time will the lane change decision be made.
  • the use of DLC is to improve the driving speed. For example, if the front car is close to the rear car, then it needs to be decelerated. If the car is allowed to overtake after the car is in front, the car will accelerate.
  • the travel information of the target vehicle and the target information related to the target vehicle are used in real time, and the target information is used to characterize the travel information of the vehicle around the target vehicle (102).
  • the target information includes but is not limited to: 1) geographical location information of the surrounding vehicle, which needs to be pointed out: the information is an absolute location information; 2) the distance information of the surrounding vehicle relative to the target vehicle, which needs to be pointed out: different from the geographical
  • the position information is a relative position information; 3) the surrounding environment when the surrounding vehicle is in the open position (such as parking on the roadside), and the speed information of the surrounding vehicles; 4) when there are multiple lanes to be selected, the surrounding vehicles are currently traveling. In which lane and so on.
  • An example is: during the driving process, the speed of the vehicle, the speed of the preceding vehicle, the distance of the vehicle; the speed of the adjacent lane and the distance of the vehicle can be used to decide whether the lane change operation can be performed, in order to improve the driving speed of the vehicle.
  • the target lane is obtained by the decision model based on the target information acquired in real time and the travel information of the target vehicle (103).
  • An example is: by calculating a plurality of utilities of the own lane, the left and right lanes, and finally, selecting a lane with the largest utility among the plurality of utilities as a lane for lane selection.
  • the target vehicle information acquired in real time and the decision model may obtain a control instruction, and the lane selection in the driverless driving is performed according to the control instruction.
  • the driver will choose the most reasonable lane to drive.
  • the vehicle In the unmanned scene using the embodiment of the present invention, the vehicle must have the same ability to independently select the optimal lane as the driver, so that the vehicle can travel on a multi-lane highway or a city road, otherwise it will not be able to get on the road.
  • the embodiment of the present invention is a lane selection scheme for integrating surrounding vehicles and navigation paths, and according to DLC and MLC modeling, the DLC and the MLC are unified into a newly-formed decision model.
  • the utility of the lane and the left and right lanes is calculated separately, and finally the lane with the largest utility is selected as the lane for the lane change selection, thereby solving the problem that the driverless vehicle selects the lane independently.
  • the embodiment of the present invention effectively combines the advantages of DLC and MLC, and obtains a more optimized decision model.
  • the decision model the DNC model plays a major role when the distance from the intersection is farther; when the approach is closer, The greater the influence of the MLC model, the stability of the target lane selected within a certain distance range, and will not switch back and forth.
  • Another example is: 1) determining each lane and the first according to the target vehicle lane change number (such as nlanechange), the target vehicle distance intersection distance value (such as distanceToJunction), and the single lane change minimum distance value (such as d0).
  • p2 and p3 are weight values.
  • the pow function is a power multiplication of the second argument as the first argument, which is a binary arithmetic function that acts on the time series.
  • the first model such as MLC
  • MLC may use an exponential model, and the benefit of the processing is that the influence of the MLC increases rapidly as the distance value of the target vehicle is gradually smaller, and finally near the intersection. It plays an absolutely dominant role, and can neglect the influence of the second model such as DLC, and the intermediate transition is smooth and natural. This design conforms to the actual lane change law. 2) Determine a second type of utility associated with the second model based on the target vehicle speed information (eg, laneSpeed) and lane speed limit information (eg, SPEED_LIMIT).
  • target vehicle speed information eg, laneSpeed
  • SPEED_LIMIT lane speed limit information
  • the second type of utility value is calculated respectively corresponding to the current lane where the target vehicle is currently located, the left lane and the right lane adjacent to the target vehicle.
  • U_DLC and U_MLC are respectively taken as integers, and then the comprehensive utility is calculated.
  • the advantage of this treatment is that it is equivalent to segmentation and classification of key factors such as speed and distance.
  • the biggest advantage is that the stability of the utility can be maintained within a certain range of vehicle speed and distance, further ensuring the stability of the lane change result. Will not switch back and forth.
  • the target vehicle information acquired in real time and the decision model obtain a control instruction, and the lane selection in the driverless driving is performed according to the control instruction.
  • An example is: by calculating a plurality of utilities of the own lane, the left and right lanes, and finally, selecting a lane with the largest utility among the plurality of utilities as a lane for lane selection. That is to say, from the lane comprehensive utility corresponding to the current lane where the target vehicle is currently located, the left lane and the right lane adjacent to the target vehicle, the lane with the largest lane comprehensive utility is selected, and the lane comprehensive utility is maximized.
  • the lane decision is the target lane for lane change selection.
  • the candidate before determining the first type of utility value associated with the first model according to the target vehicle lane change number and the distance value of the target vehicle distance intersection, the candidate may also be selected according to the road network condition.
  • the alternative lane may also be referred to as an alternate target lane. This alternative is not necessarily the final choice of the target lane to be changed, but only needs to establish a reference for the initial operation; the alternative target lane may also be The final destination lane where the final intersection needs to be forked is not limited to the possibilities here.
  • the road network condition is composed of an intersection (such as an intersection, a two-way intersection, a three-way intersection, etc.) and a next road connected to the intersection.
  • the MLC target lane is determined based on the connection relationship between the intersection and the next road.
  • the lane that can reach the intersection and enter the next road is selected as the target lane according to the connectivity. For example, if the current car is in lane 1 and needs to turn right at the intersection, then lane 2 is selected as the target lane. If it is straight through the intersection, there may be multiple lanes to be selected that meet the requirements. At this time, the lane closest to the current lane is selected as the target lane.
  • the target vehicle lane change number according to the distance between the current lane of the target vehicle and the candidate lane in the first direction (such as the Y axis), that is, after determining the final target lane, the current calculation may be calculated.
  • the second direction herein may be the X-axis relative to the first direction (eg, the Y-axis).
  • the X axis is the direction forward with the center line of the lane
  • the Y axis is the direction perpendicular thereto.
  • first direction and the second direction are expressed in a plane rectangular coordinate system
  • there are two coordinate axes in the plane rectangular coordinate system wherein the horizontal axis is the X axis and the right direction is the positive direction;
  • the axis is the Y axis and the orientation is positive.
  • the distance value of the target vehicle distance intersection (such as distanceToJunction).
  • the single lane change minimum distance value (such as d0) required to complete one lane change is obtained.
  • the lane selection method of the embodiment of the present invention before determining the second type of utility related to the second model according to the target vehicle speed information and the lane speed limit information, calculating the speed information of the vehicle around the detected target vehicle And adjusting the vehicle speed information of the target vehicle in real time.
  • the unmanned vehicle In the target lane selection of an unmanned vehicle, in order to ensure that the response time is as short as possible, the unmanned vehicle is required to judge the driving condition of the surrounding vehicle at a higher frequency, for example, it is necessary to pay attention to the speed information of the vehicle around the target vehicle, so that According to the speed information, the speed of the target vehicle is dynamically adjusted in real time. For example, estimating the speed of the target vehicle, the driving speeds of the own lane, the left lane, and the right lane can be respectively estimated according to the detected speed of the surrounding vehicles to ensure no The driving safety of the target vehicle in the human driving scene and the lane change after the target lane is determined. The biggest difference between the scene of an unmanned vehicle and an autonomous vehicle is whether to join the user's own judgment.
  • the automatic navigation route can be added to the user's own judgment, which is actually an auxiliary function for the user's autonomous driving, and the driverless is dependent on the decision model, which is fully automatic and needs to ensure the response time.
  • the driving safety of the target vehicle in the unmanned scene can be ensured, and the lane change after the target lane is determined subsequently. If it is found to be dangerous, the lane change will be abandoned.
  • the vertical distance of the target vehicle center point (such as an arbitrary point on the target vehicle axle or the center point of the vehicle) to the current lane center line is obtained, and it is determined whether the vertical distance is less than a threshold.
  • the threshold it is determined that the target vehicle belongs to the current lane, and the lane speed limit information is obtained according to a preset rule of the current lane. For example, based on the vertical distance d from the center point of the vehicle to the centerline of the lane, it is determined which lane the vehicle belongs to. When d is less than a certain threshold, for example d ⁇ 2.0 m, then the vehicle belongs to this lane.
  • the lane speed in this paper is obtained by referring to the speed at which the vehicle is traveling on the current lane.
  • the lane speed is equal to the target vehicle traveling on the current lane. speed.
  • the lane speed limit information is related to the lane speed of the target vehicle, which is different from the speed limit indicator indicated by the road speed limit sign.
  • the speed limit of the expressway specified in the traffic rules is usually 60-120 km/h.
  • the speed limit indicator indicated by the sign on a section of the expressway is 90km/h.
  • the lane speed and lane speed limit information in this paper are dynamically adjusted in real time according to the driving condition of the vehicle around the target vehicle (such as the vehicle speed information), and the speed limit indicator not specified above is a fixed value. This will be described below by way of two embodiments.
  • the minimum speed is recorded as the lane speed, and the minimum speed of at least two vehicles, that is, the lane speed is used as the lane speed limit information.
  • the speed of the self-driving vehicle can be adjusted according to the traveling speed of the vehicle around the target vehicle in the current lane, for example, in the current lane with a lane speed of 80 km/h, the target vehicle traveling direction There is a car (recorded as vehicle B) with a current speed of 70 km/h and the target vehicle itself (denoted as vehicle A) with a current speed of 75 km/h. Since vehicle B is located in front of vehicle A, In order to avoid traffic safety problems such as rear-end collision, the lane speed limit information takes the minimum value of the vehicle A and the vehicle B, that is, 70 km/hour as the lane speed limit information.
  • the lane selection method of the embodiment of the present invention in the process of obtaining the lane speed limit information according to the preset rule of the current lane, no other vehicle is detected in the current lane detecting the direction of travel of the target vehicle. At the time, the lane speed is used as the lane speed limit information. In one example, if there is no vehicle in front of the vehicle in the lane, the recorded lane speed is equal to the lane maximum speed limit.
  • lane speed in terms of lane speed, it may be performed according to a regulation in a traffic rule, such as a speed limit indicator indicated by a road speed limit sign, for example, on a current lane with a lane speed of 120 km/hour, the target There is no vehicle in the direction of the vehicle, that is, there is no vehicle in front of the target vehicle itself (recorded as vehicle A), and there is a very low possibility of traffic safety hazard. Therefore, the speed limit information of the lane speed limit is about 120 km/h. Lane speed limit information.
  • the lane selection method of the embodiment of the present invention when it is detected that there are other vehicles behind the target vehicle in the current lane, other vehicles behind the target vehicle are ignored.
  • the X coordinate (or abscissa) of a vehicle B is smaller than the X coordinate (or abscissa) of the host vehicle A, where the vehicle A is the target vehicle and the vehicle B is the other vehicle, X The axis is in the forward direction along the lane center line, and the vehicle behind the target vehicle is ignored.
  • the beneficial effect is that in the unmanned driving, regardless of the driving safety and the lane change safety, it is more necessary to pay attention to the vehicle in front of the target vehicle.
  • the driving speed avoids the target vehicle and its rear-end collision, while the vehicle behind the target vehicle does not need to pay too much attention.
  • the vehicles behind the target vehicle are ignored.
  • This embodiment is intended to illustrate an ignore strategy in a decision strategy to ignore other vehicles that are later than the terminal.
  • Other strategies may be included in the decision strategy. For example, the judgment of the intersection distance needs to be set with a predetermined minimum distance to see whether to change lanes or adopt a deceleration strategy.
  • the left lane is only a pronoun for convenience of description, including but not limited to: A fast lane occupied by vehicles for a long time.
  • the terminal vehicle speed information In order to avoid the situation that the vehicle does not occupy the leftmost lane for a long time, it is necessary to correct the terminal vehicle speed information according to the adjustment coefficient to obtain the corrected speed information.
  • determining, according to the modified speed information and the lane speed limit information, a second type of utility related to the second model. For example, when the lane data is > 3, the vehicle is currently in the leftmost lane.
  • the control command in the process of performing lane selection in the unmanned driving according to the control command, 1) the control command does not perform the change to the target lane when the driving in the own lane is maintained. Change lane handling. 2) When the control command is to change lanes to the left lane, the left lane is taken as the target lane and the lane changing process to the target lane is performed. 3) When the control command is to change lanes to the right lane, the right lane is taken as the target lane and a lane change process to the target lane is performed. The determination of the type of lane change is achieved by these means. The final type of lane change is to maintain the lane, change to the left, and change to the right.
  • the evaluation and selection of the target lane can be completed.
  • the various embodiments described above have not focused on whether the lane change can be performed immediately.
  • the lane selection in the unmanned driving is performed, and after the target lane is obtained, the driving condition of the target vehicle itself and the surrounding static and dynamic obstacles can be further combined to determine whether the other pre-compliance is met. It is assumed that if the other preset rule is met, the own lane in which the target vehicle is currently unmanned is immediately changed to the target lane; otherwise, the lane change process to the target lane is not performed. That is to say, when the target lane is selected, whether the lane change can be performed normally depends on the behavior planning after the system, and the vehicle system will judge whether the surrounding static and dynamic obstacles will affect the lane change at a higher frequency, and ensure that the lane change Road safety. If there is danger, you will give up the lane change.
  • the terminal 41 the vehicle terminal mounted on the target vehicle or the mobile terminal held by the user
  • the server 42 is included, wherein the target vehicle uses a data source provided according to the server.
  • Execute operational logic to perform corresponding lane selection processing the server is configured to provide various data sources required by the target vehicle, including the current vehicle and other vehicles associated with the current vehicle, which may be stored in the terminal equipment installed on the target vehicle (in the vehicle terminal or mobile terminal held by the user). Further, the lane selection can be performed by a control command issued by the target vehicle.
  • the terminal 41 includes: a first obtaining unit 411 configured to obtain a decision model for lane change selection according to a first model for determining a roadway change lane and a second model for determining a travel speed; the second obtaining unit 412, And configured to acquire driving information of the target vehicle and target information related to the target vehicle, wherein the target information is used to represent driving information of the vehicle surrounding the target vehicle; the lane determining unit 413 is configured to acquire the target information and the target according to the real-time acquisition.
  • the driving information of the vehicle is obtained by the decision model.
  • the target information related to the target vehicle is used to represent the driving information of the vehicle surrounding the target vehicle.
  • target information related to a target vehicle is first acquired, and the target information is used to represent driving information of a vehicle surrounding the target vehicle.
  • the target information includes: 1) geographical location information of the surrounding vehicle, which needs to be pointed out: the information is an absolute location information; 2) the distance information of the surrounding vehicle relative to the current target vehicle, which needs to be pointed out: different from the geographical location information , is a relative position information; 3) surrounding environment when the surrounding vehicle is in the open position (such as parking on the roadside), the speed information of the surrounding vehicles; 4) where there are multiple lanes to choose when the surrounding vehicle is currently traveling One lane and so on.
  • An example is: during the driving process, the speed of the vehicle, the speed of the preceding vehicle, the distance of the vehicle; the speed of the adjacent lane and the distance of the vehicle can be used to decide whether the lane change operation can be performed, in order to improve the driving speed of the vehicle. Thereafter, based on the first model for deciding the intersection change lane and the second model for determining the travel speed, a decision model for lane change selection is obtained.
  • An example is: 1)
  • the first model is MLC, which is used to evaluate whether the time t required for the current vehicle to travel to the intersection is greater than the time required to change the lane.
  • the MLC is used to make decisions on the intersection change, such as the current intersection. The impact must leave the driveway.
  • the second model is DLC, and the decision of DLC is divided into two steps: lane selection and Gap acceptance.
  • lane selection it is determined whether the adjacent lanes need to be changed according to the comprehensive information such as the speed of the vehicle and the speed limit of the lane.
  • Gap acceptance it is judged according to the distance between the front and rear lanes of the adjacent lanes, and whether there is a total lane change. space. Only when these two conditions are met at the same time will the lane change decision be made.
  • the use of DLC is to improve the driving speed. For example, if the front car is close to the rear car, then it needs to be decelerated. If the car is allowed to overtake after the car is in front, the car will accelerate.
  • the lane determining unit is further configured to calculate, according to the target information acquired in real time and the driving information of the target vehicle, a utility value corresponding to a specific lane related to the target vehicle by using the decision model; Target lane.
  • the specific lane includes at least a local lane where the target vehicle is currently located, a left lane and a right lane adjacent to the target vehicle.
  • An example is: by calculating a plurality of utilities of the own lane, the left and right lanes, and finally, selecting a lane with the largest utility among the plurality of utilities as a lane for lane selection.
  • the embodiment of the present invention is a lane selection scheme for integrating surrounding vehicles and navigation paths, and according to DLC and MLC modeling, the DLC and the MLC are unified into a newly-formed decision model.
  • the utility of the lane and the left and right lanes is calculated separately, and finally the lane with the largest utility is selected as the lane for the lane change selection, thereby solving the problem that the driverless vehicle selects the lane independently.
  • the embodiment of the present invention effectively combines the advantages of DLC and MLC, and obtains a more optimized decision model.
  • the decision model the DNC model plays a major role when the distance from the intersection is farther; when the approach is closer, The greater the influence of the MLC model, the stability of the target lane selected within a certain distance range, and will not switch back and forth.
  • the lane determining unit is further configured to: determine, according to the target vehicle lane change number, the target vehicle distance intersection distance value, and the single lane change minimum distance value, the first model is related to
  • the first type of utility includes the first type of utility corresponding to the current lane in which the target vehicle is currently located, the left lane and the right lane adjacent to the target vehicle. Determining, according to the target vehicle speed information and the lane speed limit information, a second type of utility value associated with the second model, the second type of utility value respectively corresponding to the current lane of the target vehicle, and the target vehicle The second type of utility of the adjacent left and right lanes.
  • the lane determining unit is further configured to: obtain an alternate lane according to a road network condition, where the road network condition is composed of an intersection and a next road connected to the intersection.
  • the target vehicle further includes: a lane change number determining unit configured to obtain the target vehicle lane change number according to a distance between the current lane of the target vehicle and the candidate lane in the first direction. And a distance value determining unit configured to obtain a distance value of the target vehicle distance intersection according to a distance between the position of the target vehicle and the intersection in the second direction. And a single lane change distance value determining unit configured to obtain the single lane change minimum distance value required to complete one lane change according to the current vehicle speed and the lane change time of the target vehicle.
  • the target vehicle further includes: a vehicle speed detecting unit configured to calculate and adjust the target vehicle speed information in real time according to the detected speed information of the target vehicle surrounding vehicle;
  • the speed limit determining unit is configured to obtain a vertical distance from the target vehicle center point to the current lane center line, determine whether the vertical distance is less than a threshold, and determine that the target vehicle belongs to the current lane when less than the threshold, according to the current
  • the preset rule of the lane obtains the lane speed limit information.
  • the speed limit determining unit is further configured to: when the current lane detects at least two vehicles including the vehicle where the target vehicle is located, at least two vehicles The minimum speed is used as the lane speed limit information.
  • the speed limit determining unit is further configured to: when the current lane detects that there is no other vehicle in the traveling direction of the target vehicle, use the lane speed as the lane speed limit information. .
  • the target vehicle further includes: an ignoring decision unit configured to detect that when there are other vehicles behind the vehicle where the target vehicle is located in the current lane, ignore the target vehicle After the other vehicles.
  • the target vehicle further includes: a correction decision unit configured to: when the number of the current lanes is greater than or equal to 3, and the vehicle where the target vehicle is located is currently located on the left lane, Adjusting a coefficient to correct the target vehicle speed information to obtain corrected speed information; the modeling unit is further configured to determine a second related to the second model according to the corrected speed information and the lane speed limit information Class utility.
  • the lane determining unit is further configured to: when the control command is to keep driving in the lane, do not perform a lane changing process to the target lane; the control instruction is When changing lanes to the left lane, the left lane is taken as the target lane and a lane change process to the target lane is performed; when the control command is to change lanes to the right lane, the right side is A lane is used as the target lane and a lane change process to the target lane is performed.
  • the target vehicle further includes: a lane change execution decision unit, configured to: perform lane selection according to the control instruction, and obtain the target lane, if the preset rule is met, immediately The lane in which the target vehicle is currently located changes to the target lane, otherwise, the lane change process to the target lane is not performed.
  • a lane change execution decision unit configured to: perform lane selection according to the control instruction, and obtain the target lane, if the preset rule is met, immediately The lane in which the target vehicle is currently located changes to the target lane, otherwise, the lane change process to the target lane is not performed.
  • the processor for data processing may be implemented by using a microprocessor, a central processing unit (CPU), a DSP, or an FPGA when performing processing; for an storage medium, including an operation instruction,
  • the operation instruction may be computer executable code, and the steps in the flow of the information processing method of the embodiment of the present invention are implemented by the operation instruction.
  • Driving behavior modeling mainly includes two aspects, vertical and horizontal.
  • Longitudinal driving behavior mainly includes braking, following the car and so on.
  • the horizontal driving behavior is mainly the lane changing model.
  • the lane change behavior is a comprehensive behavioral process in which the driver adjusts and completes his own driving target strategy including information judgment and operation execution by self-driving characteristics, stimulation of surrounding environment information such as vehicle speed and neutral of surrounding vehicles. Such behavior is considered to be very complicated and even difficult to describe with mathematical models.
  • the model of lane change can be divided into two types: DLC model and MLC model.
  • the DLC is to improve the driving speed, and the MLC has to leave the lane due to the influence of intersections and the like. First, it will determine if MLC needs to be considered.
  • the DLC for the lane selection, it is determined whether the adjacent lanes need to be changed according to the comprehensive information such as the speed of the vehicle and the speed limit of the lane; and for Gap acceptance, it is judged according to the distance between the vehicles in the adjacent lanes, whether or not there is enough The lane change space. Only when this condition is met at the same time will the change decision be made.
  • the driver generally decides whether the lane change operation can be performed according to the vehicle speed, the front vehicle speed, the vehicle distance, the adjacent lane speed and the distance, in order to improve the driving speed of the vehicle.
  • the DLC and the MLC are unified into one model, and the utility of the lane and the left and right lanes are respectively calculated, and finally the lane with the largest utility is selected as the lane.
  • FIG. 6-8 are schematic diagrams showing the key parameters used in the embodiment of the present invention, the structure of the decision model, and the selection of the lane change in the actual application in the unmanned scene.
  • FIG. 6 is a schematic lane change behavior decision key parameter, wherein, S is the distance before the current vehicle lane; L 1 is a front target lane spacing; L 2 of the target lane spacing; V 1 is a lane change of the vehicle speed; V 2 is the current front lane speed; V 3 is the adjacent lane speed; V 4 is the adjacent lane rear speed.
  • FIG. 7 is a schematic structural diagram of a decision model for lane change selection
  • FIG. 8 is a schematic diagram of lane selection selection in actual application.
  • the present embodiment mainly focuses on the target lane selection of an unmanned vehicle, which is different from the conventional lane changing model.
  • the driverless vehicle only pays attention to the evaluation and selection of the target lane, and does not pay attention to whether the lane change can be performed immediately.
  • whether the lane change can be performed normally depends on the subsequent motion plan, which will judge whether the surrounding static and dynamic obstacles will affect the lane change at a higher frequency, and ensure that the lane change is safe. . If there is danger, you will give up the lane change.
  • the lane change selection process shown in FIG. 9 as an example, the following is explained:
  • the lane changing process of Figure 9 includes the following contents:
  • the first step determine the final target lane based on the intersection, that is, find the target lane for MLC.
  • the MLC target lane is determined according to the connection relationship between the intersection and the next road.
  • the lane that can reach the intersection and enter the next road is selected as the goal lane according to the connectivity. For example, if the current car is in lane 1 and needs to turn right at the intersection, then lane 2 is selected as the goal lane. If it is straight through the intersection, there may be multiple lanes to be selected that meet the requirements. At this time, the lane closest to the current lane is selected as the goal lane.
  • the number of lane changes (such as nlanechange) for each lane from the final lane. Assuming that the forward direction along the lane center line is the X-axis, the distance of the current vehicle position from the intersection is calculated, and the distance is recorded as distanceToJunction.
  • the second step estimating the lane speed, that is, calculating the route speed (DLC) based on the DLC.
  • the driving speeds of the own lane, the left lane, and the right lane are respectively estimated based on the detected speed of the surrounding vehicles.
  • d is less than a certain threshold, for example d ⁇ 2.0 m, then the vehicle belongs to this lane.
  • each lane statistics process the vehicle behind the vehicle is ignored (if the x coordinate is less than the x coordinate of the vehicle, it is ignored). If there are multiple cars, record the minimum speed as the lane speed; if there is no vehicle in front of the vehicle in the lane, record the lane speed equal to the lane maximum speed limit (such as SPEED_LIMIT).
  • Step 3 Calculate the Utility of the lane, that is, integrate the comprehensive Utility obtained by the MLC and DLC-based Utility.
  • d0 is the minimum distance required to complete a lane change based on the current vehicle speed and lane change time.
  • the calculation method is as shown in formula (3):
  • MLC uses the exponential model, which can make its influence increase rapidly with the decrease of distanceToJunction, and finally play an absolute leading role near the intersection, so that the influence of DLC can be neglected, and the intermediate transition is smooth and natural.
  • This design conforms to the actual lane change law.
  • the fourth step the determination of the type of lane change
  • the final lane change type LaneChange is to maintain the lane, change to the left, and change to the right.
  • the utility is calculated in the order of the lane, the left lane, and the right lane, and the lane with the largest utility is selected as the target lane of the lane change. This sequence ensures that overtaking is prioritized from the left lane when overtaking. If the utility is the same, then the lane is prioritized.
  • the first step calculate the utility of the current lane, record the lane change type to maintain the lane, and update uMax;
  • the DLC and the MLC are effectively combined, the transition is natural, and the lane changing behavior is more stable.
  • the key factors such as vehicle speed and intersection distance are graded to ensure the stability of the lane change results and no jitter.
  • the principle of overtaking priority on the left side is guaranteed, but the leftmost lane is not occupied for a long time.
  • the specific decision order and rules adopted by the decision model ensure that the vehicle is overtaken from the left under similar conditions; for the road with more lane data, the vehicle will occupy the leftmost super lane for a long time. This is more in line with traffic rules and in line with the objective conditions of Chinese roads.
  • a terminal (an in-vehicle terminal mounted on a target vehicle or a mobile terminal held by a user) of the embodiment of the present invention, as shown in FIG. 10, the terminal includes: a processor 61 and a storage device capable of running on the processor A memory of the computer program, one representation of which may be computer storage medium 63 as shown in FIG. 10, and a bus 62 for data communication.
  • the processor is configured to execute when the computer program is executed:
  • a decision model for lane change selection is obtained according to a first model for deciding an intersection change lane and a second model for determining a travel speed;
  • the target information being used to represent driving information of the vehicle surrounding the target vehicle;
  • the target lane is obtained by the decision model according to the target information acquired in real time and the travel information of the target vehicle.
  • the lane with the largest utility value is taken as the target lane.
  • the specific lane includes at least the own lane in which the target vehicle is currently located, the left lane and the right lane adjacent to the target vehicle.
  • a lane comprehensive utility value for a particular lane is obtained based on the first type of utility value and the second type of utility value.
  • An alternative lane is obtained according to the condition of the road network, and the road network condition is composed of an intersection and a next road connected to the intersection;
  • the minimum distance value required to complete a lane change is obtained.
  • the minimum speed of at least two vehicles is used as the lane speed limit information.
  • the lane speed is used as the vehicle speed limit information.
  • the target vehicle speed information is corrected according to the adjustment coefficient to obtain corrected speed information
  • a computer storage medium stores computer executable instructions for executing:
  • a decision model for lane change selection is obtained according to a first model for deciding an intersection change lane and a second model for determining a travel speed;
  • the target information being used to represent driving information of the vehicle surrounding the target vehicle;
  • the target lane is obtained by the decision model according to the target information acquired in real time and the travel information of the target vehicle.
  • the computer executable instructions are also used to execute:
  • the lane with the largest utility value is taken as the target lane.
  • the specific lane includes at least the own lane in which the target vehicle is currently located, the left lane and the right lane adjacent to the target vehicle.
  • the computer executable instructions are also used to execute:
  • a lane comprehensive utility value for a particular lane is obtained based on the first type of utility value and the second type of utility value.
  • the computer executable instructions are also used to execute:
  • An alternative lane is obtained according to the condition of the road network, and the road network condition is composed of an intersection and a next road connected to the intersection;
  • the minimum distance value required to complete a lane change is obtained.
  • the computer executable instructions are also used to execute:
  • the computer executable instructions are also used to execute:
  • the minimum speed of at least two vehicles is used as the lane speed limit information.
  • the computer executable instructions are also used to execute:
  • the lane speed is used as the vehicle speed limit information.
  • the computer executable instructions are also used to execute:
  • the computer executable instructions are also used to execute:
  • the target vehicle speed information is corrected according to the adjustment coefficient to obtain corrected speed information
  • the disclosed apparatus and method may be implemented in other manners.
  • the device embodiments described above are merely illustrative.
  • the division of the unit is only a logical function division.
  • there may be another division manner such as: multiple units or components may be combined, or Can be integrated into another system, or some features can be ignored or not executed.
  • the coupling, or direct coupling, or communication connection of the components shown or discussed may be indirect coupling or communication connection through some interfaces, devices or units, and may be electrical, mechanical or other forms. of.
  • the units described above as separate components may or may not be physically separated, and the components displayed as the unit may or may not be physical units, that is, may be located in one place or distributed to multiple network units; Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated into one unit;
  • the unit can be implemented in the form of hardware or in the form of hardware plus software functional units.
  • the foregoing program may be stored in a computer readable storage medium, and the program is executed when executed.
  • the foregoing steps include the steps of the foregoing method embodiments; and the foregoing storage medium includes: a removable storage device, a ROM, a RAM, a magnetic disk, or an optical disk, and the like, which can store program codes.
  • the above-described integrated unit of the present invention may be stored in a computer readable storage medium if it is implemented in the form of a software functional unit and sold or used as a standalone product.
  • the technical solution of the embodiments of the present invention may be embodied in the form of a software product in essence or in the form of a software product stored in a storage medium, including a plurality of instructions.
  • a computer device (which may be a personal computer, server, or network device, etc.) is caused to perform all or part of the methods described in various embodiments of the present invention.
  • the foregoing storage medium includes various media that can store program codes, such as a mobile storage device, a ROM, a RAM, a magnetic disk, or an optical disk.
  • a model for characterizing different decision choices is modeled to obtain a decision model for lane change selection, for example, a decision result obtained by using DLC and MLC to model speed, intersection, etc.
  • a decision model for lane change selection for example, a decision result obtained by using DLC and MLC to model speed, intersection, etc.
  • the situation is fully considered in the unmanned scene, more in line with actual needs, according to the target information related to the target vehicle acquired in real time, the driving information of the target vehicle, the target lane is obtained through the decision model, and the lane selection is performed by the obtained target lane. , to achieve accurate lane change selection, to ensure that the response time is as low as possible.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Remote Sensing (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Atmospheric Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Traffic Control Systems (AREA)
  • Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
  • Navigation (AREA)

Abstract

一种车道选择方法及目标车辆、计算机存储介质，其中，该方法包括：根据用于决策路口变道的第一模型和用于决策行驶速度的第二模型，得到用于变道选择的决策模型（101）；实时获取目标车辆的行驶信息以及与目标车辆相关的目标信息，该目标信息用于表征目标车辆周边车辆的行驶信息（102）；根据实时获取的目标信息、目标车辆的行驶信息，通过该决策模型得到目标车道（103）。

Description

一种车道选择方法及目标车辆、计算机存储介质
相关申请的交叉引用
本申请基于申请号为201710262939.9、申请日为2017年04月20日的中国专利申请提出，并要求该中国专利申请的优先权，该中国专利申请的全部内容在此引入本申请作为参考。
技术领域
本发明涉及道路选择技术，尤其涉及一种车道选择方法及目标车辆、计算机存储介质。
背景技术
在车辆行驶过程中，驾驶员会选择最合理的车道进行行驶。而在无人驾驶场景(或称无人驾驶车辆的行驶场景)中，车辆在自动驾驶时必须具备和驾驶员一样的自主选择最优车道的能力，才能在多车道的高速公路或者城市道路上行驶，否则将无法上路。二者的区别在于：用户自主驾驶的过程中，是半自动，对自动导航的路线预估后可以加入用户自己的判断，因此，可以允许有很长的响应时间；而无人驾驶是全自动，不允许有过长的响应时间，需要确保响应时间尽可能低。在无人驾驶场景中，选择最优车道会涉及到变换车道的变道行为，包括自由变道(DLC，Discretionary Lane Change)和强制变道(MLC，Mandatory lane change)两种。DLC是为了改善行驶速度，MLC是由于路口等影响必须得离开本车道。
采用现有技术，需要先判断是否需要考虑MLC，在符合一定条件后再考虑DLC，以便通过这种判断机制对驾驶员的驾驶行为进行仿真模拟。然而，这种判断机制的问题是：将DLC和MLC割裂的进行分析的判断机制， 与无人驾驶的场景，尤其是变道的选择上存在较大差异。基于该判断机制的决策结果在实际应用中并不理想，无法实现精准的变道选择，从而也无法确保响应时间尽可能低的要求。
相关技术中，对于该问题，尚无有效解决方案。
发明内容
有鉴于此，本发明实施例提供了一种车道选择方法及目标车辆、计算机存储介质，至少解决了现有技术存在的问题。
本发明实施例一种车道选择方法，所述方法包括：
根据用于决策路口变道的第一模型和用于决策行驶速度的第二模型，得到用于变道选择的决策模型；
实时获取目标车辆的行驶信息以及与目标车辆相关的目标信息，所述目标信息用于表征目标车辆周边车辆的行驶信息；
根据实时获取的所述目标信息、目标车辆的行驶信息，通过所述决策模型得到目标车道。
本发明实施例的一种目标车辆，所述目标车辆包括：
第一获取单元，配置为根据用于决策路口变道的第一模型和用于决策行驶速度的第二模型，得到用于变道选择的决策模型；
第二获取单元，配置为实时获取目标车辆的行驶信息以及与目标车辆相关的目标信息，所述目标信息用于表征目标车辆周边车辆的行驶信息；
车道确定单元，配置为根据实时获取的所述目标信息、目标车辆的行驶信息，通过所述决策模型得到目标车道。
本发明实施例的一种目标车辆，所述目标车辆包括：处理器和用于存储能够在处理器上运行的计算机程序的存储器；其中，所述处理器用于运行所述计算机程序时，执行上述方案任一项所述的车道选择方法。
本发明实施例的一种计算机存储介质，所述计算机存储介质中存储有 计算机可执行指令，该计算机可执行指令用于执行上述方案任一项所述的车道选择方法。
本发明实施例的一种车道选择方法，所述方法由目标车辆执行，所述目标车辆包括有一个或多个处理器以及存储器，以及一个或一个以上的程序，其中，所述一个或一个以上的程序存储于存储器中，所述程序可以包括一个或一个以上的每一个对应于一组指令的单元，所述一个或多个处理器被配置为执行指令；所述方法包括：
根据用于决策路口变道的第一模型和用于决策行驶速度的第二模型，得到用于变道选择的决策模型；
实时获取目标车辆的行驶信息以及与目标车辆相关的目标信息，所述目标信息用于表征目标车辆周边车辆的行驶信息；
根据实时获取的所述目标信息、目标车辆的行驶信息，通过所述决策模型得到目标车道。
采用本发明实施例，根据用于表征不同决策选择的模型建模，以得到用于变道选择的决策模型，比如，采用DLC和MLC来建模得到的决策结果，可以将速度和路口等影响情况都全面考虑到无人驾驶场景中，更符合实际需求，根据实时获取的与目标车辆相关的目标信息、目标车辆的行驶信息，通过决策模型得到目标车道，由得到的目标车道来执行车道选择，实现了精准的变道选择，能确保响应时间尽可能低。
附图说明
图1为实现本发明各个实施例目标车辆上安装的车载终端或用户手持的移动终端的一个可选的硬件结构示意图；
图2为如图1所示的移动终端的通信系统示意图；
图3为本发明实施例中进行信息交互的各方硬件实体的示意图；
图4为本发明实施例一方法的实现流程示意图；
图5为本发明实施例一系统架构的示意图；
图6为应用本发明实施例一车道变换行为决策的关键参数示意图；
图7为应用本发明实施例一用于变道选择的决策模型的结构示意图；
图8为应用本发明实施例一实际应用中采样的变道选择情况示意图；
图9为应用本发明实施例一变道选择过程示意图；
图10为本发明实施例目标车辆上安装的车载终端或用户手持的移动终端的硬件结构图。
具体实施方式
下面结合附图对技术方案的实施作进一步的详细描述。
现在将参考附图描述实现本发明各个实施例的移动终端。在后续的描述中，使用用于表示元件的诸如“模块”、“部件”或“单元”的后缀仅为了有利于本发明实施例的说明，其本身并没有特定的意义。因此，"模块"与"部件"可以混合地使用。
在下面的详细说明中，陈述了众多的具体细节，以便彻底理解本发明。不过，对于本领域的普通技术人员来说，显然可在没有这些具体细节的情况下实践本发明。在其他情况下，没有详细说明公开的公知方法、过程、组件、电路和网络，以避免不必要地使实施例的各个方面模糊不清。
另外，本文中尽管多次采用术语“第一”、“第二”等来描述各种元件(或各种阈值或各种应用或各种指令或各种操作)等，不过这些元件(或阈值或应用或指令或操作)不应受这些术语的限制。这些术语只是用于区分一个元件(或阈值或应用或指令或操作)和另一个元件(或阈值或应用或指令或操作)。例如，第一操作可以被称为第二操作，第二操作也可以被称为第一操作，而不脱离本发明的范围，第一操作和第二操作都是操作，只是二者并不是相同的操作而已。
本发明实施例中的步骤并不一定是按照所描述的步骤顺序进行处理， 可以按照需求有选择的将步骤打乱重排，或者删除实施例中的步骤，或者增加实施例中的步骤，本发明实施例中的步骤描述只是可选的顺序组合，并不代表本发明实施例的所有步骤顺序组合，实施例中的步骤顺序不能认为是对本发明的限制。
本发明实施例中的术语“和/或”指的是包括相关联的列举项目中的一个或多个的任何和全部的可能组合。还要说明的是：当用在本说明书中时，“包括/包含”指定所陈述的特征、整数、步骤、操作、元件和/或组件的存在，但是不排除一个或多个其他特征、整数、步骤、操作、元件和/或组件和/或它们的组群的存在或添加。
本文的“目标车辆”是指：在无人驾驶场景中自动驾驶的汽车，或者可以称为自车。
本发明实施例的智能终端(如移动终端)可以以各种形式来实施。例如，本发明实施例中描述的移动终端可以包括诸如移动电话、智能电话、笔记本电脑、数字广播接收器、个人数字助理(PDA，Personal Digital Assistant)、平板电脑(PAD)、便携式多媒体播放器(PMP，Portable Media Player)、导航装置等等的移动终端以及诸如数字TV、台式计算机等等的固定终端。下面，假设终端是移动终端。然而，本领域技术人员将理解的是，除了特别用于移动目的的元件之外，根据本发明的实施方式的构造也能够应用于固定类型的终端。
图1为实现本发明各个实施例的移动终端一个可选的硬件结构示意图。移动终端100不限于车载终端或手机终端。本实施例中，所述移动终端置于目标车辆内。
移动终端100为车载终端时，可以包括：GPS定位单元111、无线通信单元112、无线互联网单元113、报警通信单元114、地图单元121、语音单元122、用户输入单元130、第一获取单元140、第二获取单元141、车道 确定单元142、输出单元150、显示单元151、音频输出单元152、存储单元160、接口单元170、处理单元180和电源单元190等等。图1示出了具有各种组件的移动终端，但是应理解的是，并不要求实施所有示出的组件。可以替代地实施更多或更少的组件。将在下面详细描述车载终端的元件。
GPS定位单元111用于接收卫星所传递的信息，以检查或获取车载终端的位置信息，比如，根据所传递的信息进行单星定位或双星定位等，以确定车辆相对于导航路径的位置或者导航路径上某个车道的位置等。具体的，计算来自三个或更多卫星的距离信息和准确的时间信息并且对于计算的信息应用三角测量法，从而根据经度、纬度和高度准确地计算三维当前位置信息。当前，用于计算位置和时间信息的方法使用三颗卫星并且通过使用另外的一颗卫星校正计算出的位置和时间信息的误差。此外，GPS定位单元111还能够通过实时地连续计算当前位置信息来计算速度信息，得到当前车辆的车速信息。
无线通信单元112，其允许车载终端与无线通信系统或网络之间的无线电通信。例如，无线通信单元进行通信的形式多种多样，可以采用广播的形式、Wi-Fi通信形式、移动通信(2G、3G或4G)形式等与后台服务器进行通信交互。其中，采用广播的形式进行通信交互时，可以经由广播信道从外部广播管理服务器接收广播信号和/或广播相关信息。广播信道可以包括卫星信道和/或地面信道。广播管理服务器可以是生成并发送广播信号和/或广播相关信息的服务器或者接收之前生成的广播信号和/或广播相关信息并且将其发送给终端的服务器。广播信号可以包括TV广播信号、无线电广播信号、数据广播信号等等。而且，广播信号可以进一步包括与TV或无线电广播信号组合的广播信号。广播相关信息也可以经由移动通信网络提供。广播信号可以以各种形式存在，例如，其可以以数字多媒体广播(DMB，Digital Multimedia Broadcasting)的电子节目指南(EPG，Electronic  Program Guide)、数字视频广播手持(DVB-H，Digital Video Broadcasting-Handheld)的电子服务指南(ESG，Electronic Service Guide)等等的形式而存在。广播信号和/或广播相关信息可以存储在存储单元160(或者其它类型的存储介质)中。Wi-Fi是一种可以将个人电脑、移动终端(如车载终端、手机终端)等终端以无线方式互相连接的技术，采用Wi-Fi通信形式时，能够访问Wi-Fi热点进而接入Wi-Fi网络。Wi-Fi热点是通过在互联网连接上安装访问点来创建的。这个访问点将无线信号通过短程进行传输，一般覆盖300英尺。当支持Wi-Fi的车载终端遇到一个Wi-Fi热点时，就可以用无线方式连接到Wi-Fi网络中。采用移动通信(2G、3G或4G)形式时，将无线电信号发送到基站(例如，接入点、节点B等等)、外部终端以及服务器中的至少一个和/或从其接收无线电信号。这样的无线电信号可以包括语音通话信号、视频通话信号、或者根据文本和/或多媒体消息发送和/或接收的各种类型的数据。
无线互联网单元113支持车载终端的包括无线在内的各种数据传输通讯技术，以便接入互联网。该单元可以内部或外部地耦接到车载终端。该单元所涉及的无线互联网接入技术可以包括无线局域网络(WLAN，Wireless Local Area Networks)、无线宽带(Wibro)、全球微波互联接入(Wimax)、高速下行链路分组接入(HSDPA，High Speed Downlink Packet Access)等等。
报警通信单元114，配置为向后台服务器发出报警讯号，通报车辆异常信息。具体的，是将通过GPS定位单位得到当前车辆位置信息和该车辆异常信息一起打包传到后台服务器，如报警或监控中心进行处理。地图单元121，配置为存储地图信息，地图信息可以是在线下载后离线使用的地图信息，也可以是实时下载的地图信息。地图信息还可以及时最新。语音单元122，配置为执行语音操作，一方面，可以接收用户的语音命令，另一方面， 可以结合当前的车辆位置和导航信息、车辆异常信息的后台处理结果进行语音播报，提醒用户注意路况等。
车载终端可以应用2G、3G或4G、无线技术等，支持高速数据传输，同时传送声音及数据信息，开放接口，无限应用，车载终端能够更轻松地与各种I/O设备配合使用。
用户输入单元130可以根据用户输入的命令生成键输入数据以控制车载终端的各种操作。用户输入单元130允许用户输入各种类型的信息，并且可以包括键盘、鼠标、触摸板(例如，检测由于被接触而导致的电阻、压力、电容等等的变化的触敏组件)、滚轮、摇杆等等。特别地，当触摸板以层的形式叠加在显示单元151上时，可以形成触摸屏。
第一获取单元140，配置为根据用于决策路口变道的第一模型和用于决策行驶速度的第二模型，得到用于变道选择的决策模型；第二获取单元141，配置为实时获取目标车辆的行驶信息以及与目标车辆相关的目标信息，所述目标信息用于表征目标车辆周边车辆的行驶信息；车道确定单元142，配置为根据实时获取的所述目标信息、目标车辆的行驶信息，通过所述决策模型得到目标车道。
接口单元170用作至少一个外部装置与车载终端连接可以通过的接口。例如，外部装置可以包括有线或无线头戴式耳机端口、外部电源(或电池充电器)端口、有线或无线数据端口、存储卡端口、用于连接具有识别单元的装置的端口、音频输入/输出(I/O)端口、视频I/O端口、耳机端口等等。识别单元可以是存储用于验证用户使用车载终端的各种信息并且可以包括用户识别单元(UIM，User Identify Module)、客户识别单元(SIM，Subscriber Identity Module)、通用客户识别单元(USIM，Universal Subscriber Identity Module)等等。另外，具有识别单元的装置(下面称为"识别装置")可以采取智能卡的形式，因此，识别装置可以经由端口或其它连接装置与 车载终端连接。接口单元170可以用于接收来自外部装置的输入(例如，数据信息、电力等等)并且将接收到的输入传输到车载终端内的一个或多个元件或者可以用于在车载终端和外部装置之间传输数据。
另外，当车载终端与外部底座连接时，接口单元170可以用作允许通过其将电力从底座提供到车载终端的路径，或者可以用作允许从底座输入的各种命令信号通过其传输到车载终端的路径。从底座输入的各种命令信号或电力可以用作用于识别车载终端是否准确地安装在底座上的信号。输出单元150被构造为以视觉、音频和/或触觉方式提供输出信号(例如，音频信号、视频信号、振动信号等等)。输出单元150可以包括显示单元151、音频输出单元152等等。
显示单元151可以显示在车载终端中处理的信息。例如，车载终端可以显示相关用户界面(UI，User Interface)或图形用户界面(GUI，Graphical User Interface)。当车载终端处于视频通话模式或者图像捕获模式时，显示单元151可以显示捕获的图像和/或接收的图像、示出视频或图像以及相关功能的UI或GUI等等。
同时，当显示单元151和触摸板以层的形式彼此叠加以形成触摸屏时，显示单元151可以用作输入装置和输出装置。显示单元151可以包括液晶显示器(LCD，Liquid Crystal Display)、薄膜晶体管LCD(TFT-LCD，Thin Film Transistor-LCD)、有机发光二极管(OLED，Organic Light-Emitting Diode)显示器、柔性显示器、三维(3D)显示器等等中的至少一种。这些显示器中的一些可以被构造为透明状以允许用户从外部观看，这可以称为透明显示器，典型的透明显示器可以例如为透明有机发光二极管(TOLED)显示器等等。根据特定想要的实施方式，车载终端可以包括两个或更多显示单元(或其它显示装置)，例如，车载终端可以包括外部显示单元(未示出)和内部显示单元(未示出)。触摸屏可用于检测触摸输入压力以及触摸 输入位置和触摸输入面积。
音频输出单元152可以在车载终端处于呼叫信号接收模式、通话模式、记录模式、语音识别模式、广播接收模式等等模式下时，将接收的或者在存储单元160中存储的音频数据转换音频信号并且输出为声音。而且，音频输出单元152可以提供与车载终端执行的特定功能相关的音频输出(例如，呼叫信号接收声音、消息接收声音等等)。音频输出单元152可以包括扬声器、蜂鸣器等等。
存储单元160可以存储由处理单元180执行的处理和控制操作的软件程序等等，或者可以暂时地存储已经输出或将要输出的数据(例如，电话簿、消息、静态图像、视频等等)。而且，存储单元160可以存储关于当触摸施加到触摸屏时输出的各种方式的振动和音频信号的数据。
存储单元160可以包括至少一种类型的存储介质，所述存储介质包括闪存、硬盘、多媒体卡、卡型存储器(例如，SD或DX存储器等等)、随机访问存储器(RAM，Random Access Memory)、静态随机访问存储器(SRAM，Static Random Access Memory)、只读存储器(ROM，Read Only Memory)、电可擦除可编程只读存储器(EEPROM，Electrically Erasable Programmable Read Only Memory)、可编程只读存储器(PROM，Programmable Read Only Memory)、磁性存储器、磁盘、光盘等等。而且，车载终端可以与通过网络连接执行存储单元160的存储功能的网络存储装置协作。
处理单元180通常控制车载终端的总体操作。例如，处理单元180执行与语音通话、数据通信、视频通话等等相关的控制和处理。又如，处理单元180可以执行模式识别处理，以将在触摸屏上执行的手写输入或者图片绘制输入识别为字符或图像。
电源单元190在处理单元180的控制下接收外部电力或内部电力并且 提供操作各元件和组件所需的适当的电力。
这里描述的各种实施方式可以以使用例如计算机软件、硬件或其任何组合的计算机可读介质来实施。对于硬件实施，这里描述的实施方式可以通过使用特定用途集成电路(ASIC，Application Specific Integrated Circuit)、数字信号处理器(DSP，Digital Signal Processing)、数字信号处理装置(DSPD，Digital Signal Processing Device)、可编程逻辑装置(PLD，Programmable Logic Device)、现场可编程门阵列(FPGA，Field Programmable Gate Array)、处理器、控制器、微控制器、微处理器、被设计为执行这里描述的功能的电子单元中的至少一种来实施，在一些情况下，这样的实施方式可以在处理单元180中实施。对于软件实施，诸如过程或功能的实施方式可以与允许执行至少一种功能或操作的单独的软件单元来实施。软件代码可以由以任何适当的编程语言编写的软件应用程序(或程序)来实施，软件代码可以存储在存储单元160中并且由处理单元180执行。其中，存储单元160的一个具体硬件实体可以为存储器，处理单元180的一个具体硬件实体可以为控制器。
至此，已经按照其功能描述了移动终端中以车载终端为代表的上述单元组成结构。
如图1中所示的移动终端100可以被构造为利用经由帧或分组发送数据的诸如有线和无线通信系统以及基于卫星的通信系统来操作。
现在将参考图2描述其中根据本发明实施例的移动终端100能够操作的通信系统。
这样的通信系统可以使用不同的空中接口和/或物理层。例如，由通信系统使用的空中接口包括例如频分多址(FDMA，Frequency Division Multiple Access)、时分多址(TDMA，Time Division Multiple Access)、码分多址(CDMA，Code Division Multiple Access)和通用移动通信系统 (UMTS，Universal Mobile Telecommunications System)(特别地，长期演进(LTE，Long Term Evolution))、全球移动通信系统(GSM)等等。作为非限制性示例，下面的描述涉及CDMA通信系统，但是这样的教导同样适用于其它类型的系统。
参考图2，CDMA无线通信系统可以包括多个移动终端100、多个基站(BS，Base Station)270、基站控制器(BSC，Base Station Controller)275和移动交换中心(MSC，Mobile Switching Center)280。MSC280被构造为与公共电话交换网络(PSTN，Public Switched Telephone Network)290形成接口。MSC280还被构造为与可以经由回程线路耦接到BS270的BSC275形成接口。回程线路可以根据若干已知的接口中的任一种来构造，所述接口包括例如E1/T1、ATM、IP、PPP、帧中继、HDSL、ADSL或xDSL。将理解的是，如图2中所示的系统可以包括多个BSC275。
每个BS 270可以服务一个或多个分区(或区域)，由多向天线或指向特定方向的天线覆盖的每个分区放射状地远离BS 270。或者，每个分区可以由用于分集接收的两个或更多天线覆盖。每个BS 270可以被构造为支持多个频率分配，并且每个频率分配具有特定频谱(例如，1.25MHz，5MHz等等)。
分区与频率分配的交叉可以被称为CDMA信道。BS 270也可以被称为基站收发器子系统(BTS，Base Transceiver Station)或者其它等效术语。在这样的情况下，术语“基站”可以用于笼统地表示单个BSC275和至少一个BS 270。基站也可以被称为“蜂窝站”。或者，特定BS 270的各分区可以被称为多个蜂窝站。
如图2中所示，广播发射器(BT，Broadcast Transmitter)295将广播信号发送给在系统内操作的移动终端100。如图1中所示的广播接收单元111被设置在移动终端100处以接收由BT295发送的广播信号。在图2中，示 出了几个卫星300，例如可以采用全球定位系统(GPS)卫星300。卫星300帮助定位多个移动终端100中的至少一个。
在图2中，描绘了多个卫星300，但是理解的是，可以利用任何数目的卫星获得有用的定位信息。如图1中所示的位置信息单元115通常被构造为与卫星300配合以获得想要的定位信息。替代GPS跟踪技术或者在GPS跟踪技术之外，可以使用可以跟踪移动终端的位置的其它技术。另外，至少一个GPS卫星300可以选择性地或者额外地处理卫星DMB传输。
作为无线通信系统的一个典型操作，BS 270接收来自各种移动终端100的反向链路信号。移动终端100通常参与通话、消息收发和其它类型的通信。特定基站接收的每个反向链路信号被在特定BS 270内进行处理。获得的数据被转发给相关的BSC275。BSC提供通话资源分配和包括BS 270之间的软切换过程的协调的移动管理功能。BSC275还将接收到的数据路由到MSC280，其提供用于与PSTN290形成接口的额外的路由服务。类似地，PSTN290与MSC280形成接口，MSC与BSC275形成接口，并且BSC275相应地控制BS 270以将正向链路信号发送到移动终端100。
移动终端中通信单元110的移动通信单元112基于移动终端内置的接入移动通信网络(如2G/3G/4G等移动通信网络)的必要数据(包括用户识别信息和鉴权信息)接入移动通信网络为移动终端用户的网页浏览、网络多媒体播放等业务传输移动通信数据(包括上行的移动通信数据和下行的移动通信数据)。
通信单元110的无线互联网单元113通过运行无线热点的相关协议功能而实现无线热点的功能，无线热点支持多个移动终端(移动终端之外的任意移动终端)接入，通过复用移动通信单元112与移动通信网络之间的移动通信连接为移动终端用户的网页浏览、网络多媒体播放等业务传输移动通信数据(包括上行的移动通信数据和下行的移动通信数据)，由于移动 终端实质上是复用移动终端与通信网络之间的移动通信连接传输移动通信数据的，因此移动终端消耗的移动通信数据的流量由通信网络侧的计费实体计入移动终端的通信资费，从而消耗移动终端签约使用的通信资费中包括的移动通信数据的数据流量。
图3为本发明实施例中进行信息交互的各方硬件实体的示意图，图3中包括：终端设备1和服务器2。其中，终端设备1由终端设备11-14构成，终端设备通过有线网络或者无线网络与服务器进行信息交互。终端设备可以为目标车辆上安装的车载终端或用户手持的移动终端。终端设备配置在行驶的车辆上，每个车辆上都可以配置终端设备，以便通过终端设备与后台服务器的数据交互，得到各种用于无人驾驶的控制信息。首先需要明确自动驾驶和无人驾驶的区别，用户自主驾驶的过程中，是半自动，对自动导航的路线预估后可以加入用户自己的判断，因此，可以允许有很长的响应时间；而无人驾驶是全自动，不允许有过长的响应时间，需要确保响应时间尽可能低。在无人驾驶场景中，选择最优车道会涉及到变换车道的变道行为，包括DLC和MLC两种。DLC是为了改善行驶速度，MLC是由于路口等影响必须得离开本车道，比如，需要先判断是否需要考虑MLC，在符合一定条件后再考虑DLC，以便通过这种判断机制对驾驶员的驾驶行为进行仿真模拟。然而，这种判断机制存在的问题是：将DLC和MLC割裂的进行分析的判断机制，会将DLC和MLC这2个模型完全割裂，一方面，会导致场景切换的过度不够自然，可能会出现上次还是向左变道，还没执行完，接下来又决定向右变道的情况，也就是说，现有的这种判断机制与本实施例要讨论的无人驾驶场景相比，在变道的选择上尤其是存在较大的差异，无法确保响应时间尽可能低的要求，并不适用于无人驾驶场景。另一方面，基于该判断机制的决策结果，在实际应用中受当前车辆车速影响较大，结果不够稳定，比如，当车速稍微发生变化时，就可能会出现来回 切换的情况，也无法实现精准的变道选择，也无法确保响应时间尽可能低的要求。另，现有的这种判断机制对所有车道都是平等处理的，不能采用从左侧车道的超车等需求。
而采用本发明实施例，终端设备的处理逻辑10如图3所示，处理逻辑10包括：S1、获取与目标车辆相关的目标信息，所述目标信息用于表征目标车辆周边车辆的行驶信息；S2、获取目标车辆信息；S3、根据用于决策路口变道的第一模型和用于决策行驶速度的第二模型得到用于变道选择的决策模型；S4、将实时获取的数据，包括目标车辆信息和目标车辆相关的目标信息，如当前车辆的信息和与当前车辆相关车辆的信息输入该决策模型中运算，得到控制指令，根据所述控制指令执行车道选择。
可见，所用的运算逻辑可以在目标车辆上安装的车载终端或用户手持的移动终端生成及执行对应的处理，服务器用于提供目标车辆需要的各种数据源，包括当前车辆及与当前车辆相关的其他车辆，可以将这些数据存储于目标车辆上安装的车载终端或用户手持的移动终端中，通过控制指令来执行车道选择。本发明实施例不限于运算逻辑在服务器中，则服务器收到请求后，执行运算逻辑，将控制指令实时下发给车辆，用于根据控制指令来执行车道选择，不过，由于网络交互的多重风险，将运算逻辑置于服务器可能会因为网络交互带来的数据交互延迟而导致本实施例无人驾驶场景中响应时间的增加，从而增加无人驾驶的风险，不利于风险控制。将运算逻辑置于目标车辆上安装的车载终端或用户手持的移动终端中虽然会一定程度上增加处理难度，但是控制指令的下发不受网络数据交互的影响，可以实时操控车辆的变道选择，因此，能很大程度上确保无人驾驶场景中的响应时间，也能确保变道选择的精准性。
上述图3的例子只是实现本发明实施例的一个系统架构实例，本发明实施例并不限于上述图3所述的系统结构，基于上述图3所述的系统架构， 提出本发明方法各个实施例。
本发明实施例的车道选择方法，如图4所示，所述方法包括：根据用于决策路口变道的第一模型和用于决策行驶速度的第二模型，得到用于变道选择的决策模型(101)。一个实例是：1)第一模型为MLC，用于评估当前车辆行驶到路口需要的时间t，是否大于变换车道所需要的时间，采用MLC，是对路口变道进行决策，比如当前由于路口等影响必须得离开本车道。2)第二模型为DLC，DLC的决策分为车道选择(lane selection)和确定变道的接纳(Gap acceptance)两步。其中，在lane selection中，是根据车速、车道限速等综合信息判定相邻车道是否需要变道；而Gap acceptance中，是根据相邻车道前后车的距离来判断，是否拥有总够的变道空间。只有这2个条件同时满足，才会做出变道决策。采用DLC，是对行驶速度进行改善，比如，前车距离后车比较近，那么需要减速，如果前车距离后车允许超车，则加速。实时获取目标车辆的行驶信息以及与目标车辆相关的目标信息，所述目标信息用于表征目标车辆周边车辆的行驶信息(102)。目标信息包括但不限于：1)周边车辆的地理位置信息，需要指出的是：该信息是一种绝对位置信息；2)周边车辆相对于目标车辆的距离信息，需要指出的是：区别于地理位置信息，是一种相对位置信息；3)周边车辆挂空档(如在路边停车休息)时的周边环境、周边车辆的速度信息；4)存在多条车道可以进行选择时周边车辆当前行驶于哪一个车道上等等。一个实例是：在驾驶过程中，可以根据本车车速、前车车速、车距；相邻车道车速与车距来决策是否可以进行变道操作，目的是为了改善本车的行驶速度。根据实时获取的所述目标信息、目标车辆的行驶信息，通过所述决策模型得到目标车道(103)。一个实例是：通过计算本车道、左右车道的多个效用值(utility)，最后，选择多个utility中utility最大的车道作为用于车道选择的变换车道。
进一步的，还可以根据所述目标车辆相关的目标信息，实时获取的目标车辆信息和所述决策模型得到控制指令，根据所述控制指令执行无人驾驶中的车道选择。在车辆自动行驶或手动加速场景中，驾驶员会选择最合理的车道进行行驶。而采用本发明实施例的无人驾驶场景中，车辆必须具备和驾驶员一样的自主选择最优车道的能力，才能在多车道的高速公路或者城市道路上行驶，否则将无法上路。采用本发明实施例，是一种综合周围车辆和导航路径的车道选择方案，根据DLC和MLC建模，以将DLC和MLC统一到一个新建得到的决策模型当中。分别计算本车道、左右车道的utility，最后选择utility最大的车道作为用于变道选择的变换车道，从而解决了无人驾驶车辆自主选择车道的问题。本发明实施例有效结合了DLC和MLC的优势，得到了更加优化的决策模型，采用该决策模型，当离路口越远的情况下，DLC模型起主要作用；当离路口越近的情况下，受到MLC模型的影响就越大，保证了在一定距离范围内选择的目标车道的稳定性，不会来回切换。
另一个实例是：1)根据目标车辆变道次数(如nlanechange)、目标车辆距离路口的距离值(如distanceToJunction)和单次变道最小距离值(如d0)，确定各个车道与所述第一模型相关的第一类utility。本实施例中，所述第一类utility包括分别对应目标车辆当前所在的本车道、与目标车辆相邻的左侧车道和右侧车道的值，比如，可以采取公式：U_MLC＝p2×pow(nlanechange/(distanceToJunction/d0)，p3)来计算该类utility。其中，p2和p3为权重值。pow函数是将第二个参数作为第一个参数的幂自乘，它是对时间系列起作用的一种二进制算术函数。可选的，第一模型，如MLC，可以使用指数模型，这样处理的好处是：使得MLC的影响力随着该目标车辆距离路口的距离值的逐渐变小而迅速增大，最终在路口附近起绝对主导作用，进而可以忽略第二模型如DLC的影响，中间的过渡是平滑自然的。这 样设计符合实际的变道规律。2)根据目标车辆车速信息(如laneSpeed)及车道限速信息(如SPEED_LIMIT)确定与所述第二模型相关的第二类utility。本实施例中，对应目标车辆当前所在的本车道、与目标车辆相邻的左侧车道和右侧车道，分别计算所述第二类效用值。比如，可以采用公式：U_DLC＝p1×laneSpeed/SPEED_LIMIT来计算该类utility。其中，p1为权重值。3)根据所述第一类utility和所述第二类utility得到车道综合utility，所述车道综合utility包括分别对应目标车辆当前所在的本车道、与目标车辆相邻的左侧车道和右侧车道的车道综合utility，即：采用公式：Utility＝(int)U_DLC–(int)U_MLC得到该车道综合utility。其中，先分别对U_DLC和U_MLC取整数，然后再计算综合utility。这样处理的好处是：相当于对车速、距离等关键因素进行了分段分级，最大优点是可以在一定的车速范围和距离范围内保持utility的数值稳定性，进一步保证换道结果的稳定性，不会来回切换。
最终，根据所述目标车辆相关的目标信息，实时获取的目标车辆信息和所述决策模型得到控制指令，根据所述控制指令执行无人驾驶中的车道选择。一个实例是：通过计算本车道、左右车道的多个utility，最后，选择多个utility中utility最大的车道作为用于车道选择的变换车道。也就是说，从分别对应目标车辆当前所在的本车道、与目标车辆相邻的左侧车道和右侧车道的车道综合utility中，选择车道综合utility最大的车道，将所述车道综合utility最大的车道决策为用于变道选择的目标车道。
本发明实施例的车道选择方法中，根据目标车辆变道次数和目标车辆距离路口的距离值，确定与所述第一模型相关的第一类效用值之前，还可以根据路网情况得到备选车道。该备选车道也可以称为备选的目标车道，这个备选并不一定是最终选择要变道的目标车道，只是为了初始的运算需要先建立一个参照物；备选的目标车道还可以是最终路口需要分叉的最终 目的车道，不限于这里的可能性。
本发明实施例中，所述路网情况由路口(如十字路口，二岔路口，三岔路口等)及与所述路口相连的下一个道路构成。在实际应用中，根据路口和下一条道路的连接关系确定MLC目标车道。在当前位置待选的车道里，根据连通性挑选可以到达路口并进入下一条道路的车道作为目标车道。例如当前本车在车道1，在路口需要右拐，则选择车道2作为目标车道。如果是直行通过路口的话，可能会有多条待选车道符合要求，此时选定其中离当前车道最近的车道当做目标车道。根据目标车辆当前所在本车道与所述备选车道在第一方向(如Y轴)上的距离，得到所述目标车辆变道次数，也就是说，在确定了最终目标车道之后，可以计算当前每条车道距离最终车道的变道次数。相对于第一方向(如Y轴)而言，本文中的第二方向可以为X轴。X轴为与沿车道中心线向前的方向，则Y轴为与其呈垂直的方向。一个实施例中，如果将第一方向和第二方向放到平面直角坐标系中进行表示，平面直角坐标系中有两个坐标轴，其中横轴为X轴，取向右方向为正方向；纵轴为Y轴，取向上为正方向。
根据目标车辆当前所在本车道上的位置与所述路口在X轴上的距离，计算当前车辆位置距离路口的距离，以得到所述目标车辆距离路口的距离值(如distanceToJunction)。根据目标车辆当前车速和变道时间，得到完成一次变道所需要的所述单次变道最小距离值(如d0)。
本发明实施例的车道选择方法中，在根据目标车辆车速信息及车道限速信息，确定与所述第二模型相关的第二类utility之前，根据检测到的目标车辆周边车辆的速度信息，计算并实时调整所述目标车辆的车速信息。
在无人驾驶车辆的目标车道选择中，为了确保响应时间尽量短，需要无人驾驶车辆以较高的频率来判断周围的车辆的行驶情况，比如，需要关 注目标车辆周边车辆的速度信息，以便根据该速度信息来动态实时调整目标车辆的速度，比如，估计目标车辆的速度，可以根据检测到的周围车辆的速度来分别估计本车道、左侧车道、右侧车道的行车速度，以确保无人驾驶场景中目标车辆的行驶安全、及后续确定出目标车道后的变道安全。无人驾驶车辆和自动驾驶车辆的场景最大的区别是：是否加入用户自己的判断。自动驾驶车辆的场景中，对自动导航的路线预估后可以加入用户自己的判断，实际是对用户自主驾驶的辅助功能，而无人驾驶依赖于决策模型，是全自动的，需要确保响应时间尽可能低，才可以确保无人驾驶场景中目标车辆的行驶安全、及后续确定出目标车道后的变道安全，如发现有危险的话，会放弃变道。
本发明实施例的车道选择方法中，获取目标车辆中心点(如目标车辆车轴上的任意点，或者车辆整体的中心点)到当前车道中心线的垂直距离，判断所述垂直距离是否小于阈值，当小于阈值时确定出目标车辆隶属于所述当前车道，根据在所述当前车道的预设规则得到所述车道限速信息。比如，根据车辆中心点到车道中心线的垂直距离d，来判定车辆属于哪条车道。当d小于一定阈值，例如d<2.0m时，则车辆属于此车道。
需要指出的是，本文中车道速度，是参考车辆在当前车道上行驶的速度得到的，一个特例中，当前车道上只有目标车辆一个车辆的场景中，车道速度等于目标车辆在当前车道上行驶的速度。相应的，车道限速信息与目标车辆的车道速度有关，这不同于道路上限速指示牌所指示的限速指标，比如，交通规则中规定高速公路的限速通常为60-120km/h，高速公路某个路段指示牌所指示的限速指标为90km/h。
本文中的车道速度和车道限速信息是根据目标车辆周边车辆的行驶情况(如车速信息)实时动态调整的，不是上述所规定的限速指标为一个固定值。下面举两个实施例进行对此进行描述。
一、本发明实施例的车道选择方法中，根据在所述当前车道的预设规则得到所述车道限速信息的过程中，在所述当前车道检测到包括所述目标车辆在内的至少两辆车时，记录其中最小的速度作为车道速度，将至少两辆车中最小的速度，即该车道速度作为所述车道限速信息。其中，就车道速度而言，可以根据当前车道上目标车辆周边车辆的行驶速度来对自身行驶的速度进行调整，比如，在车道速度为80公里/小时的当前车道上，所述目标车辆行驶方向上有一辆车(记为车辆B)，当前车速为70公里/小时，而该目标车辆本身(记为车辆A)，当前车速为75公里/小时，由于车辆B位于车辆A的前方，因此，为了避免出现追尾等交通安全问题，车道限速信息取车辆A和车辆B中的最小值，即将70公里/小时作为车道限速信息。
二、本发明实施例的车道选择方法中，根据在所述当前车道的预设规则得到所述车道限速信息的过程中，在所述当前车道检测到所述目标车辆行驶方向上没有其它车辆时，将车道速度作为所述车道限速信息。一个实例中，如果车道里没有自车身前的车辆，则记录车道速度等于车道最大限速。其中，就车道速度而言，可以根据交通规则中的规定，如道路上限速指示牌所指示的限速指标来执行，比如，在车道速度为120公里/小时的当前车道上，所述目标车辆行驶方向上没有任何车辆，即该目标车辆本身(记为车辆A)前方没有任何车辆，存在交通安全隐患的可能性非常低，因此，车道限速信息取车道速度，即将120公里/小时作为车道限速信息。
本发明实施例的车道选择方法中，检测在所述当前车道中位于所述目标车辆后方存在其它车辆时，忽略比所述目标车辆靠后的其它车辆。在每个车道统计过程中，如果一车辆B的X坐标(或称横坐标)小于本车辆A的X坐标(或称横坐标)，其中，车辆A为目标车辆，车辆B为其他车辆，X轴为与沿车道中心线向前的方向，则忽略比目标车辆靠后的车辆，其有益效果为：在无人驾驶中，无论考虑到行驶安全和变道安全，更需要关注 目标车辆前面车辆的行驶速度，避免目标车辆与其追尾，而目标车辆后面的车辆则无需过多关注，蒋目标车辆后面的车辆进行忽略，除了排除无需关注的因素来提高决策模型的运算精度之外，还可以提高决策模型的运算速度。这个实施例想说明的是决策策略中的忽略策略，以忽略比所述终端靠后的其它车辆。决策策略中还可以包括其他策略，比如，对路口距离的判断需要设置有个预先的最小距离看是否变道或者采取减速策略等。
本发明实施例的车道选择方法中，当所述当前车道的数量大于等于3，且所述终端当前位于左侧车道上，左侧车道只是为了方便描述的一个指代词，包括但不限于：多个车辆长时间占用的快速车道。为了避免车辆不会长期占用最左车道的情况，需要根据调整系数对所述终端车速信息进行修正处理，得到修正速度信息。根据所述修正速度信息及车道限速信息，确定与所述第二模型相关的第二类utility。比如，当车道数据>＝3，本车当前在最左车道上，在计算laneSpeed时，在统计的基础上给一个折扣系数，使用k×laneSpeed(一般情况下k＝0.9)作为车道速度参与之后U_DLC计算。这样处理的好处是：保证了在同等情况下，车辆不会长期占用最左车道的情况。
本发明实施例的车道选择方法中，在根据所述控制指令执行无人驾驶中的车道选择的过程中，1)所述控制指令为保持在本车道行驶时，不执行变化到所述目标车道的变道处理。2)所述控制指令为向左侧车道变道时，将所述左侧车道作为所述目标车道并执行变化到所述目标车道的变道处理。3)所述控制指令为向右侧车道变道时，将所述右侧车道作为所述目标车道并执行变化到所述目标车道的变道处理。通过这些手段来实现变道类型的判定。最终的变道类型分别是保持本车道、向左变道、向右变道三种情况。
一个实例中，可以按照本车道、左车道和右车道的顺序计算utility，选定utility最大的车道作为变道的目标车道。这种顺序保证了超车时优先从左侧车道超车。如果utility一样，则优先保持本车道。1)可以计算当前车道的utility，记录变道类型为保持本车道，更新uMax；2)计算左侧车道的utility，记做u_left。如果u_left>u_uMax，则记录LaneChange＝向左变道,更新uMax＝u_left；3)计算右侧车道的utility，记做u_right。如果u_right>u_uMax，则记录LaneChange＝向右变道。
上述各个实施例中，以无人驾驶场景为例，对于车载终端或携带移动终端的目标车辆而言，可完成目标车道的评估和选择。然而，上述各个实施例尚未关注是否可以立即执行变道。
可以理解的是，根据所述控制指令执行无人驾驶中的车道选择，得到所述目标车道后，可进一步结合目标车辆本身的行驶情况和周围的静态和动态障碍物，判断是否符合另一预设规则，如果符合另一预设规则，则立即由目标车辆当前无人驾驶所处于的所在的本车道变化到所述目标车道，否则，不执行变化到所述目标车道的变道处理。也就是说，当目标车道选定后，能否正常执行变道取决于系统之后的行为规划，车辆系统会以较高的频率来判断周围的静态和动态障碍物是否会影响变道，保证变道安全。如果有危险的话，会放弃变道。
本发明实施例的车道选择系统中，如图5所示，包括终端41(安装于目标车辆上的车载终端或用户手持的移动终端)和服务器42，其中，目标车辆运用根据服务器提供的数据源执行运算逻辑，以执行对应的车道选择处理，服务器配置为提供目标车辆需要的各种数据源，包括当前车辆及与当前车辆相关的其他车辆，可以将这些数据存储于目标车辆上安装的终端设备(车载终端或用户手持的移动终端)中。进一步，可以通过目标车辆下发的控制指令来执行车道选择。终端41包括：第一获取单元411，配置 为根据用于决策路口变道的第一模型和用于决策行驶速度的第二模型，得到用于变道选择的决策模型；第二获取单元412，配置为实时获取目标车辆的行驶信息以及与目标车辆相关的目标信息，所述目标信息用于表征目标车辆周边车辆的行驶信息；车道确定单元413，配置为根据实时获取的所述目标信息、目标车辆的行驶信息，通过所述决策模型得到目标车道。其中，与目标车辆相关的目标信息用于表征目标车辆周边车辆的行驶信息。
采用本发明实施例，首先获取与目标车辆相关的目标信息，所述目标信息用于表征目标车辆周边车辆的行驶信息。目标信息包括：1)周边车辆的地理位置信息，需要指出的是：该信息是一种绝对位置信息；2)周边车辆相对于当前目标车辆的距离信息，需要指出的是：区别于地理位置信息，是一种相对位置信息；3)周边车辆挂空档(如在路边停车休息)时的周边环境、周边车辆的速度信息；4)存在多条车道可以进行选择时周边车辆当前行驶于哪一个车道上等等。一个实例是：在驾驶过程中，可以根据本车车速、前车车速、车距；相邻车道车速与车距来决策是否可以进行变道操作，目的是为了改善本车的行驶速度。之后，根据用于决策路口变道的第一模型和用于决策行驶速度的第二模型进行建模，得到用于变道选择的决策模型。一个实例是：1)第一模型为MLC，用于评估当前车辆行驶到路口需要的时间t，是否大于变换车道所需要的时间，采用MLC，是对路口变道进行决策，比如当前由于路口等影响必须得离开本车道。2)第二模型为DLC，DLC的决策分为lane selection和Gap acceptance两步。其中，在lane selection中，是根据车速、车道限速等综合信息判定相邻车道是否需要变道；而Gap acceptance中，是根据相邻车道前后车的距离来判断，是否拥有总够的变道空间。只有这2个条件同时满足，才会做出变道决策。采用DLC，是对行驶速度进行改善，比如，前车距离后车比较近，那么需要减速，如果前车距离后车允许超车，则加速。
所述车道确定单元，还配置为：根据实时获取的所述目标信息、目标车辆的行驶信息，通过所述决策模型计算与目标车辆相关的特定车道对应的效用值；将效用值最大的车道作为目标车道。其中，所述特定车道至少包括目标车辆当前所在的本车道、与目标车辆相邻的左侧车道和右侧车道。一个实例是：通过计算本车道、左右车道的多个效用值(utility)，最后，选择多个utility中utility最大的车道作为用于车道选择的变换车道。
在车辆自动行驶或手动加速场景中，驾驶员会选择最合理的车道进行行驶。而采用本发明实施例的无人驾驶场景中，车辆必须具备和驾驶员一样的自主选择最优车道的能力，才能在多车道的高速公路或者城市道路上行驶，否则将无法上路。采用本发明实施例，是一种综合周围车辆和导航路径的车道选择方案，根据DLC和MLC建模，以将DLC和MLC统一到一个新建得到的决策模型当中。分别计算本车道、左右车道的utility，最后选择utility最大的车道作为用于变道选择的变换车道，从而解决了无人驾驶车辆自主选择车道的问题。本发明实施例有效结合了DLC和MLC的优势，得到了更加优化的决策模型，采用该决策模型，当离路口越远的情况下，DLC模型起主要作用；当离路口越近的情况下，受到MLC模型的影响就越大，保证了在一定距离范围内选择的目标车道的稳定性，不会来回切换。
在本发明实施例一实施方式中，所述车道确定单元，还配置为：根据目标车辆变道次数、目标车辆距离路口的距离值和单次变道最小距离值确定与所述第一模型相关的第一类utility，所述第一类效用值包括分别对应目标车辆当前所在的本车道、与目标车辆相邻的左侧车道和右侧车道的第一类utility。根据目标车辆车速信息及车道限速信息，确定特定车道与所述第二模型相关的第二类效用值，所述第二类效用值包括分别对应目标车辆当前所在的本车道、与目标车辆相邻的左侧车道和右侧车道的第二类utility。根据所述第一类utility和所述第二类utility得到特定车道的车道综合效用 值，所述车道综合utility包括分别对应目标车辆当前所在的本车道、与目标车辆相邻的左侧车道和右侧车道的车道综合utility。从分别对应目标车辆当前所在的本车道、与目标车辆相邻的左侧车道和右侧车道的车道综合utility中，选择车道综合utility最大的车道，将所述车道综合utility最大的车道决策为用于变道选择的目标车道。
在本发明实施例一实施方式中，所述车道确定单元，还配置为：根据路网情况得到备选车道，所述路网情况由路口及与所述路口相连的下一个道路构成。所述目标车辆还包括：变道次数确定单元，配置为根据目标车辆当前所在本车道与所述备选车道在第一方向上的距离，得到所述目标车辆变道次数。及距离值确定单元，配置为根据目标车辆当前所在本车道上的位置与所述路口在第二方向上的距离，得到所述目标车辆距离路口的距离值。及单次变道距离值确定单元，配置为根据目标车辆当前车速和变道时间，得到完成一次变道所需要的所述单次变道最小距离值。
在本发明实施例一实施方式中，所述目标车辆还包括：车速检测单元，配置为根据检测到的目标车辆周边车辆的速度信息，计算并实时调整所述目标车辆车速信息；
限速确定单元，配置为获取目标车辆中心点到当前车道中心线的垂直距离，判断所述垂直距离是否小于阈值，当小于阈值时确定出目标车辆隶属于所述当前车道，根据在所述当前车道的预设规则得到所述车道限速信息。
在本发明实施例一实施方式中，所述限速确定单元，还配置为：在所述当前车道检测到包括所述目标车辆所在车辆在内的至少两辆车时，将至少两辆车中最小的速度作为所述车道限速信息。
在本发明实施例一实施方式中，所述限速确定单元，还配置为：在所述当前车道检测到所述目标车辆行驶方向上没有其它车辆时，将车道速度 作为所述车道限速信息。
在本发明实施例一实施方式中，所述目标车辆还包括：忽略决策单元，配置为检测在所述当前车道中位于所述目标车辆所在车辆后方存在其它车辆时，忽略比所述目标车辆靠后的其它车辆。
在本发明实施例一实施方式中，所述目标车辆还包括：修正决策单元，配置为当所述当前车道的数量大于等于3，且所述目标车辆所在车辆当前位于左侧车道上，则根据调整系数对所述目标车辆车速信息进行修正处理，得到修正速度信息；所述建模单元，还配置为根据所述修正速度信息及车道限速信息，确定与所述第二模型相关的第二类utility。
在本发明实施例一实施方式中，所述车道确定单元，还配置为：所述控制指令为保持在本车道行驶时，不执行变化到所述目标车道的变道处理；所述控制指令为向左侧车道变道时，将所述左侧车道作为所述目标车道并执行变化到所述目标车道的变道处理；所述控制指令为向右侧车道变道时，将所述右侧车道作为所述目标车道并执行变化到所述目标车道的变道处理。
在本发明实施例一实施方式中，所述目标车辆还包括：变道执行决策单元，配置为：根据所述控制指令执行车道选择，得到所述目标车道后，如果符合预设规则，则立即由目标车辆当前所在的本车道变化到所述目标车道，否则，不执行变化到所述目标车道的变道处理。
其中，对于用于数据处理的处理器而言，在执行处理时，可以采用微处理器、中央处理器(CPU，Central Processing Unit)、DSP或FPGA实现；对于存储介质来说，包含操作指令，该操作指令可以为计算机可执行代码，通过所述操作指令来实现上述本发明实施例信息处理方法流程中的各个步骤。
这里需要指出的是：以上涉及终端和服务器项的描述，与上述方法描 述是类似的，同方法的有益效果描述，不做赘述。对于本发明终端和服务器实施例中未披露的技术细节，请参照本发明方法流程描述的实施例所描述内容。
以一个现实应用场景为例对本发明实施例阐述如下：
驾驶行为建模主要包括纵向和横向2个方面。纵向驾驶行为主要包括刹车、跟车等等。而横向驾驶行为主要就是变道模型。变道行为是驾驶员由自身驾驶特性,针对周围车辆的车速、空挡等周边环境信息的刺激,调整并完成自身驾驶目标策略包括信息判断和操作执行的综合行为过程。这样的行为被认为十分复杂甚至难以用数学模型进行描述。变道的模型可以分为DLC模型和MLC模型两种。DLC是为了改善行驶速度，MLC是由于路口等影响必须得离开本车道。首先，会判断是否需要考虑MLC。比如，评估当前车辆行驶到路口需要的时间t，是否大于变换车道所需要的时间。假如行驶道路必须变换到最右车道，与当前车道比需要变换n个车道，每变换一个车道需要时间t0，则：如果t>n×t0，则只需要考虑DLC；否则，需要同时考虑MLC和DLC，并且他们冲突时，以MLC的结果为准。在DLC的决策中，对于lane selection，是根据车速、车道限速等综合信息判定相邻车道是否需要变道；而对于Gap acceptance，是根据相邻车道前后车的距离来判断，是否拥有总够的变道空间。只有这个条件同时满足，才会做出变道决策。在行车过程中，驾驶员一般会根据本车车速、前车车速、车距；相邻车道车速与车距来决策是否可以进行变道操作，目的是为了改善本车的行驶速度。
在上述实施例中，单纯采用MLC模型或DLC模型进行变道选择都是无法达到响应及时和变道选择精确的目的。如下实施例中，是将DLC和MLC统一到一个模型当中，分别计算本车道、左右车道的utility，最后选择utility最大的车道作为变换车道。
以无人驾驶场景为例，对本发明实施例进行说明如下：
图6-8为在无人驾驶场景中采用本发明实施例用到的关键参数、决策模型的结构及实际应用中采样的变道选择情况示意图。其中，图6为车道变换行为决策的关键参数示意图，其中，S为当前车道前车间距；L 1为目标车道前净距；L 2为目标车道后净距；V 1为变道车辆速度；V 2为当前车道前车速度；V 3为相邻车道前车速度；V 4为相邻车道后车速度。图7为用于变道选择的决策模型的结构示意图，图8为实际应用中采样的变道选择情况示意图。
基于上述图6-8所示的内容，本实施例主要关注无人驾驶车辆的目标车道选择，与传统的变道模型有所差异。在本阶段，无人驾驶车辆只关注目标车道的评估和选择，不关注是否可以立即执行变道。当目标车道选定后，能否正常执行变道取决于之后的行为规划(motion plan)，它会以较高的频率来判断周围的静态和动态障碍物是否会影响变道，保证变道安全。如果有危险的话，会放弃变道。以图9所示的变道选择过程为例进行说明如下：
图9的变道选择过程中，包括如下内容：
第一步：根据路口确定最终目标车道，即找到基于MLC的目标车道(find goal lane for MLC)。
具体的，根据路口和下一条道路的连接关系确定MLC目标车道。在当前位置待选的车道里，根据连通性挑选可以到达路口并进入下一条道路的车道作为goal lane。例如当前本车在车道1，在路口需要右拐，则选择车道2作为goal lane。如果是直行通过路口的话，可能会有多条待选车道符合要求，此时选定其中离当前车道最近的车道当作目标车道(goal lane)。
确定了最终目标车道之后，可以计算当前每条车道距离最终车道的变道次数(如nlanechange)。假设沿车道中心线向前的方向为X轴，计算当前车辆位置距离路口的距离，将该距离记做distanceToJunction。
第二步：估计车道车速，即计算基于DLC的车道车速(estimate lane speed for DLC)。
根据检测到的周围车辆的速度来分别估计本车道、左侧车道、右侧车道的行车速度(如laneSpeed)。
首先根据车辆中心点到车道中心线的垂直距离d，来判定车辆属于哪条车道。当d小于一定阈值，例如d<2.0m时，则车辆属于此车道。
在每个车道统计过程中，忽略比本车靠后的车辆(如果x坐标小于本车x坐标，则忽略)。如果有多辆车，则记录其中最小的速度作为车道速度；如果车道里没有自车身前的车辆，则记录车道速度等于车道最大限速(如SPEED_LIMIT)。
当车道数据>＝3，本车当前在最左车道上，在计算laneSpeed时，在统计的基础上给一个折扣系数，使用k×laneSpeed(一般情况下k＝0.9)作为车道速度参与之后U_DLC计算。这样就保证了在同等情况下，车辆不会长期占用最左车道的情况。
第三步：计算车道的Utility，即整合基于MLC和DLC的Utility所得到的综合Utility。
采用公式(1)对特定车道，根据车道速度laneSpeed、最大限速SPEED_LIMIT来计算DLC相关的utility：
U_DLC＝p1×laneSpeed/SPEED_LIMIT       (1)
采用公式(2)根据变道次数nlanechange，车辆到路口的距离distanceToJunction和单次变道所需的最小距离d0，来计算MLC相关的utility；
U_MLC＝p2×pow(lanechange/(distanceToJunction/d0)，p3)  (2)
其中d0是根据当前车速和变道时间估计出来的完成一次变道需要的最小距离，计算方法如公式(3)所示：
d0＝MAX(dmin,vehicleSpeed×t0)         (3)
其中dmin和t0是一个常数，可以根据实际需要取值；vehicleSpeed为本车速度，t0为根据经验估计的完成一次变道需要的时间。建议dmin＝50m，t0＝10s。
p1、p2、p3分别是权重系数，可以根据需要调节，一般取p1＝10，p2＝2.0，p3＝2.0。
车道综合Utility的计算方法如公式(4)所示：
Utility＝(int)U_DLC–(int)U_MLC         (4)
注意，先分别对U_DLC和U_MLC取整数，然后再计算综合utility。这样做相当于对车速、距离等关键因素进行了分段分级，最大优点是可以在一定的车速范围和距离范围内保持utility的数值稳定性，进一步保证换道结果的稳定性，不会来回切换。
MLC使用指数模型，可以使得它的影响力随着distanceToJunction的逐渐变小而迅速增大，最终在路口附近起绝对主导作用，进而可以忽略DLC的影响，中间的过渡是平滑自然的。这样设计符合实际的变道规律。
第四步：变道类型的判定
最终的变道类型LaneChange分别是保持本车道、向左变道、向右变道三种情况。
按照本车道、左车道和右车道的顺序计算utility，选定utility最大的车道作为变道的目标车道。这种顺序保证了超车时优先从左侧车道超车。如果utility一样，则优先保持本车道。
第一步：计算当前车道的utility,记录变道类型为保持本车道，更新uMax；
第二步：计算左侧车道的utility，记做u_left。如果u_left>u_uMax，则记录LaneChange＝向左变道，更新uMax＝u_left；
第三步：计算右侧车道的utility，记做u_right。如果u_right>u_uMax，则记录LaneChange＝向右变道。
采用本发明实施例，有效结合了DLC和MLC，过渡自然，变道行为更加稳定。有效结合了DLC和MLC对车道选择的影响，距离路口越近，MLC起到的作用越大，过渡平滑自然，符合客观规律。对车速和路口距离等关键因素做了分级处理，保证了变道结果的稳定性，不会发生抖动现象。保证了左侧超车优先原则，但不长期占用最左车道。所采用的决策模型所采用的特定的判定顺序和规则，保证了在在相似条件下从左侧超车；对于车道数据较多的道路，车辆会长期占用最左侧的超车道。这样更加符合交通规则，符合中国道路的客观情况。
本发明实施例的一种终端(安装于目标车辆上的车载终端或用户手持的移动终端)，如图10所示，所述终端包括：处理器61和用于存储能够在处理器上运行的计算机程序的存储器，存储器的一个表现形式可以为如图10所示的计算机存储介质63，还包括用于数据通信的总线62。
所述处理器用于运行所述计算机程序时，执行：
根据用于决策路口变道的第一模型和用于决策行驶速度的第二模型，得到用于变道选择的决策模型；
实时获取目标车辆的行驶信息以及与目标车辆相关的目标信息，所述目标信息用于表征目标车辆周边车辆的行驶信息；
根据实时获取的所述目标信息、目标车辆的行驶信息，通过所述决策模型得到目标车道。
所述处理器用于运行所述计算机程序时，还执行：
根据实时获取的所述目标信息、目标车辆的行驶信息，通过所述决策模型计算与目标车辆相关的特定车道对应的效用值；
将效用值最大的车道作为目标车道。
所述特定车道至少包括目标车辆当前所在的本车道、与目标车辆相邻的左侧车道和右侧车道。
所述处理器用于运行所述计算机程序时，还执行：
根据目标车辆的变道次数、距离路口的距离值和单次变道最小距离值确定特定车道与所述第一模型相关的第一类效用值；
根据目标车辆车速信息及车道限速信息，确定特定车道与所述第二模型相关的第二类效用值；
根据所述第一类效用值和所述第二类效用值得到特定车道的车道综合效用值。
所述处理器用于运行所述计算机程序时，还执行：
根据路网情况得到备选车道，所述路网情况由路口及与所述路口相连的下一个道路构成；
根据目标车辆当前所在本车道与所述备选车道在第一方向上的距离，得到所述目标车辆变道次数；
根据目标车辆当前所在本车道上的位置与所述路口在第二方向上的距离，得到所述目标车辆距离路口的距离值；
根据目标车辆当前车速和变道时间，得到完成一次变道所需要的最小距离值。
所述处理器用于运行所述计算机程序时，还执行：
根据检测到的目标车辆周边车辆的速度信息，计算并实时调整所述目标车辆的车速信息；
获取目标车辆中心点到当前车道中心线的垂直距离，判断所述垂直距离是否小于阈值，当小于阈值时确定出目标车辆隶属于所述当前车道，根据在所述当前车道的预设规则得到所述车道限速信息。
所述处理器用于运行所述计算机程序时，还执行：
在所述当前车道检测到包括所述目标车辆在内的至少两辆车时，将至少两辆车中最小的速度作为所述车道限速信息。
所述处理器用于运行所述计算机程序时，还执行：
在所述当前车道检测到所述目标车辆行驶方向上没有其它车辆时，将车道速度作为所述车辆限速信息。
所述处理器用于运行所述计算机程序时，还执行：
检测在所述当前车道中位于所述目标车辆后方存在其它车辆时，忽略比所述目标车辆靠后的其它车辆。
所述处理器用于运行所述计算机程序时，还执行：
当目标车辆行驶道路的车道数量大于等于3，且所述目标车辆位于左侧车道上时，根据调整系数对所述目标车辆车速信息进行修正处理，得到修正速度信息；
根据所述修正速度信息及车道限速信息，重新确定所述特定车道与所述第二模型相关的第二类效用值。
本发明实施例的一种计算机存储介质，所述计算机存储介质中存储有计算机可执行指令，该计算机可执行指令用于执行：
根据用于决策路口变道的第一模型和用于决策行驶速度的第二模型，得到用于变道选择的决策模型；
实时获取目标车辆的行驶信息以及与目标车辆相关的目标信息，所述目标信息用于表征目标车辆周边车辆的行驶信息；
根据实时获取的所述目标信息、目标车辆的行驶信息，通过所述决策模型得到目标车道。
该计算机可执行指令用于还执行：
根据实时获取的所述目标信息、目标车辆的行驶信息，通过所述决策模型计算与目标车辆相关的特定车道对应的效用值；
将效用值最大的车道作为目标车道。
所述特定车道至少包括目标车辆当前所在的本车道、与目标车辆相邻的左侧车道和右侧车道。
该计算机可执行指令用于还执行：
根据目标车辆的变道次数、距离路口的距离值和单次变道最小距离值确定特定车道与所述第一模型相关的第一类效用值；
根据目标车辆车速信息及车道限速信息，确定特定车道与所述第二模型相关的第二类效用值；
根据所述第一类效用值和所述第二类效用值得到特定车道的车道综合效用值。
该计算机可执行指令用于还执行：
根据路网情况得到备选车道，所述路网情况由路口及与所述路口相连的下一个道路构成；
根据目标车辆当前所在本车道与所述备选车道在第一方向上的距离，得到所述目标车辆变道次数；
根据目标车辆当前所在本车道上的位置与所述路口在第二方向上的距离，得到所述目标车辆距离路口的距离值；
根据目标车辆当前车速和变道时间，得到完成一次变道所需要的最小距离值。
该计算机可执行指令用于还执行：
根据检测到的目标车辆周边车辆的速度信息，计算并实时调整所述目标车辆的车速信息；
获取目标车辆中心点到当前车道中心线的垂直距离，判断所述垂直距离是否小于阈值，当小于阈值时确定出目标车辆隶属于所述当前车道，根据在所述当前车道的预设规则得到所述车道限速信息。
该计算机可执行指令用于还执行：
在所述当前车道检测到包括所述目标车辆在内的至少两辆车时，将至少两辆车中最小的速度作为所述车道限速信息。
该计算机可执行指令用于还执行：
在所述当前车道检测到所述目标车辆行驶方向上没有其它车辆时，将车道速度作为所述车辆限速信息。
该计算机可执行指令用于还执行：
检测在所述当前车道中位于所述目标车辆后方存在其它车辆时，忽略比所述目标车辆靠后的其它车辆。
该计算机可执行指令用于还执行：
当目标车辆行驶道路的车道数量大于等于3，且所述目标车辆位于左侧车道上时，根据调整系数对所述目标车辆车速信息进行修正处理，得到修正速度信息；
根据所述修正速度信息及车道限速信息，重新确定所述特定车道与所述第二模型相关的第二类效用值。
在本申请所提供的几个实施例中，应该理解到，所揭露的设备和方法，可以通过其它的方式实现。以上所描述的设备实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，如：多个单元或组件可以结合，或可以集成到另一个系统，或一些特征可以忽略，或不执行。另外，所显示或讨论的各组成部分相互之间的耦合、或直接耦合、或通信连接可以是通过一些接口，设备或单元的间接耦合或通信连接，可以是电性的、机械的或其它形式的。
上述作为分离部件说明的单元可以是、或也可以不是物理上分开的，作为单元显示的部件可以是、或也可以不是物理单元，即可以位于一个地方，也可以分布到多个网络单元上；可以根据实际的需要选择其中的部分 或全部单元来实现本实施例方案的目的。
另外，在本发明各实施例中的各功能单元可以全部集成在一个处理单元中，也可以是各单元分别单独作为一个单元，也可以两个或两个以上单元集成在一个单元中；上述集成的单元既可以采用硬件的形式实现，也可以采用硬件加软件功能单元的形式实现。
本领域普通技术人员可以理解：实现上述方法实施例的全部或部分步骤可以通过程序指令相关的硬件来完成，前述的程序可以存储于一计算机可读取存储介质中，该程序在执行时，执行包括上述方法实施例的步骤；而前述的存储介质包括：移动存储设备、ROM、RAM、磁碟或者光盘等各种可以存储程序代码的介质。
或者，本发明上述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，也可以存储在一个计算机可读取存储介质中。基于这样的理解，本发明实施例的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机、服务器、或者网络设备等)执行本发明各个实施例所述方法的全部或部分。而前述的存储介质包括：移动存储设备、ROM、RAM、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述，仅为本发明的具体实施方式，但本发明的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本发明揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本发明的保护范围之内。因此，本发明的保护范围应以所述权利要求的保护范围为准。
工业实用性
采用本发明实施例，根据用于表征不同决策选择的模型建模，以得到用于变道选择的决策模型，比如，采用DLC和MLC来建模得到的决策结 果，可以将速度和路口等影响情况都全面考虑到无人驾驶场景中，更符合实际需求，根据实时获取的与目标车辆相关的目标信息、目标车辆的行驶信息，通过决策模型得到目标车道，由得到的目标车道来执行车道选择，实现了精准的变道选择，能确保响应时间尽可能低。

Claims (32)

  1. 一种车道选择方法，包括：
    根据用于决策路口变道的第一模型和用于决策行驶速度的第二模型，得到用于变道选择的决策模型；
    实时获取目标车辆的行驶信息以及与目标车辆相关的目标信息，所述目标信息用于表征目标车辆周边车辆的行驶信息；
    根据实时获取的所述目标信息、目标车辆的行驶信息，通过所述决策模型得到目标车道。
  2. 根据权利要求1所述的方法，其中，所述根据实时获取的所述目标信息、目标车辆的行驶信息，通过所述决策模型得到目标车道，包括：
    根据实时获取的所述目标信息、目标车辆的行驶信息，通过所述决策模型计算与目标车辆相关的特定车道对应的效用值；
    将效用值最大的车道作为目标车道。
  3. 根据权利要求2所述的方法，其中，所述特定车道至少包括目标车辆当前所在的本车道、与目标车辆相邻的左侧车道和右侧车道。
  4. 根据权利要求2所述的方法，其中，所述通过所述决策模型计算目标车辆所在车道以及相邻的左右车道对应的效用值，包括：
    根据目标车辆的变道次数、距离路口的距离值和单次变道最小距离值确定特定车道与所述第一模型相关的第一类效用值；
    根据目标车辆车速信息及车道限速信息，确定特定车道与所述第二模型相关的第二类效用值；
    根据所述第一类效用值和所述第二类效用值得到特定车道的车道综合效用值。
  5. 根据权利要求4所述的方法，其中，根据目标车辆变道次数和目标车辆距离路口的距离值，确定与所述第一模型相关的第一类效用值之前， 所述方法还包括：
    根据路网情况得到备选车道，所述路网情况由路口及与所述路口相连的下一个道路构成；
    根据目标车辆当前所在本车道与所述备选车道在第一方向上的距离，得到所述目标车辆变道次数；
    根据目标车辆当前所在本车道上的位置与所述路口在第二方向上的距离，得到所述目标车辆距离路口的距离值；
    根据目标车辆当前车速和变道时间，得到完成一次变道所需要的最小距离值。
  6. 根据权利要求4所述的方法，其中，根据目标车辆车速信息及车道限速信息，确定与所述第二模型相关的第二类效用值之前，所述方法还包括：
    根据检测到的目标车辆周边车辆的速度信息，计算并实时调整所述目标车辆的车速信息；
    获取目标车辆中心点到当前车道中心线的垂直距离，判断所述垂直距离是否小于阈值，当小于阈值时确定出目标车辆隶属于所述当前车道，根据在所述当前车道的预设规则得到所述车道限速信息。
  7. 根据权利要求6所述的方法，其中，根据在所述当前车道的预设规则得到所述车道限速信息，包括：
    在所述当前车道检测到包括所述目标车辆在内的至少两辆车时，将至少两辆车中最小的速度作为所述车道限速信息。
  8. 根据权利要求6所述的方法，其中，根据在所述当前车道的预设规则得到所述车道限速信息，包括：
    在所述当前车道检测到所述目标车辆行驶方向上没有其它车辆时，将车道速度作为所述车辆限速信息。
  9. 根据权利要求6所述的方法，其中，所述方法还包括：
    检测在所述当前车道中位于所述目标车辆后方存在其它车辆时，忽略比所述目标车辆靠后的其它车辆。
  10. 根据权利要求6所述的方法，其中，所述方法还包括：
    当目标车辆行驶道路的车道数量大于等于3，且所述目标车辆位于左侧车道上时，根据调整系数对所述目标车辆车速信息进行修正处理，得到修正速度信息；
    根据所述修正速度信息及车道限速信息，重新确定所述特定车道与所述第二模型相关的第二类效用值。
  11. 一种目标车辆，所述目标车辆包括：
    第一获取单元，配置为根据用于决策路口变道的第一模型和用于决策行驶速度的第二模型，得到用于变道选择的决策模型；
    第二获取单元，配置为实时获取目标车辆的行驶信息以及与目标车辆相关的目标信息，所述目标信息用于表征目标车辆周边车辆的行驶信息；
    车道确定单元，配置为根据实时获取的所述目标信息、目标车辆的行驶信息，通过所述决策模型得到目标车道。
  12. 根据权利要求11所述的目标车辆，其中，所述车道确定单元，还配置为：
    根据实时获取的所述目标信息、目标车辆的行驶信息，通过所述决策模型计算与目标车辆相关的特定车道对应的效用值；
    将效用值最大的车道作为目标车道。
  13. 根据权利要求12所述的目标车辆，其中，所述特定车道至少包括目标车辆当前所在的本车道、与目标车辆相邻的左侧车道和右侧车道。
  14. 根据权利要求12所述的目标车辆，其中，所述车道确定单元，还配置为：
    根据目标车辆变道次数、目标车辆距离路口的距离值和单次变道最小距离值确定与所述第一模型相关的第一类效用值；
    根据目标车辆车速信息及车道限速信息，确定特定车道与所述第二模型相关的第二类效用值；
    根据所述第一类效用值和所述第二类效用值得到特定车道的车道综合效用值。
  15. 根据权利要求14所述的目标车辆，其中，所述车道确定单元，还配置为：
    根据路网情况得到备选车道，所述路网情况由路口及与所述路口相连的下一个道路构成；
    所述目标车辆还包括：
    变道次数确定单元，配置为根据目标车辆当前所在本车道与所述备选车道在第一方向上的距离，得到所述目标车辆变道次数；
    距离值确定单元，配置为根据目标车辆当前所在本车道上的位置与所述路口在第二方向上的距离，得到所述目标车辆距离路口的距离值；
    单次变道距离值确定单元，配置为根据目标车辆当前车速和变道时间，得到完成一次变道所需要的所述单次变道最小距离值。
  16. 根据权利要求14所述的目标车辆，其中，所述目标车辆还包括：
    车速检测单元，配置为根据检测到的目标车辆周边车辆的速度信息，计算并实时调整所述目标车辆的车速信息；
    限速确定单元，配置为获取目标车辆中心点到当前车道中心线的垂直距离，判断所述垂直距离是否小于阈值，当小于阈值时确定出目标车辆隶属于所述当前车道，根据在所述当前车道的预设规则得到所述车道限速信息。
  17. 根据权利要求16所述的目标车辆，其中，所述限速确定单元，还 配置为：
    在所述当前车道检测到包括所述目标车辆在内的至少两辆车时，将至少两辆车中最小的速度作为所述车道限速信息。
  18. 根据权利要求16所述的目标车辆，其中，所述限速确定单元，还配置为：
    在所述当前车道检测到所述目标车辆行驶方向上没有其它车辆时，将车道速度作为所述车道限速信息。
  19. 根据权利要求16所述的目标车辆，其中，所述目标车辆还包括：
    忽略决策单元，配置为检测在所述当前车道中位于所述目标车辆后方存在其它车辆时，忽略比所述目标车辆靠后的其它车辆。
  20. 根据权利要求16所述的目标车辆，其中，所述目标车辆还包括：
    修正决策单元，配置为当所述目标车辆行驶道路的车道数量大于等于3，且所述目标车辆当前位于左侧车道上，则根据调整系数对所述目标车辆车速信息进行修正处理，得到修正速度信息；
    所述车道确定单元，还配置为根据所述修正速度信息及车道限速信息，重新确定所述特定车道与所述第二模型相关的第二类效用值。
  21. 一种目标车辆，所述目标车辆包括：处理器和用于存储能够在处理器上运行的计算机程序的存储器；其中，所述处理器用于运行所述计算机程序时，执行上述权利要求1-10任一项所述的车道选择方法。
  22. 一种计算机存储介质，所述计算机存储介质中存储有计算机可执行指令，该计算机可执行指令用于执行上述权利要求1-10任一项所述的车道选择方法。
  23. 一种车道选择方法，所述方法由目标车辆执行，所述目标车辆包括有一个或多个处理器以及存储器，以及一个或一个以上的程序，其中，所述一个或一个以上的程序存储于存储器中，所述程序可以包括一个或一 个以上的每一个对应于一组指令的单元，所述一个或多个处理器被配置为执行指令；所述方法包括：
    根据用于决策路口变道的第一模型和用于决策行驶速度的第二模型，得到用于变道选择的决策模型；
    实时获取目标车辆的行驶信息以及与目标车辆相关的目标信息，所述目标信息用于表征目标车辆周边车辆的行驶信息；
    根据实时获取的所述目标信息、目标车辆的行驶信息，通过所述决策模型得到目标车道。
  24. 根据权利要求23所述的方法，其中，所述根据实时获取的所述目标信息、目标车辆的行驶信息，通过所述决策模型得到目标车道，包括：
    根据实时获取的所述目标信息、目标车辆的行驶信息，通过所述决策模型计算与目标车辆相关的特定车道对应的效用值；
    将效用值最大的车道作为目标车道。
  25. 根据权利要求24所述的方法，其中，所述特定车道至少包括目标车辆当前所在的本车道、与目标车辆相邻的左侧车道和右侧车道。
  26. 根据权利要求24所述的方法，其中，所述通过所述决策模型计算目标车辆所在车道以及相邻的左右车道对应的效用值，包括：
    根据目标车辆的变道次数、距离路口的距离值和单次变道最小距离值确定特定车道与所述第一模型相关的第一类效用值；
    根据目标车辆车速信息及车道限速信息，确定特定车道与所述第二模型相关的第二类效用值；
    根据所述第一类效用值和所述第二类效用值得到特定车道的车道综合效用值。
  27. 根据权利要求26所述的方法，其中，根据目标车辆变道次数和目标车辆距离路口的距离值，确定与所述第一模型相关的第一类效用值之前， 所述方法还包括：
    根据路网情况得到备选车道，所述路网情况由路口及与所述路口相连的下一个道路构成；
    根据目标车辆当前所在本车道与所述备选车道在第一方向上的距离，得到所述目标车辆变道次数；
    根据目标车辆当前所在本车道上的位置与所述路口在第二方向上的距离，得到所述目标车辆距离路口的距离值；
    根据目标车辆当前车速和变道时间，得到完成一次变道所需要的最小距离值。
  28. 根据权利要求26所述的方法，其中，根据目标车辆车速信息及车道限速信息，确定与所述第二模型相关的第二类效用值之前，所述方法还包括：
    根据检测到的目标车辆周边车辆的速度信息，计算并实时调整所述目标车辆的车速信息；
    获取目标车辆中心点到当前车道中心线的垂直距离，判断所述垂直距离是否小于阈值，当小于阈值时确定出目标车辆隶属于所述当前车道，根据在所述当前车道的预设规则得到所述车道限速信息。
  29. 根据权利要求28所述的方法，其中，根据在所述当前车道的预设规则得到所述车道限速信息，包括：
    在所述当前车道检测到包括所述目标车辆在内的至少两辆车时，将至少两辆车中最小的速度作为所述车道限速信息。
  30. 根据权利要求28所述的方法，其中，根据在所述当前车道的预设规则得到所述车道限速信息，包括：
    在所述当前车道检测到所述目标车辆行驶方向上没有其它车辆时，将车道速度作为所述车辆限速信息。
  31. 根据权利要求28所述的方法，其中，所述方法还包括：
    检测在所述当前车道中位于所述目标车辆后方存在其它车辆时，忽略比所述目标车辆靠后的其它车辆。
  32. 根据权利要求28所述的方法，其中，所述方法还包括：
    当目标车辆行驶道路的车道数量大于等于3，且所述目标车辆位于左侧车道上时，根据调整系数对所述目标车辆车速信息进行修正处理，得到修正速度信息；
    根据所述修正速度信息及车道限速信息，重新确定所述特定车道与所述第二模型相关的第二类效用值。
PCT/CN2018/081187 2017-04-20 2018-03-29 一种车道选择方法及目标车辆、计算机存储介质 WO2018192352A1 (zh)

Priority Applications (4)

Application Number Priority Date Filing Date Title
KR1020197023464A KR102212431B1 (ko) 2017-04-20 2018-03-29 차선 선택 방법, 타깃 차량 및 컴퓨터 저장 매체
JP2019556237A JP6808853B2 (ja) 2017-04-20 2018-03-29 車線選択方法、目標車両及びコンピュータ記憶媒体
EP18787339.3A EP3614359A4 (en) 2017-04-20 2018-03-29 TRACK SELECTION METHOD, TARGET VEHICLE AND COMPUTER STORAGE MEDIUM
US16/460,555 US11059485B2 (en) 2017-04-20 2019-07-02 Lane selection method, target vehicle and computer storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710262939.9 2017-04-20
CN201710262939.9A CN108305477B (zh) 2017-04-20 2017-04-20 一种车道选择方法及终端

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US16/460,555 Continuation US11059485B2 (en) 2017-04-20 2019-07-02 Lane selection method, target vehicle and computer storage medium

Publications (1)

Publication Number Publication Date
WO2018192352A1 true WO2018192352A1 (zh) 2018-10-25

Family

ID=62872213

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/081187 WO2018192352A1 (zh) 2017-04-20 2018-03-29 一种车道选择方法及目标车辆、计算机存储介质

Country Status (7)

Country Link
US (1) US11059485B2 (zh)
EP (1) EP3614359A4 (zh)
JP (1) JP6808853B2 (zh)
KR (1) KR102212431B1 (zh)
CN (1) CN108305477B (zh)
TW (1) TWI676970B (zh)
WO (1) WO2018192352A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2020157829A (ja) * 2019-03-25 2020-10-01 本田技研工業株式会社 走行制御装置、走行制御方法、およびプログラム
CN113997934A (zh) * 2021-12-09 2022-02-01 中国第一汽车股份有限公司 车道变换方法、装置、计算机设备及存储介质
CN114194193A (zh) * 2021-01-11 2022-03-18 广东科学技术职业学院 一种控制车辆变道的方法

Families Citing this family (29)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3805889A1 (en) * 2016-12-23 2021-04-14 Mobileye Vision Technologies Ltd. Navigational system monitoring host and target vehicle behaviour
WO2019220717A1 (ja) * 2018-05-15 2019-11-21 日立オートモティブシステムズ株式会社 車両制御装置
JP6984547B2 (ja) * 2018-06-08 2021-12-22 トヨタ自動車株式会社 車線変更支援システム、車線変更支援装置及び車線変更支援方法
US10916125B2 (en) * 2018-07-30 2021-02-09 Honda Motor Co., Ltd. Systems and methods for cooperative smart lane selection
CN111091727A (zh) * 2018-10-24 2020-05-01 上汽通用汽车有限公司 基于移动车联网的用于变更车道的方法和系统
TWI678515B (zh) * 2018-11-21 2019-12-01 財團法人車輛研究測試中心 動態圖資分類裝置及其方法
CN109871017B (zh) * 2019-02-20 2022-09-13 阿波罗智能技术(北京)有限公司 自动驾驶参考线调用方法、装置和终端
CN109703569B (zh) * 2019-02-21 2021-07-27 百度在线网络技术（北京）有限公司 一种信息处理方法、装置及存储介质
CN109782776B (zh) * 2019-03-28 2022-07-29 北京百度网讯科技有限公司 无人车的车道选择方法、装置及存储介质
CN109949611B (zh) 2019-03-28 2021-11-30 阿波罗智能技术(北京)有限公司 无人车的变道方法、装置及存储介质
TWI684085B (zh) * 2019-04-24 2020-02-01 揚昇育樂事業股份有限公司 自駕車輛之自駕行駛路徑中央控制裝置
JP7159109B2 (ja) * 2019-05-16 2022-10-24 本田技研工業株式会社 車両制御装置、車両制御装方法、およびプログラム
CN110160552B (zh) * 2019-05-29 2021-05-04 百度在线网络技术（北京）有限公司 导航信息确定方法、装置、设备和存储介质
CN112634627B (zh) * 2019-10-08 2023-03-10 宁波吉利汽车研究开发有限公司 一种高速巡航状态下的换道方法、装置及汽车
CN110686693A (zh) * 2019-10-14 2020-01-14 泰牛汽车技术(苏州)有限公司 封闭场景内路网信息的构建方法
CN112991792B (zh) * 2019-12-12 2023-05-26 奥迪股份公司 车辆的变道方法、装置、计算机设备和存储介质
TWI762887B (zh) * 2020-03-19 2022-05-01 荷蘭商荷蘭移動驅動器公司 交通安全管控方法、車載裝置及可讀儲存介質
CN111413973A (zh) * 2020-03-26 2020-07-14 北京汽车集团有限公司 车辆的换道决策方法及装置、电子设备、存储介质
CN111586557B (zh) * 2020-04-03 2024-05-03 腾讯科技（深圳）有限公司 车辆通信方法、装置、计算机可读介质及电子设备
US11904890B2 (en) * 2020-06-17 2024-02-20 Baidu Usa Llc Lane change system for lanes with different speed limits
CN113808385B (zh) * 2020-06-17 2023-09-26 奥迪股份公司 机动车行车道的选择方法及装置、车辆
CN112365741B (zh) * 2020-10-23 2021-09-28 淮阴工学院 一种基于多车道车距检测的安全预警方法及系统
CN114506324B (zh) * 2020-10-23 2024-03-15 上海汽车集团股份有限公司 一种车道决策方法及相关装置
CN112416004B (zh) * 2020-11-19 2021-12-14 腾讯科技（深圳）有限公司 一种基于自动驾驶的控制方法、装置、车辆以及相关设备
CN113602263A (zh) * 2021-08-26 2021-11-05 中国第一汽车股份有限公司 车辆避让方法、装置、车载设备及存储介质
US11804131B2 (en) * 2021-11-24 2023-10-31 GM Global Technology Operations LLC Communication system for determining vehicle context and intent of a target vehicle based on perceived lane of travel
CN115472032B (zh) * 2022-08-24 2024-05-28 武汉理工大学 一种高速公路匝道合流区车辆自动换道决策系统及方法
CN115662171A (zh) * 2022-10-27 2023-01-31 长城汽车股份有限公司 变道提示方法、装置、电子设备及车辆
CN116279567B (zh) * 2023-05-11 2023-11-14 长城汽车股份有限公司 显示车道信息的方法、显示车道信息的装置及车辆

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2003157500A (ja) * 2001-11-22 2003-05-30 Fujitsu Ltd 安全走行支援装置，安全走行支援プログラム，及び安全走行支援方法
CN103065501A (zh) * 2012-12-14 2013-04-24 清华大学 一种汽车换道预警方法及换道预警系统
CN103996287A (zh) * 2014-05-26 2014-08-20 江苏大学 一种基于决策树模型的车辆强制换道决策方法
CN106114507A (zh) * 2016-06-21 2016-11-16 百度在线网络技术（北京）有限公司 用于智能车辆的局部轨迹规划方法和装置

Family Cites Families (41)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7979173B2 (en) * 1997-10-22 2011-07-12 Intelligent Technologies International, Inc. Autonomous vehicle travel control systems and methods
JP4066573B2 (ja) * 1999-09-22 2008-03-26 株式会社デンソー 先行車選択装置、車間制御装置及び記録媒体
JP3925474B2 (ja) * 2003-07-18 2007-06-06 日産自動車株式会社 車線変更支援装置
US10964209B2 (en) * 2003-12-24 2021-03-30 Mark W. Publicover Method and system for traffic and parking management
JP2006113918A (ja) * 2004-10-15 2006-04-27 Fujitsu Ten Ltd 運転支援装置
JP4581674B2 (ja) * 2004-12-24 2010-11-17 アイシン・エィ・ダブリュ株式会社 経路案内システム及び経路案内方法
TWI270827B (en) * 2005-06-29 2007-01-11 Jau-Shiang Wang Traffic lane recognition system and traffic lane deviation warning device with traffic lane recognition system and method of forming the same
US20070225914A1 (en) * 2006-03-21 2007-09-27 Hiroshi Kawazoe Lane departure avoidance control
JP4366419B2 (ja) * 2007-09-27 2009-11-18 株式会社日立製作所 走行支援装置
CA2726146A1 (en) * 2008-06-25 2009-12-30 Tomtom International B.V. Navigation apparatus and method of detection that a parking facility is sought
JP5663942B2 (ja) * 2010-05-11 2015-02-04 トヨタ自動車株式会社 走行軌道作成装置
CN103348392B (zh) * 2010-12-31 2016-06-29 通腾比利时公司 导航方法与系统
US9182761B2 (en) * 2011-08-25 2015-11-10 Nissan Motor Co., Ltd. Autonomous driving control system for vehicle
JP2013050397A (ja) * 2011-08-31 2013-03-14 Nissan Motor Co Ltd 走行制御装置
US9286800B2 (en) * 2012-12-30 2016-03-15 Robert Gordon Guidance assist vehicle module
GB201307550D0 (en) * 2013-04-26 2013-06-12 Tomtom Dev Germany Gmbh Methods and systems of providing information indicative of a recommended navigable stretch
US9946818B2 (en) * 2013-07-30 2018-04-17 University Of Florida Research Foundation, Inc. System and method for automated model calibration, sensitivity analysis, and optimization
CN103871242B (zh) * 2014-04-01 2015-09-09 北京工业大学 一种驾驶行为综合评价系统与方法
JP6537780B2 (ja) * 2014-04-09 2019-07-03 日立オートモティブシステムズ株式会社 走行制御装置、車載用表示装置、及び走行制御システム
US9609046B2 (en) * 2014-04-29 2017-03-28 Here Global B.V. Lane level road views
KR101610544B1 (ko) 2014-11-21 2016-04-07 현대자동차주식회사 차량의 자율 주행 시스템 및 방법
JP2016215790A (ja) * 2015-05-19 2016-12-22 株式会社デンソー 車線変更計画生成装置、車線変更計画生成方法
KR101724887B1 (ko) 2015-08-10 2017-04-07 현대자동차주식회사 전방 도로 형상과 연결을 분석해 차선 변경과 타이밍을 결정하는 자율주행 제어 장치 및 방법
CN105160917B (zh) * 2015-08-24 2017-09-29 武汉理工大学 基于车路协同的信号控制交叉口车速引导系统及方法
CN105206052B (zh) * 2015-09-21 2018-05-11 张力 一种驾驶行为分析方法及设备
CN117400938A (zh) * 2015-11-26 2024-01-16 御眼视觉技术有限公司 主车辆的车辆导航系统、主车辆和非暂时性机器可读介质
JP2017142145A (ja) * 2016-02-10 2017-08-17 株式会社ゼンリン 車線変更支援装置、車両制御装置およびその方法
US9672734B1 (en) * 2016-04-08 2017-06-06 Sivalogeswaran Ratnasingam Traffic aware lane determination for human driver and autonomous vehicle driving system
EP3548845B1 (en) * 2017-01-12 2021-10-13 Mobileye Vision Technologies Ltd. Navigation based on vehicle activity
US20190381914A1 (en) * 2017-01-24 2019-12-19 Honda Motor Co., Ltd. Target support device, vehicle control system, vehicle control method, vehicle control program, and support structure of vehicle seat
WO2018175441A1 (en) * 2017-03-20 2018-09-27 Mobileye Vision Technologies Ltd. Navigation by augmented path prediction
US11210744B2 (en) * 2017-08-16 2021-12-28 Mobileye Vision Technologies Ltd. Navigation based on liability constraints
US10668925B2 (en) * 2017-09-05 2020-06-02 Baidu Usa Llc Driver intention-based lane assistant system for autonomous driving vehicles
CN107792073B (zh) * 2017-09-29 2019-10-25 东软集团股份有限公司 一种车辆换道控制方法、装置及相关设备
US11360475B2 (en) * 2017-12-05 2022-06-14 Waymo Llc Real-time lane change selection for autonomous vehicles
US11072327B2 (en) * 2018-03-07 2021-07-27 Robert Bosch Gmbh Known lane intervals for automated driving
JP7125214B2 (ja) * 2018-04-03 2022-08-24 モービルアイ ビジョン テクノロジーズ リミテッド プログラムおよびコンピューティングデバイス
US20190315345A1 (en) * 2018-04-16 2019-10-17 David E. Newman Blind spot potential-hazard avoidance system
US10569773B2 (en) * 2018-05-31 2020-02-25 Nissan North America, Inc. Predicting behaviors of oncoming vehicles
US20200114921A1 (en) * 2018-10-11 2020-04-16 Ford Global Technologies, Llc Sensor-limited lane changing
CN113272743B (zh) * 2019-02-19 2024-04-12 奥普塔姆软件股份有限公司 使用有通道结构的动态环境进行基于规则的自动化控制

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2003157500A (ja) * 2001-11-22 2003-05-30 Fujitsu Ltd 安全走行支援装置，安全走行支援プログラム，及び安全走行支援方法
CN103065501A (zh) * 2012-12-14 2013-04-24 清华大学 一种汽车换道预警方法及换道预警系统
CN103996287A (zh) * 2014-05-26 2014-08-20 江苏大学 一种基于决策树模型的车辆强制换道决策方法
CN106114507A (zh) * 2016-06-21 2016-11-16 百度在线网络技术（北京）有限公司 用于智能车辆的局部轨迹规划方法和装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3614359A4 *

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2020157829A (ja) * 2019-03-25 2020-10-01 本田技研工業株式会社 走行制御装置、走行制御方法、およびプログラム
JP7152339B2 (ja) 2019-03-25 2022-10-12 本田技研工業株式会社 走行制御装置、走行制御方法、およびプログラム
CN114194193A (zh) * 2021-01-11 2022-03-18 广东科学技术职业学院 一种控制车辆变道的方法
CN114194193B (zh) * 2021-01-11 2023-06-27 广东科学技术职业学院 一种控制车辆变道的方法
CN113997934A (zh) * 2021-12-09 2022-02-01 中国第一汽车股份有限公司 车道变换方法、装置、计算机设备及存储介质
CN113997934B (zh) * 2021-12-09 2024-05-03 中国第一汽车股份有限公司 车道变换方法、装置、计算机设备及存储介质

Also Published As

Publication number Publication date
CN108305477A (zh) 2018-07-20
EP3614359A1 (en) 2020-02-26
CN108305477B (zh) 2019-08-13
TWI676970B (zh) 2019-11-11
JP6808853B2 (ja) 2021-01-06
US11059485B2 (en) 2021-07-13
US20190322281A1 (en) 2019-10-24
TW201838847A (zh) 2018-11-01
JP2020516535A (ja) 2020-06-11
KR102212431B1 (ko) 2021-02-03
EP3614359A4 (en) 2020-05-27
KR20190104391A (ko) 2019-09-09

Similar Documents

Publication Publication Date Title
WO2018192352A1 (zh) 一种车道选择方法及目标车辆、计算机存储介质
US20230139760A1 (en) Network-assisted scanning of a surrounding environment
CN105989728B (zh) 车辆及其控制方法
CN107223201B (zh) 一种导航方法、装置以及终端设备
CN109697875B (zh) 规划行驶轨迹的方法及装置
EP3054721B1 (en) Traffic adjustment for variable network state
KR101465493B1 (ko) 차량 내비게이션 시스템 및 차량의 목적지 경로를 결정하는 방법
WO2022057645A1 (zh) 辅助驾驶提醒、地图辅助驾驶提醒方法、装置和地图
US20170307400A1 (en) Device for providing electric-moving-body information and method for providing electric-moving-body information
CN105865466A (zh) 一种智能导航系统和方法
CN103884344A (zh) 一种基于海量车辆数据的智能化导航方法及导航系统
CN104344833A (zh) 车辆导航方法、装置和系统
US11555711B2 (en) Systems and methods for augmented reality in a vehicle
CN109489674B (zh) 基于位置确定路段的方法、装置及存储介质
Lee et al. Design of V2X-based vehicular contents centric networks for autonomous driving
US11231293B2 (en) Method, terminal, and computer storage medium for identifying information during navigation
CN108267142A (zh) 一种基于地址卡片的导航显示方法、系统及一种车机
KR20130011351A (ko) 스마트 정보를 이용한 차량 운행 시스템, 이를 위한 단말기, 서비스장치 및 방법
WO2010032282A1 (ja) サーバ装置、移動端末装置、交差点案内システム及び交差点案内方法
Zhang et al. The application of edge computing in high-definition maps distribution
WO2023206388A1 (zh) 换道决策方法、装置及存储介质
US11908095B2 (en) 2-D image reconstruction in a 3-D simulation
CN114987549A (zh) 车辆控制方法、装置、存储介质及车辆
CN112435471B (zh) 一种位置点处理方法和相关装置
US11878717B2 (en) Mirage detection by autonomous vehicles

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18787339

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 20197023464

Country of ref document: KR

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 2019556237

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2018787339

Country of ref document: EP

Effective date: 20191120