WO2025180342A1 - 驾驶控制方法、协同驾驶方法及相关装置 - Google Patents

驾驶控制方法、协同驾驶方法及相关装置

Info

Publication number
WO2025180342A1
WO2025180342A1 PCT/CN2025/078928 CN2025078928W WO2025180342A1 WO 2025180342 A1 WO2025180342 A1 WO 2025180342A1 CN 2025078928 W CN2025078928 W CN 2025078928W WO 2025180342 A1 WO2025180342 A1 WO 2025180342A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
perception
vehicle
roadside
cloud
Prior art date
Legal status (The legal status 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 status listed.)
Pending
Application number
PCT/CN2025/078928
Other languages
English (en)
French (fr)
Inventor
周伟
杨昱
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Yinwang Intelligent Technology Co Ltd
Original Assignee
Shenzhen Yinwang Intelligent Technology Co Ltd
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 Shenzhen Yinwang Intelligent Technology Co Ltd filed Critical Shenzhen Yinwang Intelligent Technology Co Ltd
Publication of WO2025180342A1 publication Critical patent/WO2025180342A1/zh
Pending legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • 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
    • 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
    • G08G1/096766—Systems involving transmission of highway information, e.g. weather, speed limits where the system is characterised by the origin of the information transmission
    • G08G1/096775—Systems involving transmission of highway information, e.g. weather, speed limits where the system is characterised by the origin of the information transmission where the origin of the information is a central station
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/30—Services specially adapted for particular environments, situations or purposes
    • H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
    • H04W4/44—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P] for communication between vehicles and infrastructures, e.g. vehicle-to-cloud [V2C] or vehicle-to-home [V2H]

Definitions

  • the present application relates to the field of intelligent driving technology, and in particular to a driving control method, a collaborative driving method, and related devices.
  • single-vehicle intelligent driving there are two main approaches to achieving intelligent driving: single-vehicle intelligent driving and vehicle-road collaborative intelligent driving.
  • intelligent driving technology centered around single-vehicle intelligence has already been integrated into products with Level 2 assisted driving capabilities.
  • single-vehicle intelligent driving which relies solely on the vehicle's own sensor detection, signal feedback, and actuators to complete commands, makes it difficult for the vehicle to promptly avoid threats outside the sensor's perception range, resulting in reduced driving safety. Therefore, single-vehicle intelligent driving has significant limitations in the development of high-level intelligent driving. Achieving intelligent driving through vehicle-road collaboration can further reduce the risk and probability of accidents based on single-vehicle intelligence and can also better evolve to high-level intelligent driving.
  • the embodiments of the present application provide a driving control method, a collaborative driving method and related devices, which can effectively reduce vehicle driving safety hazards and have low implementation costs and are easy to promote and use.
  • the present application provides a driving control method, which includes: obtaining first information from a cloud device; the first information includes perception information of a first object by a roadside perception device; obtaining first fusion information based on the first information and the first perception information; and performing a first driving control based on the first fusion information; wherein the first perception information includes perception information obtained by sensors of the vehicle; when the vehicle perceives the first object based on second perception information, performing a second driving control based on the second perception information; the second perception information includes perception information of the first object obtained by sensors of the vehicle.
  • the aforementioned roadside sensing device is deployed on a driving blind spot section in the forward direction of the aforementioned vehicle, and the sensing range of the aforementioned roadside sensing device covers the aforementioned driving blind spot section;
  • the aforementioned driving blind spot section includes one or more of the following: a curved road section, a road section including an intersection, a road section including an entrance or exit, or a slope top section.
  • the method further includes: obtaining second information from a cloud device; the second information indicates perception information of the roadside perception device on a second object; the second object includes one or more pedestrians; and discarding the second information.
  • the vehicle can turn off the roadside fusion perception function and restore the single-vehicle perception driving mode to reduce the fusion calculation overhead.
  • the cloud device can obtain the vehicle's information and the roadside device's perception information of the first object, and then determine whether the conditions for sending the perception information of the first object to the vehicle are met, and send it only if they are met. That is, in this solution, through the forwarding of the cloud device, the roadside perception device can be used as a perception blind spot device for the vehicle, allowing the vehicle to obtain information outside the perception range, thereby gaining a more comprehensive understanding of the driving environment and reducing safety hazards. In addition, this solution does not require direct vehicle-road communication, saving the deployment of the on-board unit OBU and the roadside unit RSU, thereby greatly saving costs. Furthermore, the cloud only sends information to the vehicle when the conditions are met, which can save transmission bandwidth.
  • the method further includes: obtaining second information from the roadside perception device; the second information indicates the perception information of the roadside perception device on the first object when the vehicle perceives the first object; sending the second information to the vehicle; obtaining third information from the vehicle; the third information is a calibration result obtained by calibrating the second information based on the perception information of the vehicle itself; sending the calibration result to the roadside perception device; the calibration result is used to correct the perception confidence of the roadside perception device.
  • communication between the vehicle and the roadside perception device is achieved through the cloud, so that the vehicle can calibrate the roadside perception information based on its own perception information.
  • the calibrated roadside perception information can be used to correct the perception confidence of the roadside perception device and improve the detection accuracy of the roadside perception device.
  • the aforementioned method when the aforementioned vehicle perceives the aforementioned first object, or when the aforementioned first object leaves the perception range of the aforementioned roadside perception device, the aforementioned method further includes: sending fourth information to the aforementioned vehicle; the aforementioned fourth information instructs the aforementioned vehicle to turn off the roadside perception fusion function, and the aforementioned roadside perception fusion function is a function of fusing the perception information of the aforementioned roadside perception device and the perception information of the aforementioned vehicle.
  • the aforementioned method also includes: obtaining fifth information from the aforementioned roadside perception device; the aforementioned fifth information indicates that the aforementioned first object has left the perception range of the aforementioned roadside perception device; and triggering an operation of sending the aforementioned fourth information to the aforementioned vehicle based on the aforementioned fifth information.
  • the cloud device can notify the vehicle to turn off the roadside fusion perception function, restore the single-vehicle perception driving mode, and reduce the fusion calculation overhead.
  • the present application provides a collaborative driving method, which is applied to a roadside perception device, and the method includes: obtaining first perception information; the first perception information includes perception information of a first object and perception information of the vehicle; identifying whether the first object threatens the driving safety of the vehicle based on the first perception information; sending first information to a cloud device, the first information indicating the perception information of the roadside perception device on the first object, and the first information being used to send to the vehicle.
  • the roadside sensing device communicates with the vehicle via the cloud, enabling the roadside sensing device to serve as a blind spot sensor for the vehicle, allowing the vehicle to obtain information beyond its sensing range, thereby providing a more comprehensive understanding of the driving environment and mitigating safety hazards. Furthermore, this solution eliminates the need for direct vehicle-road communication, eliminating the need for onboard vehicle units (OBUs) and roadside units (RSUs), significantly reducing costs. Furthermore, the roadside sensing system can automatically determine if a safety risk exists before sending information, saving data transmission bandwidth.
  • OBUs onboard vehicle units
  • RSUs roadside units
  • the method further includes: sending second information to the cloud device; the second information indicates the perception information of the roadside perception device on the first object when the vehicle perceives the first object; obtaining a calibration result from the cloud device; the calibration result is used to correct the perception confidence of the roadside perception device, and the calibration result is a calibration result obtained by the vehicle calibrating the second information based on its own perception information.
  • communication between the vehicle and the roadside perception device is achieved through the cloud, so that the vehicle can calibrate the roadside perception information based on its own perception information.
  • the calibrated roadside perception information can be used to correct the perception confidence of the roadside perception device and improve the detection accuracy of the roadside perception device.
  • the method further includes: sending a third information to the cloud device; the third information indicates that the first object has left the perception range of the roadside perception device; the third information is used to trigger the cloud device to send the fourth information to the vehicle, and the fourth information indicates that the vehicle turns off a roadside perception fusion function, and the roadside perception fusion function is a function of fusing the perception information of the roadside perception device on the first object and the perception information of the vehicle.
  • the vehicle can instruct the cloud, and the cloud can notify the vehicle to turn off the roadside fusion perception function, restore the single-vehicle perception driving mode, and reduce the fusion computing overhead.
  • the present application provides a vehicle, comprising a unit for implementing any of the methods described in the first aspect.
  • the present application provides a cloud device, which includes a unit for implementing the method described in any one of the second aspects above.
  • the present application provides a roadside perception device, which includes a unit for implementing the method described in any one of the third aspects above.
  • the present application provides a vehicle comprising a processor and a memory.
  • the memory is coupled to the processor, and when the processor executes a computer program or computer instructions stored in the memory, the method described in any one of the first aspects can be implemented.
  • the vehicle may also include a communication interface for communicating with other vehicles.
  • the communication interface may be a transceiver, circuit, bus, module, or other type of communication interface.
  • the vehicle may include:
  • Memory for storing computer programs or computer instructions
  • a processor configured to: obtain first information from a cloud device; the first information includes perception information of a first object by a roadside perception device; obtain first fusion information based on the first information and the first perception information; and perform first driving control based on the first fusion information; wherein the first perception information includes perception information obtained by sensors of the vehicle; and perform second driving control based on the second perception information when the vehicle perceives the first object based on second perception information; the second perception information includes perception information of the first object obtained by sensors of the vehicle.
  • the computer programs or computer instructions in the memory of this application may be pre-stored or downloaded from the Internet and stored when the vehicle is used. This application does not specifically limit the source of the computer programs or computer instructions in the memory.
  • the coupling in the embodiments of this application is an indirect coupling or connection between devices, units, or modules, which may be electrical, mechanical, or other forms, and is used for information exchange between devices, units, or modules.
  • the present application provides a cloud device comprising a processor and a memory.
  • the memory is coupled to the processor, and when the processor executes a computer program or computer instructions stored in the memory, the method described in any one of the second aspects above can be implemented.
  • the cloud device may also include a communication interface for communicating between the cloud device and other cloud devices.
  • the communication interface may be a transceiver, circuit, bus, module, or other type of communication interface.
  • the cloud device may include:
  • Memory for storing computer programs or computer instructions
  • a processor configured to: obtain vehicle status information from a vehicle; the aforementioned vehicle status information includes position information and speed information of the aforementioned vehicle; obtain first information; the aforementioned first information indicates perception information of a first object by a roadside perception device; determine, based on the aforementioned vehicle status information and the aforementioned first information, that the aforementioned first object satisfies a first condition; the aforementioned first condition includes: the distance between the aforementioned first object and the aforementioned vehicle is less than or equal to a first preset distance, and/or the collision time between the aforementioned first object and the aforementioned vehicle is less than or equal to a first preset duration; and send the aforementioned first information to the aforementioned vehicle via a communication interface.
  • the computer programs or computer instructions in the memory of this application can be pre-stored or downloaded from the Internet when using the cloud device.
  • This application does not specifically limit the source of the computer programs or computer instructions in the memory.
  • the coupling in the embodiments of this application is an indirect coupling or connection between devices, units or modules, which can be electrical, mechanical or other forms, and is used for information exchange between devices, units or modules.
  • the present application provides a roadside perception device, comprising a processor and a memory.
  • the memory is coupled to the processor, and when the processor executes a computer program or computer instructions stored in the memory, the method described in any one of the third aspects can be implemented.
  • the roadside perception device may also include a communication interface for communicating with other roadside perception devices.
  • the communication interface may be a transceiver, circuit, bus, module, or other type of communication interface.
  • the roadside sensing device may include:
  • Memory for storing computer programs or computer instructions
  • the processor is used to: obtain first perception information; the aforementioned first perception information includes perception information of a first object and perception information of the aforementioned vehicle; identify whether the aforementioned first object threatens the driving safety of the aforementioned vehicle based on the aforementioned first perception information; send first information to a cloud device through a communication interface, the aforementioned first information indicating the perception information of the aforementioned first object by the aforementioned roadside perception device, and the aforementioned first information is used to be sent to the aforementioned vehicle.
  • the computer programs or computer instructions in the memory of this application may be pre-stored or downloaded from the Internet and stored when the roadside sensing device is used. This application does not specifically limit the source of the computer programs or computer instructions in the memory.
  • the coupling in the embodiments of this application is an indirect coupling or connection between devices, units, or modules, which may be electrical, mechanical, or other forms, and is used for information exchange between devices, units, or modules.
  • the present application provides a collaborative driving system, comprising a vehicle, a cloud device, and a roadside sensing device; wherein the vehicle is the vehicle described in any one of the fourth aspect, the cloud device is the cloud device described in any one of the fifth aspect, and the roadside sensing device is the roadside sensing device described in any one of the sixth aspect.
  • the aforementioned vehicle is the vehicle described in any one of the seventh aspects
  • the aforementioned cloud device is the cloud device described in any one of the eighth aspects
  • the aforementioned roadside sensing device is the roadside sensing device described in any one of the ninth aspects.
  • the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program or computer instructions, and the computer program or computer instructions are executed by a processor to implement the method described in any one of the first aspects above.
  • the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program or computer instructions, and the computer program or computer instructions are executed by a processor to implement the method described in any one of the second aspects above.
  • the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program or computer instructions, and the computer program or computer instructions are executed by a processor to implement the method described in any one of the third aspects above.
  • the present application provides a computer program product.
  • the aforementioned computer program product is executed by a processor, the method described in any one of the aforementioned first aspects will be implemented.
  • the present application provides a computer program product.
  • the aforementioned computer program product is executed by a processor, the method described in any one of the aforementioned second aspects will be implemented.
  • the present application provides a computer program product.
  • the aforementioned computer program product is executed by a processor, the method described in any one of the aforementioned third aspects will be implemented.
  • Figures 1 and 2 are schematic diagrams of a cooperative driving system provided in an embodiment of the present application
  • FIG3 and FIG3A are schematic diagrams of an application scenario architecture provided by an embodiment of the present application.
  • FIGS. 4 to 8 are schematic diagrams of application scenarios provided by embodiments of the present application.
  • FIG9 is a schematic diagram of a method flow chart provided in an embodiment of the present application.
  • 10 to 13 are schematic diagrams showing the structure of the device provided in the embodiments of the present application.
  • V2X vehicle-to-everything
  • a V2X device i.e., an on-board unit (OBU)
  • OBU on-board unit
  • BSM basic safety message
  • RSU roadside unit
  • Another existing solution combines vehicle trajectory information to determine vehicle status, generating a trajectory using vehicle information from multiple roadside RSUs. This trajectory information is then transmitted to other vehicles via the RSUs, enabling them to make more accurate driving decisions.
  • this solution primarily relies on generating a trajectory using vehicle information acquired by multiple RSUs, which is then transmitted to other vehicles to ensure safe driving and avoid collisions.
  • This implementation also requires the deployment of a large number of RSUs along the road.
  • the existing implementation scheme is difficult to implement in actual application. Specifically, from the perspective of the roadside, it is necessary to continuously deploy RSU on the road, which results in very high deployment costs. From the perspective of the vehicle, it is necessary to deploy OBU-related equipment on the vehicle side to achieve roadside communication, which also increases the cost of purchasing the vehicle and increases the vehicle failure points. On the other hand, since a special spectrum is required to achieve vehicle-road communication through RSU and OBU. The communication spectrum requirements are different in different countries, which also leads to different implementations of vehicle-road collaboration solutions in different countries. It also increases the deployment certification requirements of RSU and vehicles in different countries, thereby increasing the cost overhead caused by certification.
  • the embodiments of the present application provide corresponding methods and related devices.
  • FIG. 1 is a schematic diagram of the structure of a collaborative driving system 100 provided in an embodiment of the present application.
  • the collaborative driving system 100 includes a cloud device 101, a vehicle 102, and a roadside sensing device 103. There can be one or more vehicles 102 and roadside sensing devices 103, and this embodiment of the present application does not limit this.
  • the cloud device 101 may include, for example, a cloud server and/or a cloud virtual machine, and other devices capable of performing calculations and/or data processing.
  • the cloud device 101 may include, for example, a server cluster.
  • the cloud device 101 may communicate with the vehicle 102 and provide a variety of services for the vehicle 102. For example, it may provide the vehicle 102 with over-the-air (OTA) services, high-precision map services, autonomous driving or assisted driving services, and information forwarding services.
  • OTA over-the-air
  • the cloud device 101 may also communicate with the roadside sensing device 103 and provide a variety of services for the roadside sensing device 103. For example, it may provide the roadside sensing device 103 with information analysis and processing services, or information forwarding services.
  • the vehicle 102 can be any type of vehicle traveling on the road.
  • it can be a car, a bus, a truck, a fire truck, a police car, a sanitation truck, a concrete truck, a semi-trailer, a garbage truck, or a forklift.
  • the vehicle 102 can be driven using intelligent driving technologies such as assisted driving or autonomous driving.
  • the vehicle 102 is equipped with a detection device for detecting and sensing the environment around the vehicle 102.
  • the detection device can include sensors such as a camera or a radar.
  • the radar can include various types of radars such as ultrasonic radar, laser radar, millimeter wave radar, or microwave radar, but this embodiment of the present application does not limit this.
  • Each detection device has its own detection range.
  • the detection device can sense objects within the detection range. In this embodiment of the present application, if a detection device cannot sense an object, it is considered that the object is not within the detection range of the detection device.
  • the detection range can also be referred to as the perception range.
  • the superposition of the detection ranges of one or more detection devices installed in the vehicle 102 is the perception range of the vehicle 102.
  • vehicle 102 can interact with cloud device 101 to enhance intelligent driving capabilities, thereby improving vehicle safety and travel efficiency.
  • vehicle 102 can collect road and surrounding vehicle information using sensors installed on the vehicle body, and upload this information, along with its own driving status information, to cloud device 101.
  • Vehicle 102 can also receive information from cloud device 101 to assist in its own driving.
  • the roadside sensing device 103 may be a sensing device deployed on both sides of the road.
  • the roadside sensing device 103 may include, for example, a detection device such as a camera or radar.
  • the radar may include, for example, various types of radars, such as ultrasonic radar, lidar, millimeter-wave radar, or microwave radar, though this embodiment of the present application does not limit this.
  • the roadside sensing device 103 may also include a perception computing unit. This perception computing unit processes and analyzes data sensed by the sensors to obtain analyzed information.
  • the roadside sensing device 103 may interact with the cloud device 101 to transmit the obtained information to the cloud device 101.
  • the roadside sensing device 103 also has its own detection range (actually, the detection range of a detection device such as a camera or radar).
  • the detection device can sense objects within this detection range. In this embodiment of the present application, if a detection device cannot sense an object, it is considered to be outside the detection range of the detection device.
  • This detection range may also be referred to as the perception range of the roadside sensing device 103.
  • the perception computing unit of the roadside sensing device 103 may be integrated with the sensor. Alternatively, the perception computing unit may be an independent device or module capable of communicating with the sensor.
  • the vehicle 102 and roadside sensing device 103 can communicate with the cloud device 101 via wired or wireless communication.
  • This embodiment of the present application uses wireless communication as an example.
  • the vehicle 102 and roadside sensing device 103 access a communication network 104 via wireless communication.
  • the communication network 104 transmits information from the vehicle 102 and/or roadside sensing device 103 to the cloud device 101.
  • the wireless access device may include a baseband pool (BBU) and a radio unit (RRU).
  • BBU baseband pool
  • RRU radio unit
  • the wireless access device may also be an access network device or a module of an access network device in an open access network (open RAN, ORAN) system.
  • the wireless access device may be a module or unit that can implement some functions of a base station.
  • the wireless access device may be a centralized unit (CU), a distributed unit (DU), a CU-control plane (CP), a CU-user plane (UP), or a radio unit (RU), etc.
  • the CU may also be referred to as an O-CU
  • the DU may also be referred to as an open (open, O)-DU
  • the CU-CP may also be referred to as an O-CU-CP
  • the CU-UP may also be referred to as an O-CUP-UP
  • the RU may also be referred to as an O-RU. It will be understood that this is merely an example, and the embodiments of the present application do not limit the specific technology and specific device form adopted by the wireless access device.
  • the communication network 104 further includes a network device.
  • the network device is connected to the wireless access device and is used to forward the information received by the wireless access device from the vehicle 102 and/or the roadside sensing device 103 to the cloud device 101.
  • the cloud device 101 can send information to the vehicle 102 and/or the roadside sensing device 103 through the communication network 104.
  • the network device may include, for example, a router, a switch, a wireless relay device or a wireless backhaul device, etc. It is understood that this is only an example, and the embodiments of the present application do not limit the specific technology and specific device form adopted by the network device.
  • the cloud device 101 is deployed with software systems such as a fleet management system (FMS), a high-precision map service system, a vehicle dispatching service system, a vehicle operation supervision service system, an emergency takeover service system, and an intelligent driving system.
  • FMS fleet management system
  • the transport operation management system can integrate information provided by one or more of the high-precision map service system, the vehicle dispatching service system, the vehicle operation supervision service system, the emergency takeover service system, and the intelligent driving system to achieve vehicle operation management and/or control.
  • the various service systems of the cloud device 101 can receive information from the vehicle 102 and/or the roadside sensing device 103 through the communication network 104, and integrate the received information into the transport operation management system to achieve vehicle operation management and/or control. Relevant management and/or control information is also sent to the vehicle through the communication network 104 to achieve vehicle-road-cloud intelligent driving.
  • the above-mentioned intelligent driving system can be used to cooperate with the intelligent driving of vehicle 102.
  • it can be used to cooperate with the operation of the cloud device in the intelligent driving method provided in the embodiment of the present application.
  • the subsequent introduction please refer to the subsequent introduction and will not be described in detail here.
  • an on-board intelligent driving system is deployed in the vehicle 102.
  • an assisted driving system or an automatic driving system is deployed.
  • the on-board intelligent driving system can realize functions such as perception, positioning, decision-making, planning (such as path planning) or control. These functions can be realized by sensors such as radar or cameras, hardware such as telematics BOX (T-BOX) or wire-controlled chassis, and on-board computing units.
  • the software of the on-board intelligent driving system can be deployed in a vehicle domain controller (VDC), a cockpit domain controller (CDC), a mobile data center (MDC) or other processing and control modules, and the embodiments of the present application do not impose any restrictions on this.
  • VDC vehicle domain controller
  • CDC cockpit domain controller
  • MDC mobile data center
  • the roadside perception device 103 includes a sensor and a perception computing unit. Please refer to the corresponding introduction in the above-mentioned FIG1 for details, which will not be repeated here.
  • the vehicle 102 and the roadside sensing device 103 may further include a device for communicating with the cloud device 101.
  • a communication device or module such as a customer premises equipment (CPE) may be included.
  • the communication device or module may be connected to the communication network 104 to communicate with the cloud device 101.
  • the embodiments of the present application do not limit the communication device or module.
  • CPE devices are mainly divided into two types: wired CPE and wireless CPE.
  • Wired CPE generally uses Ethernet as the data transmission medium and supports access methods such as passive optical network (PON), very/ultra-high-bit-rate digital subscriber loop (VDSL), and asymmetric digital subscriber line (ADSL).
  • Wireless CPE can directly access 4G or 5G networks, or access wired networks through external antennas, wireless APs, wireless base stations, or routers.
  • FIG3A an example can be seen in FIG3A .
  • the CPE in the roadside sensing device 103 can communicate with the cloud device 101 through wired communication.
  • the CPE in the roadside sensing device 103 and the cloud device 101 can be connected via optical fiber to achieve data transmission.
  • the CPE in the vehicle 102 can access the base station wirelessly and then communicate with the cloud device 101 via the core network.
  • FIG3A is only an example and does not constitute a limitation to the embodiments of the present application.
  • FIG3 is merely an example and does not constitute a limitation on the embodiments of the present application.
  • the cloud device 101, vehicle 102, or roadside sensing device 103 may include more or fewer hardware components or software units, or may be replaced with modules that can achieve the same functions, etc., and the specific configuration can be based on actual application requirements, and the embodiments of the present application do not impose any restrictions on this.
  • the roadside sensing device 103 can be deployed in blind spots on the road.
  • These blind spots include sections that are beyond the vehicle's sensing range and are prone to accidents that threaten vehicle driving safety.
  • these blind spots can include curved sections, sections at intersections, sections at entrances or exits, or sections at the top of slopes, etc. It is understood that the size of these blind spots can be determined based on the specific circumstances of the actual application scenario, and this embodiment of the present application does not impose any restrictions on this.
  • the curved road section may be any curved road section, and the embodiment of the present application does not limit this.
  • the above-mentioned road sections including intersections may include cross-shaped intersections, roundabout intersections, X-shaped intersections, T-shaped intersections, Y-shaped intersections, staggered intersections, multi-way intersections, etc.
  • the road section including an entrance or exit may include a tunnel entrance or exit, a residential area entrance or exit, a garage or parking lot entrance or exit, and the like.
  • the above-mentioned top section may include an uphill top section or a downhill top section, etc.
  • FIG4 exemplarily shows a schematic diagram of an application scenario in which the driving blind spot section is a curved road section.
  • vehicle 102 the perception range of vehicle 102 is limited, and it cannot perceive objects in the curved road section (such as vehicle A). Therefore, a roadside perception device 103 is deployed on the curved road section.
  • the perception range of the roadside perception device 103 can cover the curved road section, so it can perceive objects in the curved road section (such as vehicle A).
  • one or more roadside perception devices 103 can be deployed in the curved road section (the one shown in FIG4 is only an example), and the specific number of deployments is not limited in the embodiment of the present application.
  • the roadside perception device 103 can be deployed on either side of the curved road section, or can be deployed on both sides of the curved road section, depending on the actual application deployment, and the embodiment of the present application does not limit this.
  • Figure 5 exemplarily shows a schematic diagram of an application scenario in which a driving blind spot section is a section including an intersection (referred to as the intersection section).
  • a roadside perception device 103 is deployed in the intersection section.
  • the perception range of the roadside perception device 103 can cover the intersection section, so it can perceive objects in the intersection section (such as vehicle A).
  • one or more roadside perception devices 103 can be deployed in the intersection section (the one shown in Figure 5 is only an example), and the specific number of deployments is not limited in this embodiment of the application.
  • the roadside perception device 103 can be deployed at any position on both sides of the road in the intersection section, and the specific deployment is based on the actual application, which is not limited in this embodiment of the application.
  • Figure 6 exemplarily shows a schematic diagram of an application scenario in which a driving blind spot section includes a tunnel entrance section.
  • a roadside perception device 103 is deployed in the tunnel entrance section.
  • the perception range of the roadside perception device 103 can cover the tunnel entrance section, so it can perceive objects in the tunnel entrance section (such as static obstacle A).
  • one or more roadside perception devices 103 can be deployed in the tunnel entrance section (the one shown in Figure 6 is only an example), and the specific number of deployments is not limited in this embodiment of the application.
  • the roadside perception device 103 can be deployed at any position on both sides of the road in the tunnel entrance section, and the specific deployment is based on the actual application, which is not limited in this embodiment of the application.
  • Figures 7 and 8 exemplify a schematic diagram of an application scenario in which a driving blind spot section includes a hilltop section.
  • Figure 7 shows a schematic diagram of a scenario in which vehicle 102 is going uphill
  • Figure 8 shows a schematic diagram of a scenario in which vehicle 102 is going downhill.
  • the perception range of vehicle 102 is limited and it cannot perceive objects in the hilltop section (such as vehicle A). Therefore, a roadside sensing device 103 is deployed in the hilltop section.
  • the perception range of the roadside sensing device 103 can cover the hilltop section, so it can perceive objects in the hilltop section (such as vehicle A).
  • one or more roadside sensing devices 103 can be deployed in the hilltop section (the one shown in Figure 6 is only an example), and the specific number of deployments is not limited in this embodiment of the application.
  • the roadside sensing device 103 can be deployed at any position on both sides of the road in the hilltop section, and the specific deployment is based on the actual application, and the embodiment of the application does not limit this.
  • Figures 4 to 8 illustrate the vehicle 102 primarily on the blind spot
  • the vehicle 102 may be traveling on a road area outside the blind spot, such as when the vehicle 102 is traveling toward the blind spot but has not yet entered the blind spot.
  • the method may include but is not limited to the following steps.
  • a roadside sensing device obtains first information.
  • the roadside sensing device may be, for example, the roadside sensing device 103 in the above-mentioned collaborative driving system 100.
  • the vehicle may be, for example, the vehicle 102 in the collaborative driving system 100.
  • the vehicle may be a vehicle traveling toward a blind spot section.
  • the blind spot section may be, for example, any one of the blind spot sections described above, which will not be described in detail here.
  • the roadside sensing device is deployed on the blind spot section, and the specific deployment application scenarios may be exemplified by referring to FIG. 4 or FIG. 8 above, which will not be described in detail here.
  • the roadside sensing device may include one or more sensing devices deployed on the blind spot section.
  • the perception range of the above-mentioned roadside perception device can cover the above-mentioned blind spot section, so that the objects in the blind spot section can be perceived (including the above-mentioned first object, which can be, for example, one or more objects in the blind spot section).
  • the objects in the blind spot section can include moving objects and stationary objects.
  • the moving objects include, for example, vehicles, pedestrians, animals, or any objects that move in the blind spot section.
  • the stationary objects include, for example, static obstacles such as mounds in the blind spot section, signboards temporarily blocked due to construction or other reasons, vehicles that have stopped due to accidents, or other objects placed on the road. It will be understood that the objects introduced here are only examples and do not constitute a limitation on the embodiments of the present application. Other objects may also be included in the specific implementation, and the embodiments of the present application do not impose any limitation on this.
  • the sensor in the roadside perception device can detect objects in the blind spot section of the road and obtain detection data.
  • the detection data can be image data captured by the camera.
  • the detection data can be point cloud data detected by the radar. That is, the detection data is the original perception data of the roadside perception device. It will be understood that the description of the detection data here is only an example and does not constitute a limitation to the embodiments of the present application.
  • the senor after acquiring detection data, transmits the data to a perception computing unit within the roadside sensing device.
  • the perception computing unit processes and analyzes the detection data.
  • the detection data includes data acquired from detecting the first object within the blind spot. The following description uses this first object as an example.
  • the perception computing unit may extract one or more pieces of perception information of the first object, including the position, movement speed, movement direction, type (e.g., vehicle or pedestrian), and identification.
  • the specific analysis and processing method may be, for example, any one or more methods for extracting perception information of an object from image data or point cloud data, and this embodiment of the application is not limited thereto.
  • the first information may include one or more of the extracted perception information.
  • the first information may also include the perception confidence information of the sensor.
  • the first information may also include event information corresponding to the first object.
  • the event information may be, for example, event information determined in vehicle-to-everything (V2X) technology.
  • V2X vehicle-to-everything
  • the first information may be referred to as the perception information after analysis and processing.
  • the first information includes detection data of the first object by the roadside perception device, that is, raw perception data of the first object.
  • the first information may also include perception confidence information of the sensor and/or event information corresponding to the first object.
  • this first information may be referred to as unanalyzed perception information.
  • the roadside perception device sends the first information to the cloud device.
  • the first information indicates the perception information of the roadside perception device on the first object when the vehicle cannot perceive the first object.
  • the roadside perception device may send the first information to the cloud device through a communication module or device (such as the CPE, etc.).
  • a communication module or device such as the CPE, etc.
  • the roadside perception device when the first object is outside the vehicle's perception range (i.e., the vehicle cannot perceive the first object), the roadside perception device sends the first information to the cloud device.
  • the vehicle and the first object are both located on a blind spot, so the roadside perception device can perceive the vehicle.
  • the first object can be, for example, object A in the figure (e.g., vehicle A or static obstacle A in the figure), and the vehicle can be vehicle 102 in the figure. Because the vehicle is located on a blind spot, the roadside perception device can perceive the vehicle and obtain perception information about the vehicle.
  • the distance between the vehicle and the first object can be calculated.
  • the specific distance calculation method is not limited in this embodiment of the present application.
  • the size of the distance is determined. If the distance is greater than a preset distance, it can be determined that the first object is outside the vehicle's perception range.
  • the preset distance can be, for example, the vehicle's perception distance or a custom distance, etc.
  • the roadside perception device when the above-mentioned first object satisfies the first condition, the roadside perception device sends the above-mentioned first information to the above-mentioned cloud device.
  • the first condition may include that the distance between the first object and the above-mentioned vehicle is less than or equal to a first preset distance, and/or includes that the collision time (time-to-collision, TTC) between the first object and the above-mentioned vehicle is less than or equal to a first preset duration.
  • TTC time-to-collision
  • the above-mentioned first object is outside the perception range of the above-mentioned vehicle, and the roadside perception device does not necessarily send the above-mentioned first information to the cloud device.
  • the above-mentioned first information is sent to the above-mentioned cloud device.
  • the first preset distance and/or the first preset duration may be set according to actual application requirements, and the present application embodiment does not limit this. Through this implementation, unnecessary redundant data transmission can be further saved, saving transmission bandwidth.
  • the roadside sensing device may transmit the first information to the cloud device according to a preset format structure.
  • the roadside sensing device may encapsulate the first information into a message or packet and transmit it to the cloud device.
  • the first information may be encapsulated into a roadside safety message (RSM) and transmitted to the cloud device.
  • RSM roadside safety message
  • S903 The cloud device obtains the first information.
  • the cloud device can receive the first information.
  • the cloud device sends second information to the vehicle, where the second information is obtained based on the first information.
  • the cloud device receives the first information, can obtain second information based on the first information, and then can send the second information to the vehicle.
  • the cloud device can analyze and process the raw perception data in the first information to extract one or more of the first object's location, movement speed, movement direction, type, and identification.
  • the second information then includes the one or more pieces of perception information.
  • the first information can be directly sent to the vehicle as the second information. This is not a limitation in the present embodiment.
  • the cloud device can send the first information as the above second information to the vehicle.
  • it can select part of the first information and send it to the vehicle. This embodiment of the present application is not limited to this.
  • the cloud device transmits the second information to the vehicle if the first object satisfies a second condition.
  • the second condition includes the distance between the first object and the vehicle being less than or equal to a second preset distance, and/or the time between the collision of the first object and the vehicle being less than or equal to a second preset duration.
  • the vehicle may send its driving status information to a cloud device.
  • This driving status information may include one or more of the vehicle's location, driving speed, direction of movement (or driving direction), type, and identification. It should be understood that the driving status information described herein is merely illustrative and does not constitute a limitation on the embodiments of the present application.
  • the cloud device may calculate the distance between the vehicle and the first object and/or the collision time between the vehicle and the first object based on the driving status information and the received first information. For example, the cloud device may calculate the distance and/or collision time in conjunction with a high-precision map, and the embodiments of the present application do not limit the specific implementation process of this calculation.
  • the cloud device sends the second information to the vehicle.
  • the second preset distance and/or the second preset duration may be set based on actual application requirements, and the embodiments of the present application do not limit this. This implementation method can save unnecessary redundant data transmission and save transmission bandwidth.
  • the vehicle obtains the second information and obtains first fusion information based on the second information and the first perception information; and performs first driving control based on the first fusion information;
  • the first perception information includes perception information obtained by the vehicle's sensors; when the vehicle perceives the first object based on the second perception information, the vehicle performs second driving control based on the second perception information;
  • the second perception information includes perception information of the first object obtained by the vehicle's sensors.
  • the operations performed by the vehicle described in the embodiments of the present application may be performed by a vehicle controller.
  • the operations may be performed by a VDC, CDC, MDC, or other controller that deploys the software of the vehicle-mounted intelligent driving system shown in FIG. 3 .
  • the vehicle's own sensors are also constantly detecting the surrounding road conditions to obtain its own perception information. After the vehicle receives the second information from the cloud device, it can achieve information fusion based on the second information and the vehicle's own perception information.
  • the vehicle can fuse the second information and its own perception information into a high-precision map.
  • any perception information fusion method can be used to achieve the fusion of the second information and the vehicle's own perception information, and the embodiment of the present application does not limit the method of perception information fusion.
  • intelligent driving control of the vehicle is implemented based on the fused high-precision map.
  • the vehicle can perceive the existence of the first object based on the fused high-precision map, and thus can calculate the distance and/or collision time between itself and the first object. Then, based on the distance and/or collision time, operational controls such as deceleration or lane changing are performed to achieve safe driving.
  • the vehicle may integrate the second information and its own perception information into a customized map. Based on the integrated map, the vehicle may also sense the presence of the first object and, based on the distance to the first object and/or collision time, perform maneuvers such as deceleration or lane change to achieve safe driving.
  • the vehicle's own perception information includes the perception information of the first object. This eliminates the need to fuse roadside perception data with the vehicle's own perception data. While conserving computing resources, the vehicle's own perception data offers a higher degree of confidence, enabling more accurate and rational driving control and reducing the risk of accidents.
  • the vehicle after the vehicle can perceive the first object, it can still receive perception information (referred to as third information) from the roadside perception device regarding the first object from the cloud device.
  • This third information can then be fused with the vehicle's own perception information according to a weight ratio, and corresponding driving control can be performed based on the fused perception information.
  • the weight of the vehicle's own perception information is greater than the weight of the third information.
  • the weight can be expressed as a percentage or a score, which is not limited in this embodiment of the present application.
  • the fusion of the vehicle's own perception information and the third information can be achieved using a perception fusion model, such as a machine learning model or a deep learning model.
  • the input of the perception fusion model can include the vehicle's own perception information (including the perception information regarding the first object), the third information, and the weight (or weight ratio) of the two information, and the output is the fused perception information.
  • Driving control can then be performed based on the fused perception information.
  • the roadside perception information is utilized to expand the vehicle's perception range, and on the other hand, the higher weight ratio of the vehicle's own perception can increase the confidence level of the perception fusion.
  • the roadside perception device has a higher confidence level in sensing vehicles and a lower confidence level in sensing pedestrians. Therefore, if the roadside perception information forwarded by the cloud device to the vehicle includes perception information about the vehicle, the vehicle can fuse the perception information of the vehicle with its own perception information.
  • the first object includes one or more target vehicles
  • the second information includes the perception information of the roadside perception device on the one or more target vehicles. If the roadside perception information forwarded by the cloud device to the vehicle includes perception information about pedestrians, the perception information about pedestrians can be discarded and not used. This is to reduce interference with subsequent fusion and driving control. Exemplarily, for example, it is possible to determine whether it is the perception information of pedestrians or the perception information of vehicles by the type in the second information.
  • the vehicle may detect the first object and obtain perception information of the first object (referred to as second perception information).
  • the second perception information may include one or more of the following: the location, movement speed, movement direction, type, and identification of the first object.
  • the vehicle can still receive the perception information of the first object detected by the above-mentioned roadside perception device (referred to as the fourth information) from the cloud device. Then, the vehicle can calibrate the fourth information based on its own perception information of the first object to obtain a calibration result.
  • the fourth information also indicates one or more of the position, moving speed, moving direction, type and identification of the first object.
  • the vehicle can also obtain one or more of the position, moving speed, moving direction, type and identification of the first object by analyzing and processing the perception information of the first object.
  • data association can be performed using a Euclidean distance algorithm or a Mahalanobis distance algorithm to achieve a match between the first object perceived by the roadside device and the first object perceived by the vehicle.
  • the vehicle can then compare the fourth information with the vehicle's perception information of the first object to obtain deviation information of the perception information.
  • the fourth information can be compared with the position information in the vehicle's perception information of the first object to obtain a position deviation.
  • the fourth information can also be compared with the moving speed in the vehicle's perception information of the first object to obtain a speed deviation, and so on.
  • the one or more deviations constitute the deviation information of the perception information, and the deviation information is the above-mentioned calibration result.
  • the vehicle may first fuse the above-mentioned vehicle's perception information of the first object and the fourth information into the vehicle's map (such as a high-precision map or a custom map). Then, the vehicle can obtain one or more of the position, moving speed, moving direction, type and identification of the first object based on the fused map. This information is referred to as fused perception information. The vehicle can then compare the fourth information with the fused perception information to obtain deviation information of the perception information. For example, the fourth information can be compared with the position information in the fused perception information to obtain a position deviation. Optionally, the fourth information can also be compared with the moving speed in the fused perception information to obtain a speed deviation, and so on. The one or more deviations constitute the deviation information of the perception information, and the deviation information is the above-mentioned calibration result.
  • the vehicle's map such as a high-precision map or a custom map.
  • the vehicle can obtain one or more of the position, moving speed, moving direction, type and identification of the first object
  • the vehicle can send them to the cloud device.
  • the cloud device then sends them to the roadside perception device.
  • the roadside perception device calibrates its perception confidence level based on them. For example, the roadside perception device can use these calibration results as calibration parameters to input the perception model of its own perception computing unit to calibrate the parameters of the perception model, thereby calibrating the perception confidence level of the roadside perception device.
  • the roadside sensing device may send fifth information to the cloud device.
  • the roadside sensing device fails to detect the presence of the first object in the detection information detected by the sensor, for example, if it fails to extract the sensing information of the first object, it can be determined that the first object has left the aforementioned blind spot section.
  • the fifth information is used to indicate that the first object has left the aforementioned blind spot section.
  • the fifth information can be empty data or can be preset first indicator information, etc., which is not limited in this embodiment of the present application.
  • the roadside perception device extracts the perception information of the first object and the vehicle from the detection information detected by the sensor, and then calculates the distance between the two. If the distance is less than a preset distance, it can be determined that the first object has entered the perception range of the vehicle.
  • the fifth information is used to indicate that the first object has entered the perception range of the vehicle.
  • the fifth information can be a preset second indicator mark information, etc., which is not limited in this embodiment of the present application.
  • the second indicator mark information and the first indicator mark information can be the same or different.
  • the cloud device can learn that the first object has left the blind spot section, or the first object has entered the perception range of the vehicle. If the first object leaves the blind spot section, it indicates that the first object will not (or will not temporarily) pose a threat to the driving safety of the vehicle. If the first object enters the perception range of the vehicle, the vehicle can handle it based on its own perception information. Therefore, the cloud device can generate perception fusion shutdown information based on the fifth information and send the perception fusion shutdown information to the vehicle. After the vehicle receives the perception fusion shutdown information, it restores the single-vehicle perception driving mode according to the instructions of the information and turns off the function of fusing the perception information of the first object detected by the roadside perception device.
  • the first object is the last object to leave the blind spot section. Only in this case will the fusion shutdown operation be triggered. That is, there are no objects in the blind spot section that threaten the driving safety of the vehicle.
  • the roadside detection device can send empty data to the cloud device. For example, the data in the message or message sent to the cloud device is empty. After receiving the empty data, the cloud device can send the perception fusion shutdown information to the vehicle. If there are other objects in the blind spot section after the first object leaves the blind spot section, especially objects that threaten the driving safety of the vehicle, the fusion shutdown operation will not be triggered.
  • the roadside sensing device may also obtain the traffic light's traffic indication information and send it to the cloud device.
  • This traffic indication information may be, for example, traffic light phase information.
  • the cloud device may dynamically calculate the optimal path and/or speed for the vehicle based on the vehicle's location information and send this information to the vehicle. After receiving this information, the vehicle may perform corresponding driving control based on this information, for example, driving according to the optimal path and/or speed.
  • the cloud device may only send the calculated optimal path and/or speed information to the vehicle if the information is different from the information reported by the vehicle, thereby saving transmission bandwidth.
  • roadside sensing devices are deployed in blind spots on the road instead of continuously deploying a large number of sensing devices on the road; and the vehicle does not communicate with the roadside sensing device, but realizes information interaction between the vehicle and the road through the cloud, so that there is no need to deploy OBU in the vehicle and no need to use expensive RSU on the roadside, thereby greatly reducing costs.
  • the roadside sensing device is regarded as an extension of the vehicle's sensing device, that is, the information perceived by the roadside sensing device is directly sent to the vehicle via the cloud, and the vehicle integrates the received sensing information with the information perceived by its own sensing device to expand the vehicle's sensing range and reduce driving safety hazards. That is, this solution provides a vehicle-road collaboration solution that can effectively reduce vehicle driving safety hazards, has low implementation costs, and is easy to promote and use.
  • each control unit or device includes a hardware structure and/or software module corresponding to the execution of each function.
  • the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
  • the embodiment of the present application can divide the functional modules of the device according to the above method example.
  • each functional module can be divided according to each function, or two or more functions can be integrated into one module.
  • the above integrated modules can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiment of the present application is schematic and is only a logical function division. In actual implementation, there may be other division methods.
  • the embodiment of the present application also provides an apparatus for implementing any of the above methods.
  • the provided apparatus includes units (or means) for implementing each step in any of the above methods.
  • FIG 10 is a schematic diagram of the structure of a driving control system 1000 provided in an embodiment of the present application.
  • the driving control system 1000 shown in Figure 10 can be a driving control system in a vehicle in any embodiment of the above method.
  • the driving control system 1000 can include an acquisition unit 1001 and a processing unit 1002. Among them:
  • An acquiring unit 1001 is configured to acquire first information from a cloud device; the first information includes perception information of a first object by a roadside perception device;
  • the processing unit 1002 is configured to obtain first fusion information based on the first information and the first perception information; and perform first driving control based on the first fusion information; wherein the first perception information includes perception information obtained by a sensor of the vehicle;
  • the processing unit 1002 is further configured to execute a second driving control according to the second perception information when the vehicle perceives the first object according to the second perception information; the second perception information includes perception information of the first object obtained by the sensor of the vehicle.
  • the first object includes one or more target vehicles
  • the first information includes perception information of the roadside perception device on the one or more target vehicles.
  • the acquiring unit 1001 is further configured to acquire second information from a cloud device; the second information indicates perception information of the roadside perception device on the second object; the second object includes one or more pedestrians;
  • the processing unit 1002 is specifically configured to:
  • the second driving control is performed according to the second fusion information.
  • the acquiring unit 1001 is further configured to acquire fourth information from a cloud device; the fourth information indicates perception information of the roadside perception device on the first object when the vehicle perceives the first object;
  • the vehicle also includes a sending unit for sending the calibration result, which is used to correct the perception confidence of the roadside perception device.
  • the acquiring unit 1001 is further configured to, when the vehicle senses the first object, or when the first object leaves the sensing range of the roadside sensing device,
  • the fifth information instructs the vehicle to turn off a roadside perception fusion function, where the roadside perception fusion function is a function of fusing perception information of the roadside perception device with perception information of the vehicle.
  • the acquiring unit 1001 is specifically configured to:
  • the first condition includes: a distance between the first object and the vehicle is less than or equal to a first preset distance, and/or a collision time between the first object and the vehicle is less than or equal to a first preset duration.
  • FIG 11 is a schematic diagram of the structure of a cloud device 1100 provided in an embodiment of the present application.
  • the cloud device 1100 shown in Figure 11 can be a cloud device for implementing any embodiment of the above method.
  • the cloud device 1100 may include an acquisition unit 1101, a processing unit 1102, and a sending unit 1103. Among them:
  • the acquisition unit 1101 is configured to acquire vehicle status information from a vehicle; the vehicle status information includes location information and speed information of the vehicle;
  • the processing unit 1102 is configured to determine, based on the vehicle state information and the first information, that the first object satisfies a first condition; the first condition comprising: a distance between the first object and the vehicle is less than or equal to a first preset distance, and/or a collision time between the first object and the vehicle is less than or equal to a first preset duration;
  • the acquiring unit 1101 is further configured to acquire second information from the roadside sensing device; the second information indicates perception information of the roadside sensing device regarding the first object when the vehicle perceives the first object;
  • the sending unit 1103 is further configured to send the second information to the vehicle;
  • the sending unit 1103 is further configured to send the calibration result to the roadside perception device; the calibration result is used to correct the perception confidence of the roadside perception device.
  • the sending unit 1103 is further configured to, when the vehicle senses the first object, or when the first object leaves the sensing range of the roadside sensing device,
  • the acquiring unit 1101 is further configured to acquire fifth information from the roadside sensing device; the fifth information indicates that the first object has left a sensing range of the roadside sensing device;
  • Figure 12 is a schematic diagram of the structure of a roadside sensing device 1200 provided in an embodiment of the present application.
  • the roadside sensing device 1200 shown in Figure 12 can be a roadside sensing device for implementing any embodiment of the above method.
  • the roadside sensing device 1200 may include an acquisition unit 1201, a processing unit 1202, and a sending unit 1203. Among them:
  • An acquiring unit 1201 is configured to acquire first perception information, wherein the first perception information includes perception information of the first object and perception information of the vehicle;
  • the processing unit 1202 is configured to identify, based on the first perception information, whether the first object threatens the driving safety of the vehicle;
  • the sending unit 1203 is used to send first information to the cloud device, where the first information indicates the perception information of the roadside perception device on the first object, and the first information is used to be sent to the vehicle.
  • the sending unit 1203 is further configured to send second information to the cloud device; the second information indicates perception information of the roadside perception device on the first object when the vehicle perceives the first object;
  • the roadside perception device also includes an acquisition unit for obtaining a calibration result from the cloud device; the calibration result is used to correct the perception confidence of the roadside perception device, and the calibration result is a calibration result obtained by the vehicle calibrating the second information based on its own perception information.
  • the sending unit 1203 is further configured to
  • a third message is sent to the cloud device; the third message indicates that the first object has left the perception range of the roadside perception device; the third message is used to trigger the cloud device to send the fourth message to the vehicle, and the fourth message instructs the vehicle to turn off the roadside perception fusion function, which is a function of fusing the perception information of the roadside perception device on the first object and the perception information of the vehicle.
  • the division of the various units in the above vehicle, cloud device, or roadside sensing device is only a division of logical functions. In actual implementation, they can be fully or partially integrated into a physical entity, or they can be physically separated.
  • the units in the device can be implemented in the form of a processor calling software; for example, the device includes a processor, the processor is connected to a memory, and the memory stores instructions.
  • the processor calls the instructions stored in the memory to implement any of the above methods or realize the functions of the various units of the device, where the processor is, for example, a general-purpose processor, such as a central processing unit (CPU) or a microprocessor, and the memory is a memory within the device or a memory outside the device.
  • CPU central processing unit
  • microprocessor a microprocessor
  • the units in the device may be implemented in the form of hardware circuits, and the functions of some or all of the units may be implemented by designing the hardware circuits.
  • the hardware circuits may be understood as one or more processors.
  • the hardware circuit is an application-specific integrated circuit (ASIC), and the functions of some or all of the above units may be implemented by designing the logical relationships between the components within the circuit.
  • the hardware circuit may be implemented by a programmable logic device (PLD).
  • PLD programmable logic device
  • FPGA field programmable gate array
  • All units of the above devices may be implemented entirely by a processor calling software, or entirely by a hardware circuit, or partially by a processor calling software, with the remainder implemented by a hardware circuit.
  • a processor is a circuit with data processing capabilities.
  • the processor can be a circuit with instruction reading and execution capabilities, such as a CPU, a microprocessor, a graphics processing unit (GPU) (which can be understood as a microprocessor), or a digital signal processor (DSP).
  • the processor can implement certain functions through the logical relationship of a hardware circuit, and the logical relationship of the hardware circuit is fixed or reconfigurable, such as a hardware circuit implemented by an ASIC or PLD, such as an FPGA.
  • the process of the processor loading a configuration document to implement the hardware circuit configuration can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units.
  • it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a neural network processing unit (NPU), a tensor processing unit (TPU), a deep learning processing unit (DPU), etc.
  • NPU neural network processing unit
  • TPU tensor processing unit
  • DPU deep learning processing
  • each unit in the above device can be one or more processors (or processing circuits) configured to implement the above method, such as: CPU, GPU, NPU, TPU, DPU, microprocessor, DSP, ASIC, FPGA, or a combination of at least two of these processor forms.
  • processors or processing circuits
  • FIG. 13 is a schematic diagram of a possible physical structure of the device provided herein.
  • the device 1300 shown in Figure 13 can be a vehicle, cloud device, or roadside sensing device in the methods described in the above embodiments.
  • the device 1300 includes a processor 1301 , a memory 1302 , and a communication interface 1303 .
  • the processor 1301 , the communication interface 1303 , and the memory 1302 can be interconnected or connected via a bus 1304 .
  • the memory 1302 is used to store computer programs and data of the device 1300.
  • the memory 1302 may include, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or portable read-only memory (CD-ROM).
  • RAM random access memory
  • ROM read-only memory
  • EPROM erasable programmable read-only memory
  • CD-ROM portable read-only memory
  • the software or program codes required for all or part of the functions of the device in the above method embodiment are stored in the memory 1302 .
  • the processor 1301 in addition to calling the program code in the memory 1302 to implement some functions, can also cooperate with other components (such as the communication interface 1303) to jointly complete other functions described in the method embodiment (such as the function of receiving or sending data).
  • the processor 1301 may be a CPU, GPU, NPU, TPU, DPU, microprocessor, DSP, ASIC, FPGA, or a combination of at least two of the aforementioned processor types.
  • the processor 1301 may be configured to read programs stored in the memory 1302 and execute the operations performed by the corresponding device in the method described in FIG. 9 and its possible embodiments.
  • the present application also provides a chip including a processor and a memory, wherein the memory is configured to store computer programs or computer instructions, and the processor is configured to execute the computer programs or computer instructions stored in the memory, so that the chip performs the operations performed by the vehicle in FIG. 9 and its possible embodiments.
  • the present application also provides a chip including a processor and a memory, wherein the memory is configured to store computer programs or computer instructions, and the processor is configured to execute the computer programs or computer instructions stored in the memory, so that the chip performs the operations performed by the cloud device in FIG. 9 and its possible embodiments.
  • the present application also provides a chip comprising a processor and a memory, wherein the memory is configured to store computer programs or computer instructions, and the processor is configured to execute the computer programs or computer instructions stored in the memory, so that the chip performs the operations performed by the roadside sensing device in FIG. 9 and its possible embodiments.
  • An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program or computer instructions, and the computer program or computer instructions are executed by a processor to implement the method implemented by the vehicle in Figure 9 and its possible embodiments.
  • An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program or computer instructions, and the computer program or computer instructions are executed by a processor to implement the method implemented by the cloud device in Figure 9 and its possible embodiments.
  • An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program or computer instructions, and the computer program or computer instructions are executed by a processor to implement the method implemented by the roadside perception device in Figure 9 and its possible embodiments.
  • An embodiment of the present application also provides a computer program product.
  • the computer program product is read and executed by a computer, the operations implemented by the vehicle in the method described in any one of Figure 9 and its possible embodiments will be executed.
  • An embodiment of the present application also provides a computer program product.
  • the computer program product is read and executed by a computer, the operations implemented by the cloud device in the method described in any one of Figure 9 and its possible embodiments will be executed.
  • An embodiment of the present application also provides a computer program product.
  • the computer program product is read and executed by a computer, the operations implemented by the roadside perception device in the method described in any one of Figure 9 and its possible embodiments will be executed.
  • the size of the serial number of each process does not mean the order of execution.
  • the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
  • references throughout this specification to "one embodiment,” “an embodiment,” or “one possible implementation” mean that specific features, structures, or characteristics associated with that embodiment or implementation are included in at least one embodiment of the present application. Therefore, the appearance of "in one embodiment,” “in an embodiment,” or “one possible implementation” throughout this specification does not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Atmospheric Sciences (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Traffic Control Systems (AREA)

Abstract

一种驾驶控制方法、协同驾驶方法及相关装置。通过云端设备实现车辆和路侧感知装置之间的通信，使得在车辆无法感知到第一对象的情况下，可以获取来自路侧感知装置对该第一对象的感知信息。并将获取的该感知信息与车辆自身传感器获取的感知信息融合以扩大感知范围，进而基于融合后的感知信息实现车辆的驾驶控制，有效降低车辆驾驶安全隐患。

Description

驾驶控制方法、协同驾驶方法及相关装置
本申请要求在2024年2月28日提交中国国家知识产权局、申请号为202410225645.9的中国专利申请的优先权，申请名称为“驾驶控制方法、协同驾驶方法及相关装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及智能驾驶技术领域，尤其涉及一种驾驶控制方法、协同驾驶方法及相关装置。
背景技术
目前实现智能驾驶的途径主要有两种，一种是单车智能驾驶，另一种是车路协同智能驾驶。在单车智能驾驶方面，以单车智能为核心的智能驾驶技术已经在产品中搭载了L2辅助驾驶功能。但是，单纯依靠车辆自身的传感器检测、信号反馈和执行机构完成指令的单车智能驾驶，对于传感器感知范围外存在的威胁，车辆很难及时规避，造成车辆驾驶的安全性下降。因此，单车智能驾驶在高阶智能驾驶发展的过程中有很大的局限性。而通过车路协同来实现智能驾驶，则可以在单车智能的基础上进一步降低事故风险和概率，也可以更好的演进到高阶智能驾驶。
车路协同的解决方案已经有很多年，并且在车路通信之间也确定了相应的通信标准。但是，目前车路协同的实现成本较高，在实际应用中的实现存在着困难。
发明内容
本申请实施例提供了一种驾驶控制方法、协同驾驶方法及相关装置，可以有效降低车辆驾驶安全隐患且实现成本低，易于推广使用。
第一方面，本申请提供一种驾驶控制方法，前述方法包括：获取来自云端设备的第一信息；该第一信息包括路侧感知装置对第一对象的感知信息；根据该第一信息和第一感知信息获取第一融合信息；并根据该第一融合信息执行第一驾驶控制；其中，该第一感知信息包括通过车辆的传感器获得的感知信息；在该车辆根据第二感知信息感知到该第一对象的情况下，根据该第二感知信息执行第二驾驶控制；该第二感知信息包括通过该车辆的传感器获得的对该第一对象的感知信息。
示例性地，前述路侧感知装置部署在前述车辆前进方向的驾驶盲区路段上，前述路侧感知装置的感知范围覆盖前述驾驶盲区路段；前述驾驶盲区路段包括如下的一项或多项：弯道路段，包括路口的路段，包括进口或出口的路段，或坡顶路段。
上述方案中，路侧感知装置可以感知到车辆感知范围之外的对象，并通过云端设备将该对象的感知信息发送给车辆进行感知融合。若车辆自身可以感知到该对象，则采用自身的感知实现驾驶控制，节省融合计算的资源。即将路侧感知装置作为车辆的感知补盲设备，使得车辆可以获取感知范围之外的信息，从而可以更加全面了解行车环境，降低安全隐患。此外，本方案中无需车路直接通信，节省车载单元(on board unit，OBU)和路侧单元(road side unit，RSU)的部署，从而极大节省成本。
一种可能的实现方式中，前述第一对象包括一个或多个目标车辆，前述第一信息包括前述路侧感知装置对前述一个或多个目标车辆的感知信息。
上述方案中，车辆可以通过云端获取到路侧感知装置对目标车辆的感知信息，从而扩大了车辆的感知范围，利于补盲。
一种可能的实现方式中，前述方法还包括：获取来自云端设备的第二信息；前述第二信息指示前述路侧感知装置对第二对象的感知信息；前述第二对象包括一个或多个行人；丢弃前述第二信息。
上述方案中，由于路侧感知装置感知到的行人信息的准确性不高，丢弃可以减少对后续融合和驾驶控制的干扰。
一种可能的实现方式中，前述方法还包括：获取来自前述云端设备的第三信息；前述第三信息指示在前述车辆感知到前述第一对象的情况下，前述路侧感知装置对前述第一对象的感知信息；前述根据前述车辆自身的第二感知信息执行第二驾驶控制，包括：将前述第三信息和前述第二感知信息按照预设的权重比例实现信息融合，获取第二融合信息；前述第二感知信息的权重比例大于前述第三信息的权重比例；根据前述第二融合信息执行前述第二驾驶控制。
上述方案中，通过权重比例实现路侧感知与车自身的感知融合，一方面扩大了车的感知范围，另一方面车自身的感知权重比例较高，可以提高感知融合的置信度。
一种可能的实现方式中，前述方法还包括：获取来自云端设备的第四信息；前述第四信息指示在前述车辆感知到前述第一对象的情况下，前述路侧感知装置对前述第一对象的感知信息；根据前述第二感知信息校准前述第四信息，获得校准结果；发送前述校准结果，前述校准结果用于修正前述路侧感知装置的感知置信度。
上述方案中，车辆可以根据自身的感知信息来校准路侧感知信息，校准后的路侧感知信息可以用于修正路侧感知装置的感知置信度，提高路侧感知装置的检测正确性。
一种可能的实现方式中，在前述车辆感知到前述第一对象的情况下，或者在前述第一对象离开前述路侧感知装置的感知范围的情况下，前述方法还包括：获取来自前述云端设备的第五信息；前述第五信息指示前述车辆关闭路侧感知融合功能，前述路侧感知融合功能为将前述路侧感知装置的感知信息和前述车辆的感知信息融合的功能。
上述方案中，若路侧感知装置的感知范围没有威胁对象或车辆可以感知威胁对象时，车辆可以关闭路侧融合感知功能，恢复单车感知驾驶模式，减少融合计算开销。
一种可能的实现方式中，前述获取来自云端设备的第一信息，包括：在前述车辆无法感知到前述第一对象，且前述第一对象满足第一条件的情况下，获取前述第一信息；前述第一条件包括：前述第一对象和前述车辆之间的距离小于等于第一预设距离，和/或前述第一对象和前述车辆的碰撞时间小于等于第一预设时长。
上述方案中，在第一对象威胁到车辆的行车安全时才获取到路侧感知信息，可以节省传输带宽。
第二方面，本申请提供一种协同驾驶方法，前述方法包括：获取来自车辆的车辆状态信息；前述车辆状态信息包括前述车辆的位置信息和速度信息；获取第一信息；前述第一信息指示路侧感知装置对第一对象的感知信息；根据前述车辆状态信息和前述第一信息确定前述第一对象满足第一条件；前述第一条件包括：前述第一对象和前述车辆之间的距离小于等于第一预设距离，和/或前述第一对象和前述车辆的碰撞时间小于等于第一预设时长；向前述车辆发送前述第一信息。
上述方案中，云端设备可以获取车辆的信息和路侧设备对第一对象的感知信息，然后判断是否满足将第一对象的感知信息发送给车辆的条件，满足才发送。即本方案中，通过云端设备的转发，可以实现路侧感知装置作为车辆的感知补盲设备，使得车辆可以获取感知范围之外的信息，从而可以更加全面了解行车环境，降低安全隐患。此外，本方案中无需车路直接通信，节省车载单元OBU和路侧单元RSU的部署，从而极大节省成本。进一步地，只有满足条件时云端才向车辆发送信息，可以节省传输带宽。
一种可能的实现方式中，前述方法还包括：获取来自前述路侧感知装置的第二信息；前述第二信息指示前述车辆感知到前述第一对象的情况下，前述路侧感知装置对前述第一对象的感知信息；向前述车辆发送前述第二信息；获取来自前述车辆的第三信息；前述第三信息为根据前述车辆自身的感知信息校准前述第二信息获得的校准结果；向前述路侧感知装置发送前述校准结果；前述校准结果用于修正前述路侧感知装置的感知置信度。
上述方案中，通过云端实现车辆与路侧感知装置之间的通信，使得车辆可以根据自身的感知信息来校准路侧感知信息，校准后的路侧感知信息可以用于修正路侧感知装置的感知置信度，提高路侧感知装置的检测正确性。
一种可能的实现方式中，在前述车辆感知到前述第一对象的情况下，或者在前述第一对象离开前述路侧感知装置的感知范围的情况下，前述方法还包括：向前述车辆发送第四信息；前述第四信息指示前述车辆关闭路侧感知融合功能，前述路侧感知融合功能为将前述路侧感知装置的感知信息和前述车辆的感知信息融合的功能。
示例性地，前述方法还包括：获取来自前述路侧感知装置的第五信息；前述第五信息指示前述第一对象离开前述路侧感知装置的感知范围；根据前述第五信息触发向前述车辆发送前述第四信息的操作。
上述方案中，若路侧感知装置的感知范围没有威胁对象或车辆可以感知威胁对象时，可以指示云端设备，云端设备可以通知车辆关闭路侧融合感知功能，恢复单车感知驾驶模式，减少融合计算开销。
第三方面，本申请提供一种协同驾驶方法，前述方法应用于路侧感知装置，前述方法包括：获取第一感知信息；前述第一感知信息包括对第一对象的感知信息以及包括对前述车辆的感知信息；根据前述第一感知信息识别前述第一对象威胁前述车辆的行车安全；向云端设备发送第一信息，前述第一信息指示前述路侧感知装置对前述第一对象的感知信息，前述第一信息用于发送给前述车辆。
上述方案中，路侧感知装置通过云端实现车辆与路侧感知装置之间的通信，可以实现路侧感知装置作为车辆的感知补盲设备，使得车辆可以获取感知范围之外的信息，从而可以更加全面了解行车环境，降低安全隐患。此外，本方案中无需车路直接通信，节省车载单元OBU和路侧单元RSU的部署，从而极大节省成本。进一步地，路侧感知可以先自己判断存在安全风险才发送信息，节省数据传输带宽。
一种可能的实现方式中，前述方法还包括：向前述云端设备发送第二信息；前述第二信息指示前述车辆感知到前述第一对象的情况下，前述路侧感知装置对前述第一对象的感知信息；从前述云端设备获取校准结果；前述校准结果用于修正前述路侧感知装置的感知置信度，前述校准结果为前述车辆根据自身的感知信息校准前述第二信息获得的校准结果。
上述方案中，通过云端实现车辆与路侧感知装置之间的通信，使得车辆可以根据自身的感知信息来校准路侧感知信息，校准后的路侧感知信息可以用于修正路侧感知装置的感知置信度，提高路侧感知装置的检测正确性。
一种可能的实现方式中，前述方法还包括：向前述云端设备发送第三信息；前述第三信息指示前述第一对象离开前述路侧感知装置的感知范围；前述第三信息用于触发前述云端设备向前述车辆发送前述第四信息，前述第四信息指示前述车辆关闭路侧感知融合功能，前述路侧感知融合功能为将前述路侧感知装置对前述第一对象的感知信息和前述车辆的感知信息融合的功能。
上述方案中，若路侧感知装置的感知范围没有威胁对象或车辆可以感知威胁对象时，可以指示云端，云端可以通知车辆关闭路侧融合感知功能，恢复单车感知驾驶模式，减少融合计算开销。
第四方面，本申请提供一种车辆，前述车辆包括用于实现上述第一方面任一项所述方法的单元。
第五方面，本申请提供一种云端设备，前述云端设备包括用于实现上述第二方面任一项所述方法的单元。
第六方面，本申请提供一种路侧感知装置，前述路侧感知装置包括用于实现上述第三方面任一项所述方法的单元。
第七方面，本申请提供一种车辆，该车辆包括处理器和存储器。该存储器与处理器耦合，处理器执行存储器中存储的计算机程序或计算机指令时，可以实现上述第一方面任一项描述的方法。该车辆还可以包括通信接口，通信接口用于该车辆与其它车辆进行通信，示例性的，通信接口可以是收发器、电路、总线、模块或其它类型的通信接口。
在一种可能的实现中，该车辆可以包括：
存储器，用于存储计算机程序或计算机指令；
处理器，用于：获取来自云端设备的第一信息；该第一信息包括路侧感知装置对第一对象的感知信息；根据该第一信息和第一感知信息获取第一融合信息；并根据该第一融合信息执行第一驾驶控制；其中，该第一感知信息包括通过车辆的传感器获得的感知信息；在该车辆根据第二感知信息感知到该第一对象的情况下，根据该第二感知信息执行第二驾驶控制；该第二感知信息包括通过该车辆的传感器获得的对该第一对象的感知信息。
需要说明的是，本申请中存储器中的计算机程序或计算机指令可以预先存储也可以使用该车辆时从互联网下载后存储，本申请对于存储器中计算机程序或计算机指令的来源不进行具体限定。本申请实施例中的耦合是装置、单元或模块之间的间接耦合或连接，其可以是电性，机械或其它的形式，用于装置、单元或模块之间的信息交互。
第八方面，本申请提供一种云端设备，该云端设备包括处理器和存储器。该存储器与处理器耦合，处理器执行存储器中存储的计算机程序或计算机指令时，可以实现上述第二方面任一项描述的方法。该云端设备还可以包括通信接口，通信接口用于该云端设备与其它云端设备进行通信，示例性的，通信接口可以是收发器、电路、总线、模块或其它类型的通信接口。
在一种可能的实现中，该云端设备可以包括：
存储器，用于存储计算机程序或计算机指令；
处理器，用于：获取来自车辆的车辆状态信息；前述车辆状态信息包括前述车辆的位置信息和速度信息；获取第一信息；前述第一信息指示路侧感知装置对第一对象的感知信息；根据前述车辆状态信息和前述第一信息确定前述第一对象满足第一条件；前述第一条件包括：前述第一对象和前述车辆之间的距离小于等于第一预设距离，和/或前述第一对象和前述车辆的碰撞时间小于等于第一预设时长；通过通信接口向前述车辆发送前述第一信息。
需要说明的是，本申请中存储器中的计算机程序或计算机指令可以预先存储也可以使用该云端设备时从互联网下载后存储，本申请对于存储器中计算机程序或计算机指令的来源不进行具体限定。本申请实施例中的耦合是装置、单元或模块之间的间接耦合或连接，其可以是电性，机械或其它的形式，用于装置、单元或模块之间的信息交互。
第九方面，本申请提供一种路侧感知装置，该路侧感知装置包括处理器和存储器。该存储器与处理器耦合，处理器执行存储器中存储的计算机程序或计算机指令时，可以实现上述第三方面任一项描述的方法。该路侧感知装置还可以包括通信接口，通信接口用于该路侧感知装置与其它路侧感知装置进行通信，示例性的，通信接口可以是收发器、电路、总线、模块或其它类型的通信接口。
在一种可能的实现中，该路侧感知装置可以包括：
存储器，用于存储计算机程序或计算机指令；
处理器，用于：获取第一感知信息；前述第一感知信息包括对第一对象的感知信息以及包括对前述车辆的感知信息；根据前述第一感知信息识别前述第一对象威胁前述车辆的行车安全；通过通信接口向云端设备发送第一信息，前述第一信息指示前述路侧感知装置对前述第一对象的感知信息，前述第一信息用于发送给前述车辆。
需要说明的是，本申请中存储器中的计算机程序或计算机指令可以预先存储也可以使用该路侧感知装置时从互联网下载后存储，本申请对于存储器中计算机程序或计算机指令的来源不进行具体限定。本申请实施例中的耦合是装置、单元或模块之间的间接耦合或连接，其可以是电性，机械或其它的形式，用于装置、单元或模块之间的信息交互。
第十方面，本申请提供一种协同驾驶系统，该系统包括车辆、云端设备和路侧感知装置；其中，前述车辆为上述第四方面任一项所述的车辆，前述云端设备为上述第五方面任一项所述的云端设备，前述路侧感知装置为上述第六方面任一项所述的路侧感知装置；
或者，前述车辆为上述第七方面任一项所述的车辆，前述云端设备为上述第八方面任一项所述的云端设备，前述路侧感知装置为上述第九方面任一项所述的路侧感知装置。
第十一方面，本申请提供一种计算机可读存储介质，前述计算机可读存储介质存储有计算机程序或计算机指令，前述计算机程序或计算机指令被处理器执行以实现上述第一方面任一项所述的方法。
第十二方面，本申请提供一种计算机可读存储介质，前述计算机可读存储介质存储有计算机程序或计算机指令，前述计算机程序或计算机指令被处理器执行以实现上述第二方面任一项所述的方法。
第十三方面，本申请提供一种计算机可读存储介质，前述计算机可读存储介质存储有计算机程序或计算机指令，前述计算机程序或计算机指令被处理器执行以实现上述第三方面任一项所述的方法。
第十四方面，本申请一种计算机程序产品，前述计算机程序产品被处理器执行时，上述第一方面任一项所述的方法将被实现。
第十五方面，本申请一种计算机程序产品，前述计算机程序产品被处理器执行时，上述第二方面任一项所述的方法将被实现。
第十六方面，本申请一种计算机程序产品，前述计算机程序产品被处理器执行时，上述第三方面任一项所述的方法将被实现。
上述第四方面至第十六方面提供的方案，用于实现或配合实现上述第一方面或第二方面或第三方面中对应提供的方法，因此可以与第一方面或第二方面或第三方面中对应的方法达到相同或相应的有益效果，此处不再进行赘述。
附图说明
图1和图2所示为本申请实施例提供的协同驾驶系统示意图；
图3和图3A所示为本申请实施例提供的应用场景架构示意图；
图4至图8所示为本申请实施例提供的应用场景示意图；
图9所示为本申请实施例提供的方法流程示意图；
图10至图13所示为本申请实施例提供的装置结构示意图。
具体实施方式
下面结合本申请实施例中的附图示例性对本申请实施例进行描述。本申请的说明书和权利要求书及所述附图中的术语“第一”、“第二”、“第三”和“第四”等是用于区别不同对象，而不是用于描述特定顺序。此外，术语“包括”和“具有”以及它们任何变形，意图在于覆盖不排他的包含。例如包含了一系列步骤或单元的过程、方法、系统、产品或设备没有限定于已列出的步骤或单元，而是可选地还包括没有列出的步骤或单元，或可选地还包括对于这些过程、方法、产品或设备固有的其它步骤或单元。在本文中提及“实施例”意味着，结合实施例描述的特定特征、结构或特性可以包含在本申请的至少一个实施例中。在说明书中的各个位置出现该短语并不一定均是指相同的实施例，也不是与其它实施例互斥的独立的或备选的实施例。本领域技术人员显式地和隐式地理解的是，本文所描述的实施例可以与其它实施例相结合。
在本申请的各个实施例中，一方面具有相互独立性，即实施例之间不会互相限制和约束。另一方面如果没有特殊说明以及逻辑冲突，各个实施例之间的术语和/或描述具有一致性，且可以相互引用。不同的实施例中的技术特征根据其内在的逻辑关系可以组合形成新的实施例。
下面结合附图对本申请实施例进行示例性介绍。
首先介绍本申请实施例所要解决的技术问题。现有的实现方案中，为了在单车智能的基础上进一步降低驾驶事故风险和概率，通过车路协同的方式来获取更多道路环境中的信息，以协助车辆更安全地驾驶。但是，该现有的方案中，一种实现方式是V2X车路协同的方案。该方案中，可以通过在车辆上部署V2X设备(即车载单元(on board unit，OBU))采集自身的车辆信息并通过基本安全消息(basic safety message，BSM)进行广播。路侧设备(即路侧单元(road side unit，RSU))接收到周边车辆的BSM消息后，对周边车辆的运动状态进行相关的交通分析。同时，其他车辆可以对相关的路侧数据进行订阅，选择合适的道路环境，可以缓解交通堵塞，降低事故发生率。但是，这种方案中，为了达到更好的交通信息发布，需要在道路沿线进行大量的RSU设备部署。导致车路协同方案中部署困难，且有着很高的部署成本，难以大规模推广。
现有方案的另一种实现中，会结合车辆的轨迹信息来对车辆进行判断，通过多个路侧RSU设备上的车辆信息形成轨迹信息。并通过路侧RSU设备将这些车辆的轨迹信息发送给其他车辆，为车辆做出更准确的驾驶决策提供依据。但是，该方案主要考虑的是通过多个路侧RSU设备获取到的车辆信息来形成车辆轨迹，从而发送给其他车辆来实现安全驾驶，避免碰撞。这种实现也需要在道路沿线进行大量的RSU设备部署。
根据上述的描述可知，现有的实现方案在实际应用中实现难度大。具体的，从路侧的角度来看，需要在道路中实现连续部署RSU，这造成了非常高的部署成本。从车的角度来看，需要在车端部署OBU相关设备来实现路侧通信，这也加大了购车成本，同时增加了车辆故障点。另外一方面，由于通过RSU和OBU来实现车路通信需要特殊的频谱。通信频谱在不同的国家要求不一样，这也导致车路协同方案在不同的国家实现不一样。并增加了RSU和车辆在不同国家的部署认证要求，从而增加因认证带来的成本开销。
因此，为了解决上述因现有的方案实现成本高，在实际应用中的实现存在着困难的问题，本申请实施例提供了相应的方法及相关装置。
下面首先示例性介绍本申请实施例提供的协同驾驶系统。
请参见图1，图1是本申请实施例提供的一种协同驾驶系统100的结构示意图。该协同驾驶系统100包括云端设备101、车辆102和路侧感知装置103。该车辆102和路侧感知装置103均可以是一个或多个，本申请实施例对此不做限制。
示例性地，该云端设备101例如可以包括云端服务器和/或云端虚拟机等能够实现计算和/或数据处理的设备。或者，该云端设备101例如可以包括服务器集群。该云端设备101可以与该车辆102进行通信，为车辆102提供多种服务。例如，为车辆102提供空中升级(over the air，OTA)服务、高精地图服务、自动驾驶或辅助驾驶服务，以及信息转发服务等。此外，该云端设备101还可以与路侧感知装置103进行通信，为路侧感知装置103提供多种服务。例如，为路侧感知装置103提供信息分析处理服务，或者提供信息转发服务等。
示例性地，车辆102例如可以是道路上行驶的任意类型的车辆。例如小轿车、公交车、货车、消防车、警车、环卫车、混凝土车、半挂车、垃圾车或者叉车等等。该车辆102可以通过辅助驾驶或自动驾驶等智能驾驶技术行驶。车辆102中安装有探测装置，以用于探测感知车辆102周围的环境。示例性地，该探测装置例如可以包括摄像头或雷达等传感器。该雷达例如可以包括超声波雷达、激光雷达、毫米波雷达或微波雷达等各种类型的雷达，本申请实施例对此不做限制。每个探测装置都有自己的探测范围。探测装置可以感知到在该探测范围内的对象。在本申请实施例中，若探测装置无法感知到的某个对象，则认为该对象不在该探测装置的探测范围内。该探测范围也可以称为感知范围。车辆102中安装的一个或多个探测装置的探测范围的叠加即为该车辆102的感知范围。
示例性地，车辆102可以与云端设备101进行交互，以提升智能驾驶功能，从而提升车辆的安全性和出行效率。例如，车辆102可以通过车身上安装的传感装置收集路面信息和周围车辆信息，并将收集到的信息以及自身的驾驶状态信息等上传到云端设备101。车辆102也可以接收来自云端设备101的信息以辅助自身的驾驶。
示例性地，上述路侧感知装置103可以是部署在道路两侧的感知装置。该路侧感知装置103例如可以包括摄像头或雷达等探测装置。该雷达例如可以包括超声波雷达、激光雷达、毫米波雷达或微波雷达等各种类型的雷达，本申请实施例对此不做限制。示例性地，一种可能的实现中，路侧感知装置103还可以包括感知计算单元。该感知计算单元对传感器感知到的数据进行计算处理和分析，获得分析后的信息。路侧感知装置103可以与云端设备101进行交互，以将该得到的信息发送给云端设备101。路侧感知装置103也有自己的探测范围(实际上是摄像头或雷达等探测装置的探测范围)。探测装置可以感知到在该探测范围内的对象。在本申请实施例中，若探测装置无法感知到的某个对象，则认为该对象不在该探测装置的探测范围内。该探测范围也可以称为路侧感知装置103的感知范围。示例性地，路侧感知装置103的感知计算单元可以是与传感器集成在一起。或者，该感知计算单元可以是能够与该传感器通信的独立的装置或模块。
示例性地，上述车辆102和路侧感知装置103可以通过有线或无线的方式与上述云端设备101通信。本申请实施例以无线通信方式为例介绍。可以示例性地参见图2。如图2所示，车辆102和路侧感知装置103以无线通信的方式接入通信网络104。通信网络104将来自车辆102和/或路侧感知装置103的信息传输到云端设备101。
示例性地，上述通信网络104中包括无线接入设备。车辆102和路侧感知装置103可以通过无线接入设备接入该通信网络104。该无线接入设备例如可以包括宏基站，微基站(也称为小站)，中继站，接入点(例如WiFi系统中的接入节点等)，小区(Cell)等。示例性的基站可以是演进型基站(evolutional node B，eNB)，以及5G系统、新空口(new radio，NR)系统中的下一代节点(next-generation Node B，gNB)。另外，基站也可以为收发点(transmission receive point，TRP)、中心单元(central unit，CU)或其他网络实体。另外，在分布式基站场景中，无线接入设备可以是基带处理单元(baseband unit，BBU)和射频单元(remote radio unit，RRU)，在云无线接入网(cloud radio access network，CRAN)场景下可以是基带池BBU pool和射频单元RRU。或者，无线接入设备还可以是开放接入网(open RAN，ORAN)系统中的接入网设备或者接入网设备的模块。示例性地，该无线接入设备可以是能够实现基站部分功能的模块或单元。例如，无线接入设备可以是集中式单元(central unit，CU)，分布式单元(distributed unit，DU)，CU-控制面(control plane，CP)，CU-用户面(user plane，UP)，或者无线单元(radio unit，RU)等。其中，在ORAN系统中，CU还可以称为O-CU，DU还可以称为开放(open，O)-DU，CU-CP还可以称为O-CU-CP，CU-UP还可以称为O-CUP-UP，RU还可以称为O-RU。可以理解的是，此处仅为示例，本申请的实施例对无线接入设备所采用的具体技术和具体设备形态不做限定。
示例性地，上述通信网络104中还包括网络设备。该网络设备与上述无线接入设备连接，用于将无线接入设备接收到的来自上述车辆102和/或上述路侧感知装置103的信息转发给上述云端设备101。此外，可以理解的是，上述云端设备101可以通过上述通信网络104向车辆102和/或路侧感知装置103发送信息。该网络设备例如可以包括路由器、交换机、无线中继设备或无线回传设备等等。可以理解的是，此处仅为示例，本申请的实施例对网络设备所采用的具体技术和具体设备形态不做限定。
为了进一步理解本申请实施例可能的应用场景架构，可以示例性参见图3。在图3中，云端设备101中部署有运输作业管理系统(fleet management system,FMS)、高精地图服务系统、车辆调度服务系统、车辆运营监管服务系统、应急接管服务系统和智能驾驶系统等等软件系统。示例性地，该运输作业管理系统可以综合高精地图服务系统、车辆调度服务系统、车辆运营监管服务系统、应急接管服务系统和智能驾驶系统中的一项或多项提供的信息实现车辆的作业管理和/或控制。例如，云端设备101的各个服务系统可以通过通信网络104接收来自车辆102和/或路侧感知装置103的信息，并将接收的信息来综合到运输作业管理系统实现车辆的作业管理和/或控制。相关的管理和/或控制的信息也通过通信网络104发送给车辆，以实现车路云智能驾驶。
上述智能驾驶系统该智能驾驶系统可以用于配合实现车辆102的智能驾驶。在本申请实施例中，可以用于配合实现本申请实施例提供的智能驾驶方法中云端设备实现的操作。具体参见后续的介绍，此处暂不详述。
在上述图3中，车辆102中部署有车载智能驾驶系统。例如部署有辅助驾驶系统或自动驾驶系统等。该车载智能驾驶系统可以实现感知、定位、决策、规划(例如路径规划)或控制等功能。这些功能可以由雷达或摄像头等传感器、远程信息处理器(Telematics BOX，T-BOX)或线控底盘等硬件，以及车载计算单元的配合实现。示例性地，该车载智能驾驶系统的软件可以部署在整车控制器(vehicle domain controller，VDC)、座舱域控制器(cockpit domain controller，CDC)、移动数据中心(mobile data center，MDC)或者其它处理控制模块中，本申请实施例对此不做限制。
在上述图3中，路侧感知装置103包括传感器和感知计算单元，具体参考前述图1中的对应介绍，此处不赘述。
一种可能的实现中，上述图3中，车辆102和路侧感知装置103还可以包括用于实现与云端设备101通信的装置。例如，可以包括客户终端设备(Customer Premise Equipment，CPE)等通信装置或模块。该通信装置或模块可以接入通信网络104以实现与云端设备101的通信。本申请实施例对该通信装置或模块不做限制。示例性地，以CPE为例。CPE设备主要分为两种类型：有线CPE和无线CPE。有线CPE一般使用以太网作为数据传输介质，支持无源光纤网络(passive optical network，PON)、甚/超高速数字用户线路(very-high-bit-rate digital subscriber loop，VDSL)、非对称数字用户线路(asymmetric digital subscriber line，ADSL)等接入方式。无线CPE可以直接接入4G或5G网络，也可以通过外接天线、无线AP，无线基站或路由器等方式接入有线网络。
一种可能的实现中，可以示例性参见图3A所示。在图3A中可以看到，路侧感知装置103中的CPE可以通过有线通信方式实现与云端设备101之间的通信。例如，可以通过光纤连接路侧感知装置103中的CPE和云端设备101以实现数据传输。另外，车辆102中的CPE可以通过无线的方式接入基站，然后经核心网实现与云端设备101之间的通信。可以理解的是，图3A所示仅为示例，不构成对本申请实施例的限制。
可以理解的是，上述图3所示仅为示例，不构成对本申请实施例的限制。在具体实现中，云端设备101、车辆102或路侧感知装置103可以包括更多或更少的硬件组成或软件单元，或者可以用可以实现同样功能的模块替代等等，具体可以根据实际应用需求配置，本申请实施例对此不做限制。
一种可能的实施方式中，为了减少部署成本，上述路侧感知装置103可以部署在道路中的驾驶盲区路段。该驾驶盲区路段包括超出车辆感知范围且容易出现威胁车辆驾驶安全事故的路段。例如，该驾驶盲区路段可以包括弯道路段，包括路口的路段，包括进口或出口的路段，或坡顶路段等等。可以理解的是，该驾驶盲区路段的区域范围大小可以根据实际应用场景的具体情况划分，本申请实施例对此不做限制。
示例性地，该弯道路段可以是任意的弯道路段，本申请实施例对此不作限制。
示例性地，上述包括路口的路段例如可以包括十字形平面交叉路口，环形平面交叉路口，X形平面交叉路口，T形平面交叉路口，Y形平面交叉路口，错位平面交叉路口，多路平面交叉路口等等。
示例性地，上述包括进口或出口的路段例如可以包括隧道进口或出口、住宅区进口或出口、车库或停车场进口或出口等等。
示例性地，上述坡顶路段可以包括上坡坡顶路段或下坡坡顶路段等。
为了便于理解上述路侧感知装置103部署在道路中的驾驶盲区路段的应用场景，可以示例性参见图4至图8。
图4示例性示出了一种驾驶盲区路段为弯道路段的应用场景示意图。可以看到，车辆102的感知范围有限，无法感知到弯道路段中的对象(例如车辆A)。因此，在该弯道路段部署了路侧感知装置103。该路侧感知装置103的感知范围可以覆盖该弯道路段，因此可以感知到弯道路段中的对象(例如车辆A)。可以理解的是，该弯道路段中可以部署有一个或多个路侧感知装置103(图4中所示仅为示例)，具体部署的数量本申请实施例不做限制。此外，路侧感知装置103可以部署在该弯道路段的任意一侧，或者可以部署在该弯道路段的两侧，具体根据实际应用部署，本申请实施例对此不做限制。
图5示例性示出了一种驾驶盲区路段为包括路口的路段(简称路口路段)的应用场景示意图。可以看到，车辆102的感知范围有限，无法感知到路口路段中的对象(例如车辆A)。因此，在该路口路段部署了路侧感知装置103。该路侧感知装置103的感知范围可以覆盖该路口路段，因此可以感知到路口路段中的对象(例如车辆A)。可以理解的是，该路口路段中可以部署有一个或多个路侧感知装置103(图5中所示仅为示例)，具体部署的数量本申请实施例不做限制。此外，路侧感知装置103可以部署在该路口路段中道路两侧的任意一个位置，具体根据实际应用部署，本申请实施例对此不做限制。
图6示例性示出了一种驾驶盲区路段为包括隧道入口路段的应用场景示意图。可以看到，车辆102的感知范围有限，无法感知到隧道入口路段中的对象(例如静态障碍物A)。因此，在该隧道入口路段部署了路侧感知装置103。该路侧感知装置103的感知范围可以覆盖该隧道入口路段，因此可以感知到隧道入口路段中的对象(例如静态障碍物A)。可以理解的是，该隧道入口路段中可以部署有一个或多个路侧感知装置103(图6中所示仅为示例)，具体部署的数量本申请实施例不做限制。此外，路侧感知装置103可以部署在该隧道入口路段中道路两侧的任意一个位置，具体根据实际应用部署，本申请实施例对此不做限制。
图7和图8示例性示出了一种驾驶盲区路段为包括坡顶路段的应用场景示意图。其中，图7所示为车辆102上坡场景下的示意图，图8所示为车辆102下坡场景下的示意图。可以看到，车辆102的感知范围有限，无法感知到坡顶路段中的对象(例如车辆A)。因此，在该坡顶路段部署了路侧感知装置103。该路侧感知装置103的感知范围可以覆盖该坡顶路段，因此可以感知到坡顶路段中的对象(例如车辆A)。可以理解的是，该坡顶路段中可以部署有一个或多个路侧感知装置103(图6中所示仅为示例)，具体部署的数量本申请实施例不做限制。此外，路侧感知装置103可以部署在该坡顶路段中道路两侧的任意一个位置，具体根据实际应用部署，本申请实施例对此不做限制。
上述图4至图8所示主要以车辆102在上述驾驶盲区路段上，在另一种实现中，车辆102可以在驾驶盲区路段之外的道路区域行驶。例如车辆102朝着驾驶盲区路段行驶，但还未进入驾驶盲区路段的情况等。
可以理解的是，上述图4至图8所示应用场景仅为示例，不构成对本申请实施例的限制。在具体实现中还可以包括其它的驾驶盲区路段的应用场景，本申请实施例不一一列出。
示例性地，结合上述介绍的协同驾驶系统，下面介绍本申请实施例提供的方法。可以示例性参见图9，该方法可以包括但不限于如下步骤。
S901、路侧感知装置获取第一信息。
示例性地，该路侧感知装置例如可以是上述协同驾驶系统100中的路侧感知装置103。该车辆例如可以是该协同驾驶系统100中的车辆102。该车辆可以是朝着驾驶盲区路段行驶的车辆。该驾驶盲区路段例如可以是上述介绍的驾驶盲区路段中的任意一种，此处不再赘述。该路侧感知装置部署在该驾驶盲区路段上，具体的部署应用场景可以示例性参见上述图4或图8，此处不赘述。示例地，该路侧感知装置可以包括部署在该驾驶盲区路段上的一个或多个感知装置。
在具体实现中，上述路侧感知装置的感知范围可以覆盖上述驾驶盲区路段，从而可以感知到该驾驶盲区路段中的对象(包括上述第一对象，该第一对象例如可以是该驾驶盲区路段中的一个或多个对象)。示例性地，该驾驶盲区路段中的对象可以包括移动的对象和静止的对象。该移动的对象例如包括车辆、行人、动物或任意在该驾驶盲区路段中移动的对象。该静止的对象例如包括该驾驶盲区路段中的土堆、因施工等原因临时拦截的标识牌、因事故导致停止行驶的车辆或其它被放置在道路上的物体等静态障碍物。可以理解的是，此处介绍的对象仅为示例，不构成对本申请实施例的限制。具体实现中还可以包括其它的对象，本申请实施例对此不做限制。
示例性地，一种可能的实施方式中，上述路侧感知装置中的传感器可以对驾驶盲区路段中的对象进行检测获得检测数据。示例性地，若该传感器为摄像头，该检测数据可以是该摄像头拍摄得到的图像数据。或者，示例性地，若该传感器为雷达，该检测数据可以是该雷达探测到的点云数据。即该检测数据为路侧感知装置的原始感知数据。可以理解的是，此处关于检测数据的描述仅为示例，不构成对本申请实施例的限制。
一种可能的实现方式中，上述传感器获得检测数据后，将该检测数据发送给该路侧感知装置中的感知计算单元。由该感知计算单元对该检测数据进行处理和分析。该检测数据包括对该驾驶盲区路段中的上述第一对象检测获得的数据，下面以该第一对象为例介绍。
上述感知计算单元通过对上述检测数据进行分析处理后，可以提取出对该第一对象的位置、移动速度、移动方向、类型(例如是车辆还是行人等)和标识中的一项或多项感知信息。该具体的分析处理方法例如可以是从图像数据或点云数据中提取出对象的感知信息的任意一种或多种方法，本申请实施例对此不做限制。
示例性地，一种可能的实现方式中，上述第一信息可以包括上述提取出来的一项或多项感知信息。可选的，该第一信息还可以包括上述传感器的感知置信度信息。可选的，若该第一对象为车辆，该第一信息还可以包括该第一对象相应的事件信息。该事件信息例如可以是车联万物(vehicle to everything，V2X)技术中确定的事件信息等。为了便于后续的介绍，可以将该第一信息称为分析处理后的感知信息。
另一种可能的实现方式中，上述第一信息包括的是上述路侧感知装置对上述第一对象的检测数据，即包括的是对该第一对象的原始感知数据。同理，可选的，该第一信息还可以包括上述传感器的感知置信度信息和/或该第一对象相应的事件信息等。为了便于后续的介绍，可以将该第一信息称为未分析处理的感知信息。这种实现方式的好处是路侧感知装置无需进行信息提取处理，降低路侧感知装置的处理复杂度。
可以理解的是，上述列出的第一信息包括的内容仅为示例，不构成对本申请实施例的限制。
S902、路侧感知装置向云端设备发送该第一信息，第一信息指示在所述车辆无法感知到第一对象的情况下，路侧感知装置对所述第一对象的感知信息。
示例性地，上述路侧感知装置获得上述第一信息后，上述路侧感知装置可以通过通信模块或装置(例如上述CPE等)将该第一信息发送给云端设备。
一种可能的实施方式中，在上述第一对象位于上述车辆的感知范围之外(即车辆无法感知到第一对象)的情况下，上述路侧感知装置向上述云端设备发送上述第一信息。示例性地，这种情况下，车辆和上述第一对象均位于驾驶盲区路段上，因此路侧感知装置可以感知到该车辆。为了便于理解，例如可以示例性地参考前述图4至图8中的任意一个应用场景示意图，该第一对象例如可以是图中的对象A(例如图中的车辆A或静态障碍物A)，该车辆可以是图中的车辆102。由于上述车辆位于驾驶盲区路段上，路侧感知装置可以感知到该车辆，并获得对该车辆的感知信息。然后，根据对该车辆的感知信息和上述第一信息可以计算出车辆和第一对象的距离。具体的距离计算方式本申请实施例不做限制。然后，判断该距离的大小。若该距离大于预设的距离的情况下，那么可以确定该第一对象在该车辆的感知范围之外。示例性地，该预设的距离例如可以是该车辆的感知距离或者可以是自定义距离等等。确定该第一对象在该车辆的感知范围之外后，路侧感知装置向上述云端设备发送上述第一信息。从而节省不必要的冗余数据的发送，节省传输带宽。
一种可能的实施方式中，在上述第一对象满足第一条件的情况下，路侧感知装置向上述云端设备发送上述第一信息。示例性地，该第一条件可以包括第一对象和上述车辆的距离小于等于第一预设距离，和/或包括第一对象和上述车辆的碰撞时间((time-to-collision，TTC))小于等于第一预设时长。示例性地，在具体实现中，上述第一对象位于上述车辆的感知范围之外，路侧感知装置也不一定向云端设备发送上述第一信息。而是，第一对象位于上述车辆的感知范围之外，且可能威胁到该车辆的行车安全时(例如第一对象满足上述第一条件时)，向上述云端设备发送上述第一信息。
示例性地，上述第一预设距离和/或上述第一预设时长可以是根据实际应用需求设定，本申请实施例对此不做限制。通过这种实现方式，可以进一步节省不必要的冗余数据的发送，节省传输带宽。
一种可能的实现中，上述路侧感知装置可以是按照预设的格式结构将上述第一信息发送给上述云端设备的。例如，路侧感知装置可以是将该第一信息封装成报文或消息的形式发送给云端设备。例如，可以将该第一信息封装成路侧安全消息(roadside safety message，RSM)的形式发送给云端设备。
S903、云端设备获取该第一信息。
上述路侧感知装置向云端设备发送上述第一信息后，云端设备可以接收到该第一信息。
S904、云端设备向车辆发送第二信息，第二信息基于第一信息获得。
云端设备接收到该第一信息，可以根据该第一信息获得第二信息，然后可以向车辆发送该第二信息。
示例性地，一种可能的实现方式中，若该第一信息为上述未分析处理的感知信息，那么云端设备可以对该第一信息中的原始感知数据进行分析处理，提取出上述第一对象的位置、移动速度、移动方向、类型和标识中的一项或多项感知信息。则上述第二信息包括该一项或多项感知信息。或者，也可以直接将该第一信息作为上述第二信息发送给车辆。本申请实施例对此不作限制。
另一种可能的实现方式中，若该第一信息为上述分析处理后的感知信息，那么，云端设备可以将该第一信息作为上述第二信息发送给车辆。或者，可以从该第一信息中选择部分数据发送给车辆。本申请实施例对此不作限制。
一种可能的实施方式中，在上述第一对象满足第二条件的情况下，上述云端设备向上述车辆发送上述第二信息。该第二条件包括上述第一对象和上述车辆的距离小于等于第二预设距离，和/或包括上述第一对象和上述车辆的碰撞时间小于等于第二预设时长。
示例性地，在具体实现中，上述车辆可以将自身的驾驶状态信息发送给云端设备。该驾驶状态信息可以包括该车辆的位置、行驶速度、移动方向(或者说行驶方向)、类型和标识等信息中的一项或多项。可以理解，此处描述的驾驶状态信息仅为示例，不构成对本申请实施例的限制。云端设备接收到该车辆的驾驶状态信息后，可以根据该驾驶状态信息和上述接收到的第一信息计算出该车辆和第一对象的距离，和/或计算出该车辆和第一对象的碰撞时间。示例性地，云端设备可以结合高精地图来计算该距离和/或碰撞时间，本申请实施例对该具体计算的实现过程不做限制。在该距离小于等于上述第二预设距离，和/或在该碰撞时间小于等于上述第二预设时长的情况下，云端设备向上述车辆发送上述第二信息。示例性地，该第二预设距离和/或该第二预设时长可以是根据实际应用需求设定，本申请实施例对此不做限制。通过这种实现方式，可以节省不必要的冗余数据的发送，节省传输带宽。
S905、车辆获取该第二信息，并根据该第二信息和第一感知信息获取第一融合信息；并根据该第一融合信息执行第一驾驶控制；第一感知信息包括通过车辆的传感器获得的感知信息；在该车辆根据第二感知信息感知到该第一对象的情况下，根据该第二感知信息执行第二驾驶控制；该第二感知信息包括通过该车辆的传感器获得的对该第一对象的感知信息。
一种可能的实现方式中，本申请实施例所描述的车辆所执行的操作可以是有车辆的控制器来执行的。例如，可以是由部署了上述图3中所示的车载智能驾驶系统的软件的VDC、CDC、MDC或者其它控制器来执行的。
示例性地，该车辆自身的传感器也在不断地探测周围的路面情况获得自身的感知信息。在车辆接收到来自上述云端设备的第二信息之后，可以根据该第二信息和该车辆自身的感知信息实现信息融合。
一种可能的实现中，上述车辆可以将上述第二信息和自身的感知信息融合到高精地图中。示例性地，可以采用任意的感知信息融合方法来实现该第二信息和车辆自身的感知信息的融合，本申请实施例对该感知信息融合的方法不做限制。获得融合后的高精地图后，根据该融合后的高精地图来实现车辆的智能驾驶控制。示例性地，车辆可以根据该融合后的高精地图感知到第一对象的存在，因此可以计算自身与该第一对象的距离和/或碰撞时间。进而根据该距离和/或碰撞时间来做出减速或者换道等操作控制，实现安全驾驶。
在另一种具体实现中，上述车辆可以将上述第二信息和自身的感知信息融合到自定义的地图中。同样可以根据融合后的地图感知到上述第一对象的存在，进而根据与该第一对象的距离和/或碰撞时间来做出减速或者换道等操作控制，实现安全驾驶。
一种可能的实现方式中，若上述第一对象进入上述车辆的感知范围，即该车辆可以感知到该第一对象后，可以根据该车辆自身的感知信息来执行驾驶控制。这种情况下，该车辆自身的感知信息即包括对上述第一对象的感知信息。无需再进行路侧感知数据和车辆自身感知数据的融合操作。节省计算资源的同时，采用车辆自身的感知数据置信度更高，以便于做出更合理准确的驾驶控制，降低出现安全事故的风险。
另一种可能的实现方式中，在上述车辆可以感知到上述第一对象后，车辆依然可以从云端设备接收到路侧感知装置对该第一对象的感知信息(简称为第三信息)。然后，可以按照权重比例来实现该第三信息和车辆自身的感知信息的融合，并根据融合后的感知信息来执行对应的驾驶控制。示例性地，车辆自身的感知信息的权重大于该第三信息的权重。示例性地，权重可以通过百分占比或者打分等方式来表示，本申请实施例对此不作限制。示例性地，在具体实现中，可以通过机器学习模型或者深度学习模型等感知融合模型来实现车辆自身的感知信息和该第三信息的融合。例如，该感知融合模型的输入可以包括车辆自身的感知信息(包括对该第一对象的感知信息)、第三信息以及该两个信息的权重(或者权重比例)，输出即为融合后的感知信息。从而可以根据融合后的感知信息来执行驾驶控制。这种实现方式下，一方面利用路侧感知信息扩大了车辆的感知范围，另一方面车辆自身的感知权重比例较高，可以提高感知融合的置信度。
一种可能的实现方式中，上述路侧感知装置对车辆的感知置信度较高，而对行人的感知置信度较低。因此，若车辆接收到上述云端设备转发过来的路侧感知信息中包括对车辆的感知信息，则车辆可以将该车辆的感知信息与自身的感知信息进行融合。例如，上述第一对象包括一个或多个目标车辆，上述第二信息包括路侧感知装置对该一个或多个目标车辆的感知信息。若车辆接收到上述云端设备转发过来的路侧感知信息中包括对行人的感知信息，那么可以将该对行人的感知信息丢弃，不予使用。以减少对后续融合和驾驶控制的干扰。示例性地，例如可以通过上述第二信息中的类型来判断出是行人的感知信息还是车辆的感知信息。
一种可能的实现方式中，在上述第一对象进入上述车辆的感知范围之后，该车辆可以探测到该第一对象，并获取到该第一对象的感知信息(简称为第二感知信息)。示例性地，该第二感知信息也可以包括该第一对象的位置、移动速度、移动方向、类型和标识中的一项或多项信息。
此外，在上述第一对象进入上述车辆的感知范围之后，车辆仍然可以从云端设备接收到上述路侧感知装置探测到的该第一对象的感知信息(简称为第四信息)。然后，车辆可以根据自身对第一对象的感知信息校准该第四信息，以获得校准结果。示例性地，该第四信息同样指示了第一对象的位置、移动速度、移动方向、类型和标识中的一项或多项信息。车辆也可以通过分析处理对第一对象的感知信息获得该第一对象的位置、移动速度、移动方向、类型和标识中的一项或多项信息。
示例性地，一种可能的实现中，可以通过欧氏距离算法或马氏距离算法进行数据关联，以实现路侧装置感知的第一对象和车辆感知的第一对象之间的匹配。然后，车辆可以将上述第四信息与该车辆对第一对象的感知信息进行对比，获得感知信息的偏差信息。例如，可以将该第四信息与该车辆对第一对象的感知信息中的位置信息进行比较，获得位置偏差。可选的，还可以将该第四信息与该车辆对第一对象的感知信息中的移动速度进行比较，获得速度偏差等等。该一个或多个偏差组成了感知信息的偏差信息，该偏差信息即为上述校准结果。
或者，示例性地，另一种可能的实现中，车辆可以先将上述车辆对第一对象的感知信息和第四信息融合到车辆的地图(例如高精地图或自定义地图)中。然后，车辆根据融合后的地图可以获得第一对象的位置、移动速度、移动方向、类型和标识中的一项或多项信息，这些信息简称为融合感知信息。然后，车辆可以将该第四信息与该融合感知信息进行对比，获得感知信息的偏差信息。例如，可以将该第四信息与该融合感知信息中的位置信息进行比较，获得位置偏差。可选的，还可以将该第四信息与该融合感知信息中的移动速度进行比较，获得速度偏差等等。该一个或多个偏差组成了感知信息的偏差信息，该偏差信息即为上述校准结果。
车辆获得上述校准结果后，可以将该校准结果发送给云端设备。云端设备再将该校准结果发送给上述路侧感知装置。路侧感知装置接收到该校准结果后，根据该校准结果校准自身的感知置信度。示例性地，路侧感知装置可以将该校准结果作为校准参数输入到自身感知计算单元的感知模型中，以实现感知模型的参数校正，因而校准路侧感知装置的感知置信度。
一种可能的实现方式中，若上述路侧感知装置感知到上述第一对象离开上述驾驶盲区路段，或者感知到第一对象进入上述车辆的感知范围。该路侧感知装置可以向云端设备发送第五信息。
示例性地，路侧感知装置在传感器检测到的检测信息中检测不到第一对象的存在，例如提取不到第一对象的感知信息，那么可以确定第一对象离开上述驾驶盲区路段。这种情况下，上述第五信息用于指示该第一对象离开上述驾驶盲区路段。示例性地，该第五信息可以是空数据，或者可以是预设的第一指示标记信息等，本申请实施例对此不做限制。
示例性地，路侧感知装置在传感器检测到的检测信息中提取出第一对象和车辆的感知信息，然后计算该两者之间的距离。若该距离小于预设的距离，那么可以确定该第一对象进入车辆的感知范围。这种情况下，上述第五信息用于指示该第一对象进入车辆的感知范围。示例性地，该第五信息可以是预设的第二指示标记信息等，本申请实施例对此不做限制。示例性地，该第二指示标记信息和上述第一指示标记信息可以相同，或者可以不同。
上述云端设备接收到上述第五信息后，可以获知上述第一对象离开上述驾驶盲区路段，或者第一对象进入上述车辆的感知范围。若第一对象离开上述驾驶盲区路段，那么表明该第一对象不会(或者暂时不会)对车辆的驾驶安全造成威胁。若第一对象进入上述车辆的感知范围，那么由该车辆来根据自身的感知信息来处理即可。因此，云端设备可以根据该第五信息生成感知融合关闭信息，并向车辆发送该感知融合关闭信息。该车辆接收到该感知融合关闭信息后，根据该信息的指示恢复单车感知驾驶模式，关闭与路侧感知装置检测到的第一对象的感知信息融合的功能。
示例性地，一种可能的实现中，上述第一对象是离开上述驾驶盲区路段的最后一个对象，这种情况下才会触发上述的融合关闭操作。即驾驶盲区路段中不存在任何威胁上述车辆驾驶安全的对象，此时路侧探测装置可以向云端设备发送空数据。例如，向云端设备发送的报文或消息中的数据为空。云端设备接收到该空数据后，可以向车辆发送上述感知融合关闭信息。若上述第一对象离开驾驶盲区路段后，驾驶盲区路段中还存在其它对象，特别是存在威胁上述车辆驾驶安全的对象，那么不会触发上述的融合关闭操作。
一种可能的实现方式中，若上述驾驶盲区路段中包括红绿灯。那么，上述路侧感知装置还可以获取该红绿灯的通行指示信息，并向上述云端设备发送该通行指示信息。该通行指示信息例如可以是红绿灯的相位信息等。云端设备接收到该通行指示信息后，可以结合上述车辆的位置信息为该车辆动态计算出最优路径和/或速度等信息，并将该信息发送给车辆。车辆接收到该信息后，可以根据该信息完成对应的驾驶控制。例如，按照该最优路径和/或速度来行驶等。
一种可能的实现方式中，可以是在上述计算出的最优路径和/或速度等信息相比于车辆上报的信息发生改变的情况下，上述云端设备才向车辆发送该最优路径和/或速度等信息。从而节省传输带宽。
综上所述，本申请实施例中，在道路盲区路段部署路侧感知装置，而不是在道路上连续部署大量的感知装置；并且车辆不和路侧感知装置通信，而是经由云端实现车路之间的信息交互，使得车内无需部署OBU，路侧也无需采用昂贵的RSU，从而极大地降低了成本。此外，把路侧感知装置当成是车辆外延的感知装置，即路侧感知装置感知到的信息经云端直接发给车辆，由车辆将该接收的感知信息和自身感知装置感知的信息融合以扩大车辆的感知范围，降低驾驶安全隐患。即本方案提供了一种可以有效降低车辆驾驶安全隐患且实现成本低，易于推广使用的车路协同方案。
上述主要对本申请实施例提供的方法进行了介绍。可以理解的是，各个控制单元或设备为了实现上述对应的功能，其包含了执行各个功能相应的硬件结构和/或软件模块。结合本文中所公开的实施例描述的各示例的单元及步骤，本申请能够以硬件或硬件和计算机软件的结合形式来实现。某个功能究竟以硬件还是计算机软件驱动硬件的方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用使用不同方法来实现所描述的功能，但这种实现不应认为超出本申请的范围。
本申请实施例可以根据上述方法示例对设备进行功能模块的划分，例如，可以对应各个功能划分各个功能模块，也可以将两个或两个以上的功能集成在一个模块中。上述集成的模块既可以采用硬件的形式实现，也可以采用软件功能模块的形式实现。需要说明的是，本申请实施例对模块的划分是示意性的，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。
在采用对应各个功能划分各个功能模块的情况下，本申请实施例还提供用于实现以上任一种方法的装置，例如，提供的装置包括用以实现以上任一种方法中的各步骤的单元(或手段)。
例如，请参考图10，其为本申请实施例提供的一种驾驶控制系统1000的结构示意图。图10所示的驾驶控制系统1000可以是上述方法中的任一实施例的车辆中的驾驶控制系统。该驾驶控制系统1000可以包括获取单元1001和处理单元1002。其中：
获取单元1001，用于获取来自云端设备的第一信息；该第一信息包括路侧感知装置对第一对象的感知信息；
处理单元1002，用于根据该第一信息和第一感知信息获取第一融合信息；并根据该第一融合信息执行第一驾驶控制；其中，该第一感知信息包括通过车辆的传感器获得的感知信息；
该处理单元1002，还用于在该车辆根据第二感知信息感知到该第一对象的情况下，根据该第二感知信息执行第二驾驶控制；该第二感知信息包括通过该车辆的传感器获得的对该第一对象的感知信息。
一种可能的实现方式中，该第一对象包括一个或多个目标车辆，该第一信息包括该路侧感知装置对该一个或多个目标车辆的感知信息。
一种可能的实现方式中，该获取单元1001，还用于获取来自云端设备的第二信息；该第二信息指示路侧感知装置对该第二对象的感知信息；该第二对象包括一个或多个行人；
该处理单元1002，还用于丢弃该第二信息。
一种可能的实现方式中，该获取单元1001，还用于获取来自该云端设备的第三信息；该第三信息指示在该车辆感知到该第一对象的情况下，该路侧感知装置对该第一对象的感知信息；
该处理单元1002具体用于：
将该第三信息和该第二感知信息按照预设的权重比例实现信息融合，获取第二融合信息；该第二感知信息的权重比例大于该第三信息的权重比例；
根据该第二融合信息执行该第二驾驶控制。
一种可能的实现方式中，该获取单元1001，还用于获取来自云端设备的第四信息；该第四信息指示在该车辆感知到该第一对象的情况下，该路侧感知装置对该第一对象的感知信息；
该处理单元1002，还用于根据该第二感知信息校准该第四信息，获得校准结果；
该车辆还包括发送单元，用于发送该校准结果，该校准结果用于修正该路侧感知装置的感知置信度。
一种可能的实现方式中，该获取单元1001，还用于在该车辆感知到该第一对象的情况下，或者在该第一对象离开该路侧感知装置的感知范围的情况下，
获取来自该云端设备的第五信息；该第五信息指示该车辆关闭路侧感知融合功能，该路侧感知融合功能为将该路侧感知装置的感知信息和该车辆的感知信息融合的功能。
一种可能的实现方式中，该获取单元1001具体用于：
在该车辆无法感知到该第一对象，且该第一对象满足第一条件的情况下，获取该第一信息；
该第一条件包括：该第一对象和该车辆之间的距离小于等于第一预设距离，和/或该第一对象和该车辆的碰撞时间小于等于第一预设时长。
图10所示驾驶控制系统1000中各个单元的具体操作以及有益效果可以参见上述图9及其可能的实施例中对应的描述，此处不再赘述。
例如，请参考图11，其为本申请实施例提供的一种云端设备1100的结构示意图。图11所示的云端设备1100可以是用于实现上述方法中的任一实施例的云端设备。该云端设备1100可以包括获取单元1101、处理单元1102和发送单元1103。其中：
获取单元1101，用于获取来自车辆的车辆状态信息；该车辆状态信息包括该车辆的位置信息和速度信息；
获取单元1101，还用于获取第一信息；该第一信息指示路侧感知装置对第一对象的感知信息；
处理单元1102，用于根据该车辆状态信息和该第一信息确定该第一对象满足第一条件；该第一条件包括：该第一对象和该车辆之间的距离小于等于第一预设距离，和/或该第一对象和该车辆的碰撞时间小于等于第一预设时长；
发送单元1103，用于向该车辆发送该第一信息。
一种可能的实现方式中，该获取单元1101，还用于获取来自该路侧感知装置的第二信息；该第二信息指示该车辆感知到该第一对象的情况下，该路侧感知装置对该第一对象的感知信息；
该发送单元1103，还用于向该车辆发送该第二信息；
该获取单元1101，还用于获取来自该车辆的第三信息；该第三信息为根据该车辆自身的感知信息校准该第二信息获得的校准结果；
该发送单元1103，还用于向该路侧感知装置发送该校准结果；该校准结果用于修正该路侧感知装置的感知置信度。
一种可能的实现方式中，该发送单元1103，还用于在该车辆感知到该第一对象的情况下，或者在该第一对象离开该路侧感知装置的感知范围的情况下，
向该车辆发送第四信息；该第四信息指示该车辆关闭路侧感知融合功能，该路侧感知融合功能为将该路侧感知装置的感知信息和该车辆的感知信息融合的功能。
一种可能的实现方式中，该获取单元1101，还用于获取来自该路侧感知装置的第五信息；该第五信息指示该第一对象离开该路侧感知装置的感知范围；
该处理单元1102，还用于根据该第五信息触发向该车辆发送该第四信息的操作。
图11所示云端设备1100中各个单元的具体操作以及有益效果可以参见上述图9及其可能的实施例中对应的描述，此处不再赘述。
例如，请参考图12，其为本申请实施例提供的一种路侧感知装置1200的结构示意图。图12所示的路侧感知装置1200可以是用于实现上述方法中的任一实施例的路侧感知装置。该路侧感知装置1200可以包括获取单元1201、处理单元1202和发送单元1203。其中：
获取单元1201，用于获取第一感知信息；该第一感知信息包括对第一对象的感知信息以及包括对该车辆的感知信息；
处理单元1202，用于根据该第一感知信息识别该第一对象威胁该车辆的行车安全；
发送单元1203，用于向云端设备发送第一信息，该第一信息指示该路侧感知装置对该第一对象的感知信息，该第一信息用于发送给该车辆。
一种可能的实现方式中，该发送单元1203，还用于向该云端设备发送第二信息；该第二信息指示该车辆感知到该第一对象的情况下，该路侧感知装置对该第一对象的感知信息；
该路侧感知装置还包括获取单元，用于从该云端设备获取校准结果；该校准结果用于修正该路侧感知装置的感知置信度，该校准结果为该车辆根据自身的感知信息校准该第二信息获得的校准结果。
一种可能的实现方式中，该发送单元1203，还用于
向该云端设备发送第三信息；该第三信息指示该第一对象离开该路侧感知装置的感知范围；该第三信息用于触发该云端设备向该车辆发送该第四信息，该第四信息指示该车辆关闭路侧感知融合功能，该路侧感知融合功能为将该路侧感知装置对该第一对象的感知信息和该车辆的感知信息融合的功能。
图12所示路侧感知装置1200中各个单元的具体操作以及有益效果可以参见上述图9及其可能的实施例中对应的描述，此处不再赘述。
应理解以上车辆、云端设备或路侧感知装置中各单元的划分仅是一种逻辑功能的划分，实际实现时可以全部或部分集成到一个物理实体上，也可以物理上分开。此外，装置中的单元可以以处理器调用软件的形式实现；例如装置包括处理器，处理器与存储器连接，存储器中存储有指令，处理器调用存储器中存储的指令，以实现以上任一种方法或实现该装置各单元的功能，其中处理器例如为通用处理器，例如中央处理单元(central processing unit，CPU)或微处理器，存储器为装置内的存储器或装置外的存储器。或者，装置中的单元可以以硬件电路的形式实现，可以通过对硬件电路的设计实现部分或全部单元的功能，该硬件电路可以理解为一个或多个处理器；例如，在一种实现中，该硬件电路为专用集成电路(application-specific integrated circuit，ASIC)，通过对电路内元件逻辑关系的设计，实现以上部分或全部单元的功能；再如，在另一种实现中，该硬件电路为可以通过可编程逻辑器件(programmable logic device，PLD)实现，以现场可编程门阵列(field programmable gate array，FPGA)为例，其可以包括大量逻辑门电路，通过配置文件来配置逻辑门电路之间的连接关系，从而实现以上部分或全部单元的功能。以上装置的所有单元可以全部通过处理器调用软件的形式实现，或全部通过硬件电路的形式实现，或部分通过处理器调用软件的形式实现，剩余部分通过硬件电路的形式实现。
在本申请实施例中，处理器是一种具有数据的处理能力的电路，在一种实现中，处理器可以是具有指令读取与运行能力的电路，例如CPU、微处理器、图形处理器(graphics processing unit，GPU)(可以理解为一种微处理器)、或数字信号处理器(digital singnal processor，DSP)等；在另一种实现中，处理器可以通过硬件电路的逻辑关系实现一定功能，该硬件电路的逻辑关系是固定的或可以重构的，例如处理器为ASIC或PLD实现的硬件电路，例如FPGA。在可重构的硬件电路中，处理器加载配置文档，实现硬件电路配置的过程，可以理解为处理器加载指令，以实现以上部分或全部单元的功能的过程。此外，还可以是针对人工智能设计的硬件电路，其可以理解为一种ASIC，例如神经网络处理单元(Neural Network Processing Unit，NPU)张量处理单元(tensor processing unit，TPU)、深度学习处理单元(deep learning processing unit,DPU)等。
可见，以上装置中的各单元可以是被配置成实施以上方法的一个或多个处理器(或处理电路)，例如：CPU、GPU、NPU、TPU、DPU、微处理器、DSP、ASIC、FPGA，或这些处理器形式中至少两种的组合。
此外，以上装置中的各单元可以全部或部分可以集成在一起，或者可以独立实现。在一种实现中，这些单元集成在一起，以片上系统(system-on-a-chip，SOC)的形式实现。该SOC中可以包括至少一个处理器，用于实现以上任一种方法或实现该装置各单元的功能，该至少一个处理器的种类可以不同，例如包括CPU和FPGA，CPU和人工智能处理器，CPU和GPU等。
示例性地，参见图13，其为本申请提供的设备的一种可能的物理实体的结构示意图。图13所示的设备1300可以是上述实施例所述方法中的车辆、云端设备或路侧感知装置。该设备1300包括：处理器1301、存储器1302和通信接口1303。处理器1301、通信接口1303以及存储器1302可以相互连接或者通过总线1304相互连接。
示例性的，存储器1302用于存储设备1300的计算机程序和数据，存储器1302可以包括但不限于是随机存储记忆体(random access memory，RAM)、只读存储器(read-only memory，ROM)、可擦除可编程只读存储器(erasable programmable read only memory，EPROM)或便携式只读存储器(compact disc read-only memory，CD-ROM)等。
上述方法实施例中设备的全部或部分的功能所需的软件或程序代码存储在存储器1302中。
一种可能的实施方式中，如果是部分功能所需的软件或程序代码存储在存储器1302中，则处理器1301除了调用存储器1302中的程序代码实现部分功能外，还可以配合其他部件(如通信接口1303)共同完成方法实施例描述的其他功能(如接收或发送数据的功能)。
通信接口1303的个数可以为多个，用于支持设备1300进行通信，例如接收或发送数据或信号等。
示例性的，处理器1301可以是上述介绍的CPU、GPU、NPU、TPU、DPU、微处理器、DSP、ASIC、FPGA，或这些处理器形式中至少两种的组合等。处理器1301可以用于读取存储器1302中存储的程序，执行上述图9及其可能的实施例所述方法中对应设备执行的操作。
图13所示设备1300中各个单元的具体操作以及有益效果可以参见上述图9及其可能的实施例中对应的描述，此处不再赘述。
本申请实施例还提供一种芯片，该芯片包括处理器和存储器。其中，该存储器用于存储计算机程序或计算机指令，该处理器用于执行该存储器中存储的计算机程序或计算机指令，使得该芯片执行上述图9及其可能的实施例中车辆所执行的操作。
本申请实施例还提供一种芯片，该芯片包括处理器和存储器。其中，该存储器用于存储计算机程序或计算机指令，该处理器用于执行该存储器中存储的计算机程序或计算机指令，使得该芯片执行上述图9及其可能的实施例中云端设备所执行的操作。
本申请实施例还提供一种芯片，该芯片包括处理器和存储器。其中，该存储器用于存储计算机程序或计算机指令，该处理器用于执行该存储器中存储的计算机程序或计算机指令，使得该芯片执行上述图9及其可能的实施例中路侧感知装置所执行的操作。
本申请实施例还提供一种计算机可读存储介质，该计算机可读存储介质存储有计算机程序或计算机指令，该计算机程序或计算机指令被处理器执行以实现上述图9及其可能的实施例中车辆所实现的方法。
本申请实施例还提供一种计算机可读存储介质，该计算机可读存储介质存储有计算机程序或计算机指令，该计算机程序或计算机指令被处理器执行以实现上述图9及其可能的实施例中云端设备所实现的方法。
本申请实施例还提供一种计算机可读存储介质，该计算机可读存储介质存储有计算机程序或计算机指令，该计算机程序或计算机指令被处理器执行以实现上述图9及其可能的实施例中路侧感知装置所实现的方法。
本申请实施例还提供一种计算机程序产品，当该计算机程序产品被计算机读取并执行时，上述图9及其可能的实施例中任一项所述的方法中车辆所实现的操作将被执行。
本申请实施例还提供一种计算机程序产品，当该计算机程序产品被计算机读取并执行时，上述图9及其可能的实施例中任一项所述的方法中云端设备所实现的操作将被执行。
本申请实施例还提供一种计算机程序产品，当该计算机程序产品被计算机读取并执行时，上述图9及其可能的实施例中任一项所述的方法中路侧感知装置所实现的操作将被执行。
应理解，在本申请的各个实施例中，各个过程的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本申请实施例的实施过程构成任何限定。
还应理解，术语“包括”(也称“includes”、“including”、“comprises”和/或“comprising”)当在本说明书中使用时指定存在所陈述的特征、整数、步骤、操作、元素、和/或部件，但是并不排除存在或添加一个或多个其他特征、整数、步骤、操作、元素、部件、和/或其分组。
还应理解，说明书通篇中提到的“一个实施例”、“一实施例”、“一种可能的实现方式”意味着与实施例或实现方式有关的特定特征、结构或特性包括在本申请的至少一个实施例中。因此，在整个说明书各处出现的“在一个实施例中”或“在一实施例中”、“一种可能的实现方式”未必一定指相同的实施例。此外，这些特定的特征、结构或特性可以任意适合的方式结合在一个或多个实施例中。
最后应说明的是：以上各实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述各实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分或者全部技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的范围。

Claims (20)

  1. 一种驾驶控制方法，其特征在于，所述方法包括：
    获取来自云端设备的第一信息；所述第一信息包括路侧感知装置对第一对象的感知信息；
    根据所述第一信息和第一感知信息获取第一融合信息；并根据所述第一融合信息执行第一驾驶控制；其中，所述第一感知信息包括通过车辆的传感器获得的感知信息；
    在所述车辆根据第二感知信息感知到所述第一对象的情况下，根据所述第二感知信息执行第二驾驶控制；所述第二感知信息包括通过所述车辆的传感器获得的对所述第一对象的感知信息。
  2. 根据权利要求1所述的方法，其特征在于，所述第一对象包括一个或多个目标车辆，所述第一信息包括所述路侧感知装置对所述一个或多个目标车辆的感知信息。
  3. 根据权利要求1或2所述的方法，其特征在于，所述方法还包括：
    获取来自云端设备的第二信息；所述第二信息指示所述路侧感知装置对第二对象的感知信息；所述第二对象包括一个或多个行人；
    丢弃所述第二信息。
  4. 根据权利要求1-3任一项所述的方法，其特征在于，所述方法还包括：获取来自所述云端设备的第三信息；所述第三信息指示在所述车辆感知到所述第一对象的情况下，所述路侧感知装置对所述第一对象的感知信息；
    所述根据所述车辆自身的第二感知信息执行第二驾驶控制，包括：
    将所述第三信息和所述第二感知信息按照预设的权重比例实现信息融合，获取第二融合信息；所述第二感知信息的权重比例大于所述第三信息的权重比例；
    根据所述第二融合信息执行所述第二驾驶控制。
  5. 根据权利要求1-4任一项所述的方法，其特征在于，所述方法还包括：
    获取来自云端设备的第四信息；所述第四信息指示在所述车辆感知到所述第一对象的情况下，所述路侧感知装置对所述第一对象的感知信息；
    根据所述第二感知信息校准所述第四信息，获得校准结果；
    发送所述校准结果，所述校准结果用于修正所述路侧感知装置的感知置信度。
  6. 根据权利要求1-5任一项所述的方法，其特征在于，在所述车辆感知到所述第一对象的情况下，或者在所述第一对象离开所述路侧感知装置的感知范围的情况下，所述方法还包括：
    获取来自所述云端设备的第五信息；所述第五信息指示所述车辆关闭路侧感知融合功能，所述路侧感知融合功能为将所述路侧感知装置的感知信息和所述车辆的感知信息融合的功能。
  7. 根据权利要求1-6任一项所述的方法，其特征在于，所述获取来自云端设备的第一信息，包括：
    在所述车辆无法感知到所述第一对象，且所述第一对象满足第一条件的情况下，获取所述第一信息；
    所述第一条件包括：所述第一对象和所述车辆之间的距离小于等于第一预设距离，和/或所述第一对象和所述车辆的碰撞时间小于等于第一预设时长。
  8. 根据权利要求1-7任一项所述的方法，其特征在于，所述路侧感知装置部署在所述车辆前进方向的驾驶盲区路段上，所述路侧感知装置的感知范围覆盖所述驾驶盲区路段；
    所述驾驶盲区路段包括如下的一项或多项：弯道路段，包括路口的路段，包括进口或出口的路段，或坡顶路段。
  9. 一种协同驾驶方法，其特征在于，所述方法包括：
    获取来自车辆的车辆状态信息；所述车辆状态信息包括所述车辆的位置信息和速度信息；
    获取第一信息；所述第一信息指示路侧感知装置对第一对象的感知信息；
    根据所述车辆状态信息和所述第一信息确定所述第一对象满足第一条件；所述第一条件包括：所述第一对象和所述车辆之间的距离小于等于第一预设距离，和/或所述第一对象和所述车辆的碰撞时间小于等于第一预设时长；
    向所述车辆发送所述第一信息。
  10. 根据权利要求9所述的方法，其特征在于，所述方法还包括：
    获取来自所述路侧感知装置的第二信息；所述第二信息指示所述车辆感知到所述第一对象的情况下，所述路侧感知装置对所述第一对象的感知信息；
    向所述车辆发送所述第二信息；
    获取来自所述车辆的第三信息；所述第三信息为根据所述车辆自身的感知信息校准所述第二信息获得的校准结果；
    向所述路侧感知装置发送所述校准结果；所述校准结果用于修正所述路侧感知装置的感知置信度。
  11. 根据权利要求9或10所述的方法，其特征在于，在所述车辆感知到所述第一对象的情况下，或者在所述第一对象离开所述路侧感知装置的感知范围的情况下，所述方法还包括：
    向所述车辆发送第四信息；所述第四信息指示所述车辆关闭路侧感知融合功能，所述路侧感知融合功能为将所述路侧感知装置的感知信息和所述车辆的感知信息融合的功能。
  12. 根据权利要求11所述的方法，其特征在于，所述方法还包括：
    获取来自所述路侧感知装置的第五信息；所述第五信息指示所述第一对象离开所述路侧感知装置的感知范围；
    根据所述第五信息触发向所述车辆发送所述第四信息的操作。
  13. 一种驾驶控制系统，其特征在于，包括：
    获取单元，用于获取来自云端设备的第一信息；所述第一信息包括路侧感知装置对第一对象的感知信息；
    处理单元，用于根据所述第一信息和第一感知信息获取第一融合信息；并根据所述第一融合信息执行第一驾驶控制；其中，所述第一感知信息包括通过车辆的传感器获得的感知信息；
    所述处理单元，还用于在所述车辆根据第二感知信息感知到所述第一对象的情况下，根据所述第二感知信息执行第二驾驶控制；所述第二感知信息包括通过所述车辆的传感器获得的对所述第一对象的感知信息。
  14. 根据权利要求13所述的驾驶控制系统，其特征在于，
    所述获取单元，还用于获取来自云端设备的第二信息；所述第二信息指示路侧感知装置对所述第二对象的感知信息；所述第二对象包括一个或多个行人；
    所述处理单元，还用于丢弃所述第二信息。
  15. 根据权利要求13或14所述的驾驶控制系统，其特征在于，
    所述获取单元，还用于获取来自所述云端设备的第三信息；所述第三信息指示在所述车辆感知到所述第一对象的情况下，所述路侧感知装置对所述第一对象的感知信息；
    所述处理单元具体用于：
    将所述第三信息和所述第二感知信息按照预设的权重比例实现信息融合，获取第二融合信息；所述第二感知信息的权重比例大于所述第三信息的权重比例；
    根据所述第二融合信息执行所述第二驾驶控制。
  16. 根据权利要求13-15任一项所述的驾驶控制系统，其特征在于，
    所述获取单元，还用于获取来自云端设备的第四信息；所述第四信息指示在所述车辆感知到所述第一对象的情况下，所述路侧感知装置对所述第一对象的感知信息；
    所述处理单元，还用于根据所述第二感知信息校准所述第四信息，获得校准结果；
    所述车辆还包括发送单元，用于发送所述校准结果，所述校准结果用于修正所述路侧感知装置的感知置信度。
  17. 一种云端设备，其特征在于，所述云端设备包括：
    获取单元，用于获取来自车辆的车辆状态信息；所述车辆状态信息包括所述车辆的位置信息和速度信息；
    获取单元，还用于获取第一信息；所述第一信息指示路侧感知装置对第一对象的感知信息；
    处理单元，用于根据所述车辆状态信息和所述第一信息确定所述第一对象满足第一条件；所述第一条件包括：所述第一对象和所述车辆之间的距离小于等于第一预设距离，和/或所述第一对象和所述车辆的碰撞时间小于等于第一预设时长；
    发送单元，用于向所述车辆发送所述第一信息。
  18. 一种车辆，其特征在于，所述车辆包括处理器和存储器，其中，所述存储器用于存储计算机程序或计算机指令，所述处理器用于执行所述存储器中存储的计算机程序或计算机指令，使得所述车辆执行如权利要求1-8任一项所述的方法。
  19. 一种云端设备，其特征在于，所述云端设备包括处理器和存储器，其中，所述存储器用于存储计算机程序或计算机指令，所述处理器用于执行所述存储器中存储的计算机程序或计算机指令，使得所述云端设备执行如权利要求9-12任一项所述的方法。
  20. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质存储有计算机程序或计算机指令，所述计算机程序或计算机指令被处理器执行以实现权利要求1-8任意一项所述的方法；
    或者，所述计算机程序或计算机指令被处理器执行以实现权利要求9-12任意一项所述的方法。
PCT/CN2025/078928 2024-02-28 2025-02-25 驾驶控制方法、协同驾驶方法及相关装置 Pending WO2025180342A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202410225645.9 2024-02-28
CN202410225645.9A CN120599850A (zh) 2024-02-28 2024-02-28 驾驶控制方法、协同驾驶方法及相关装置

Publications (1)

Publication Number Publication Date
WO2025180342A1 true WO2025180342A1 (zh) 2025-09-04

Family

ID=96889589

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2025/078928 Pending WO2025180342A1 (zh) 2024-02-28 2025-02-25 驾驶控制方法、协同驾驶方法及相关装置

Country Status (2)

Country Link
CN (1) CN120599850A (zh)
WO (1) WO2025180342A1 (zh)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110874945A (zh) * 2018-08-31 2020-03-10 百度在线网络技术（北京）有限公司 基于车路协同的路侧感知系统及其车辆控制方法
EP3752399A1 (en) * 2018-02-15 2020-12-23 Toyota Motor Europe Control method for a vehicle, computer program, non-transitory computer-readable medium, and automated driving system
DE102019128511A1 (de) * 2019-10-22 2021-04-22 Denso Automotive Deutschland Gmbh Vorrichtung und Verfahren zum Fusionieren von Informationen
CN114179829A (zh) * 2021-12-24 2022-03-15 中汽创智科技有限公司 多端协同的车辆行驶方法、装置、系统及介质
CN114429715A (zh) * 2022-01-27 2022-05-03 中国第一汽车股份有限公司 车路云协同的路径确定方法、装置、系统、设备和介质
CN115691183A (zh) * 2022-08-31 2023-02-03 广州软件应用技术研究院 一种基于端边云协同计算的车路协同驾驶方法及系统

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3752399A1 (en) * 2018-02-15 2020-12-23 Toyota Motor Europe Control method for a vehicle, computer program, non-transitory computer-readable medium, and automated driving system
CN110874945A (zh) * 2018-08-31 2020-03-10 百度在线网络技术（北京）有限公司 基于车路协同的路侧感知系统及其车辆控制方法
DE102019128511A1 (de) * 2019-10-22 2021-04-22 Denso Automotive Deutschland Gmbh Vorrichtung und Verfahren zum Fusionieren von Informationen
CN114179829A (zh) * 2021-12-24 2022-03-15 中汽创智科技有限公司 多端协同的车辆行驶方法、装置、系统及介质
CN114429715A (zh) * 2022-01-27 2022-05-03 中国第一汽车股份有限公司 车路云协同的路径确定方法、装置、系统、设备和介质
CN115691183A (zh) * 2022-08-31 2023-02-03 广州软件应用技术研究院 一种基于端边云协同计算的车路协同驾驶方法及系统

Also Published As

Publication number Publication date
CN120599850A (zh) 2025-09-05

Similar Documents

Publication Publication Date Title
US12022353B2 (en) Vehicle to everything dynamic geofence
EP3622496B1 (en) System and method for trust parameters in vehicle warning messages
US11915593B2 (en) Systems and methods for machine learning based collision avoidance
CN113195325B (zh) 与指示距车道参考点的横向距离的车道内位置数据相关的方法和装置
US11743694B2 (en) Vehicle to everything object exchange system
US11422561B2 (en) Sensor system for multiple perspective sensor data sets
US10802110B2 (en) Vehicular radar interference management using basic safety messages
CN111200842B (zh) 数据通信的方法、控制单元和车辆以及计算机程序
KR20220034250A (ko) 협력 학습 신경망 및 시스템
Malinverno et al. Performance analysis of C-V2I-based automotive collision avoidance
US12493098B2 (en) Method for VRU to predict movement path in wireless communication system supporting sidelink, and device for same
EP3914923B1 (en) Network node and method performed therein for handling data of objects in a communication network
Jandial et al. Implementation and evaluation of intelligent roadside infrastructure for automated vehicle with I2V communication
US20230124127A1 (en) Method for predicting entry path by vru device in wireless communication system supporting sidelink, and apparatus therefor
Duarte et al. Safesmart: A vanet system for faster responses and increased safety in time-critical scenarios
Godoy et al. An auxiliary V2I network for road transport and dynamic environments
Bouchemal et al. Testbed of V2X infrastructure for autonomous vehicles
Hejazi et al. Modeling and evaluation of cooperative Vulnerable Road User protection schemes in realistic C-ITS environments
EP3882729B1 (en) Method, computer program, apparatus, vehicle and network component for determining a speed limit for a tele-operated vehicle
CN120019676A (zh) 电子设备、通信方法和存储介质
WO2019040024A2 (en) SYSTEM AND METHOD FOR DIFFUSION BY ROUTING AND PROCESSING TRAFFIC WARNING INFORMATION TO ADVISE A DRIVER
WO2025180342A1 (zh) 驾驶控制方法、协同驾驶方法及相关装置
EP1953725B1 (en) Mobile unit communication apparatus and program
WO2023171371A1 (ja) 通信装置および通信方法
EP4535329A1 (en) Communication device and communication method

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: 25760883

Country of ref document: EP

Kind code of ref document: A1