CN114516366A - Vehicle control system, apparatus and method for narrow turn mode - Google Patents

Abstract

The invention provides a vehicle control system, device and method for narrow turning mode. The vehicle control apparatus is configured to: receiving environmental information around a vehicle and vehicle state information; starting an automatic driving narrow turning mode when determining that the vehicle in the narrow turning area has a potential collision risk or receiving an automatic driving request of a driver; and determining a planned path through the narrow turning area in the narrow turning mode, and dynamically adjusting the vehicle speed request and the steering request in controlling the vehicle to implement the planned path based on the environment information and the vehicle state information.

Description

Vehicle control system, apparatus and method for tight turn mode

technical field

The present invention generally relates to the technical field of vehicle control, and in particular, to a vehicle control system, apparatus and method for tight turning mode.

Background technique

Although road planning has been implemented, for example, on the basis of utilizing the existing roads as much as possible, the combination of land use and urban and rural planning is realized through improvement measures. However, there are inevitably scenarios where the vehicle needs to turn on narrow roads, such as winding country roads or urban roads with complex environments. For such a scenario, it is not easy to drive a vehicle through even an experienced driver, let alone a novice driver. In addition, driving in bad weather or at night in such a driving scenario increases the risk of a dangerous accident. In the prior art, there is no better solution for how to guide the vehicle through the narrow turning area.

SUMMARY OF THE INVENTION

The following introduction is provided to introduce a selection of concepts in a simplified form that are further described in the detailed description that follows. This introduction is not intended to highlight key features or essential features of the claimed subject matter, nor is it intended to limit the scope of the claimed subject matter.

According to one aspect of the present invention, there is provided a vehicle control apparatus for a narrow turn mode, which is configured to: receive environmental information around the vehicle and vehicle status information; when it is determined that the vehicle in the narrow turn area has a potential collision risk Or when receiving the driver's automatic driving request, turn on the narrow turning mode of automatic driving, wherein the narrow turning is defined as the width of the lane is less than 1.5 times the width of the vehicle body, and the turning of the lane is greater than 70°; and in the narrow turning mode, Determine a planned path through the narrow turning area, and dynamically adjust the speed request and steering request so that some or all of the Threshold of:

- the difference between the requested steering angle and the current body yaw angle;

- the requested steering speed;

- the difference between the currently requested steering angle and the last requested steering angle;

- The requested acceleration in the direction of travel of the vehicle.

According to a possible embodiment, the vehicle control device is configured to dynamically adjust the steering request and the vehicle speed request such that the larger the requested steering angle, the lower the requested vehicle speed.

According to a feasible embodiment, the vehicle control device is further configured to: control the vehicle to decelerate or brake to avoid collision with the moving object when it is determined based on the planned path and the predicted trajectory of the moving object that the vehicle will collide with the moving object. collision of moving objects; and/or when it is determined that a stationary object appears on the planned path based on the planned path and the environment information, sending object reminder information to the driver or adjusting the planned path to avoid the stationary object.

According to a possible embodiment, the vehicle control device is configured to determine whether the following items are satisfied, and determine that the vehicle has a potential collision risk when at least one of the following is satisfied:

- the distance between the vehicle and the potential collision object is less than the safe distance threshold;

- An environment unfavorable for driving occurs;

- The running behavior of the vehicle appears to be reciprocating.

According to a feasible implementation manner, the distance between the vehicle and the potential collision object being less than the safety distance threshold includes at least one of the following:

- The sum of the distances between the two sides of the vehicle and the potential collision object is less than the bilateral distance threshold;

- the distance between the left or right side of the vehicle and the potential collision object is less than the one-sided distance threshold;

- It is determined based on the planned path and the estimated trajectory of the moving object that the vehicle will collide with the moving object.

According to a feasible embodiment, the environment unfavorable for driving includes weather environment and lighting environment unfavorable for driving.

According to a feasible implementation manner, the weather environment or lighting environment unfavorable for driving includes at least one of the following:

- there is fog, rain, snow or hail;

- Insufficient light or strong reflections.

According to a feasible implementation manner, the reciprocation of the running behavior of the vehicle includes at least one of the following:

- The number of times the vehicle turns left and right alternately exceeds the predetermined number of times;

- The number of times the vehicle alternates between advancing in one direction and reversing in an opposite direction exceeds a predetermined number of times.

According to a feasible implementation manner, the vehicle control device is further configured to determine the planned route by: determining a scene of the narrow turning area based on environmental information, and selecting from a set of stored planned routes and the determined scene corresponding planned path; or, determining the planned path based on real-time environmental conditions, vehicle preferences, and driver preferences, optionally, using real-time environmental conditions, vehicle preferences, and driver preferences as input parameters of the machine learning model, and obtaining A model output containing the planned path.

According to a feasible implementation manner, the vehicle control device is further configured to: after the narrow turning mode is turned on, before determining the planned route, determine whether the vehicle is in a position that does not have enough space for passage; if the determination result is affirmative When , based on the record of the vehicle's driving track and the record of the obstacle information on the way, the vehicle is controlled to return to the position at the beginning of entering the narrow turning area.

According to one possible embodiment, the narrow turn area contains a path that turns approximately at a right angle.

According to another aspect of the present invention, there is provided a vehicle control system for a narrow turn mode, comprising: a sensor including an environment sensor for sensing a vehicle surrounding environment and generating environmental information and a vehicle state for sensing and generating A vehicle state sensor for vehicle state information; and a vehicle control device as described above, configured to be communicatively coupled to the sensor, when it is determined that a vehicle in a narrow turning area has a potential collision risk or a driver's request for automatic driving is received, Turning on a narrow turning mode of automatic driving, wherein a narrow turning is defined as a lane width less than 1.5 times the vehicle body width and a lane turning greater than 70°; in the narrow turning mode, determining a planned path through the narrow turning area, and In the process of controlling the vehicle to implement the planned path based on the environmental information and the vehicle state information, the vehicle speed request and the steering request are dynamically adjusted so that some or all of the following items satisfy the corresponding thresholds:

- The difference between the requested steering angle and the current body yaw angle.

- the requested steering speed;

- the difference between the currently requested steering angle and the last requested steering angle;

- The requested acceleration in the direction of travel of the vehicle.

According to a possible embodiment, the environment sensor includes a plurality of environment sensors arranged around the vehicle.

According to a possible embodiment, the plurality of environmental sensors include ultrasonic sensors and surround view cameras.

According to a possible embodiment, the ultrasonic sensor includes a plurality of ultrasonic sensors arranged on the front, rear, left and right sides of the vehicle, and the surround-view camera includes a plurality of surround-view cameras arranged on the left and right sides of the vehicle Camera.

According to a possible embodiment, the number of sensors arranged on the left and right sides of the vehicle increases as the distance between the front and rear wheels of the vehicle increases.

According to yet another aspect of the present invention, there is provided a vehicle control method for a narrow turn mode, optionally, the method is performed by the vehicle control device as described above and/or the vehicle control system as described above, wherein The method includes: receiving environmental information around the vehicle and vehicle status information; when it is determined that the vehicle in a narrow turning area has a potential collision risk or a driver's automatic driving request is received, the narrow turning mode of automatic driving is turned on, wherein the narrow turning mode is Turning is defined as a lane width less than 1.5 times the vehicle body width and a lane turning greater than 70°; and in the narrow turning mode, determining a planned path through the narrow turning area, and controlling the vehicle based on environmental information and vehicle state information In the process of implementing the planned path, the vehicle speed request and the steering request are dynamically adjusted so that some or all of the following items meet the corresponding thresholds:

- The difference between the requested steering angle and the current body yaw angle.

- the requested steering speed;

- the difference between the currently requested steering angle and the last requested steering angle;

- The requested acceleration in the direction of travel of the vehicle.

According to yet another aspect of the present invention, there is provided a machine-readable storage medium storing executable instructions which, when executed, cause a machine to execute the vehicle control method as described above.

Description of drawings

By way of example and not of limitation, implementations of the present invention are illustrated in the accompanying drawings, in which like reference numerals refer to the same or similar parts, wherein:

FIG. 1 illustrates an exemplary scenario in which some implementations of the present invention may be implemented;

2 is a schematic block diagram of a vehicle control system according to a possible embodiment of the present invention;

FIG. 3 schematically shows an exemplary arrangement of some components of the vehicle control system of FIG. 2 in a vehicle; and

FIG. 4 is a flowchart of a vehicle control method according to a possible embodiment of the present invention.

Detailed ways

Embodiments of the present invention provide a vehicle control solution for a narrow turn scene, which enables a narrow turn when it is determined that a vehicle driven by a human driver has a potential collision risk in the narrow turn scene or in response to a driver's automatic driving request mode of autonomous driving to assist the vehicle through this narrow turning area with the aid of electronic controls, thereby enhancing vehicle safety.

According to the embodiment of the present invention, considering that the applicable situation is to use automatic driving when there are drivers and passengers in the vehicle, in the functional design of the narrow turning mode, not only the pursuit of traffic efficiency by "machine thinking", but Fully considering the feelings of the occupants in the vehicle, a control strategy to improve comfort is adopted in vehicle control, thereby improving vehicle friendliness.

According to the embodiment of the present invention, while the electronic control is used to control the behavior of the vehicle, the characteristics of electronic control performed by the mechanical system of the vehicle are considered, that is, the mechanical system often cannot realize the sudden change of behavior, and the steering control request and the process of realizing the planned path are not affected. The vehicle speed control request is adjusted in real time, so that the vehicle can better follow the planned route, and even if there is a deviation, it can be corrected without accumulating the deviation in the direction of increasing the deviation.

The embodiments of the present invention mainly relate to a vehicle control scheme in a narrow turning scenario. A narrow turn is defined as a lane width less than 1.5 times the body width and a lane turn greater than 70°. Narrow turn areas in particular contain paths that turn around at right angles.

Referring to Figure 1, a tight turn scenario is shown in which some implementations of the present invention may be implemented. The scene in Figure 1 is, for example, a road in an old city. The width of the road is only slightly larger than the width of the vehicle body. There are houses or complex obstacles on both sides of the road (for example, randomly placed trash cans, irregularly parked bicycles, bicycles that may run at any time) pets, people who suddenly walked out of the house), and there are scenes that require turns in the section of narrow roads, especially right-angle turns or turns close to right-angle turns (for example, turns of 80°-110°).

It can be understood that the narrow turning scenarios applicable to the present invention may also be other scenarios where the vehicle needs to turn on a narrow road, for example, a mountain curve, a country road, or a narrow road turning condition that is originally wide but caused by random parking.

FIG. 2 schematically shows a vehicle control system 100 according to a possible embodiment of the present invention, which mainly includes a sensor 10 and a vehicle control device 50 . The sensor 10 may include an environment sensor 20, a vehicle state sensor 30, and a communication unit 40 having a function of exchanging information with the outside of the vehicle.

The environmental sensor 20 is used to sense environmental conditions around the vehicle and generate environmental information. The environmental sensor 20 may be provided in the vehicle or around the vehicle body, that is, implemented as an onboard sensor. The environmental sensor 20 may include a vehicle-mounted camera (single-target, multi-target, surround view), lidar, ultrasonic radar (eg, millimeter-wave radar), and the like. Vehicle cameras can obtain environmental information through image or video analysis, such as the relative distance of the vehicle from the roadside or obstacles. The radar can obtain the relative distance of the vehicle from the roadside or obstacles by analyzing the point cloud.

The environmental sensor 20 may include a plurality of environmental sensors disposed around the vehicle body, and the arrangement takes into account safety redundancy, ie, ensuring that the environmental conditions around the vehicle can be adequately captured, especially the environmental conditions on both sides of the vehicle.

Referring to FIG. 3 , in one embodiment, six ultrasonic sensors (six ultrasonic sensors 21A to 21F at the front of the vehicle; and the rear of the vehicle are provided respectively at the front and rear of the vehicle (ie, the head and the tail), respectively. 6 ultrasonic sensors 22A to 22F). On the left and right sides of the vehicle, four ultrasonic sensors (four ultrasonic sensors 23A to 23D on the left side of the vehicle; and four ultrasonic sensors 24A to 24D on the right side of the vehicle) are provided, respectively. In addition, one surround-view camera (front surround-view camera 21G, rear surround-view camera 22G, left-side surround-view camera 23E, and right-side surround-view camera 24E) is provided at the front, rear, left, and right sides of the vehicle, respectively.

It can be understood that the above embodiments describe the arrangement positions and specific numbers of the environmental sensors. The number and arrangement of environmental sensors can be adapted according to the application instance.

In one embodiment, in order to strengthen the safety redundancy of monitoring the environment on both sides of the vehicle, the number of sensors on the side of the vehicle is determined according to the distance between the front and rear wheels of the vehicle, so as to ensure that on the sides of the vehicle, every predetermined length (for example, , 60cm) is provided with a sensor. For example, if the distance between the front and rear wheels of the vehicle is less than or equal to 1.8m, three sensors are installed on both sides of the vehicle; if the distance between the front and rear wheels of the vehicle is greater than 1.8m, four sensors are installed on both sides of the vehicle.

In addition, in order to ensure the measurement effect of the vehicle side sensor, the side sensor can be installed on the side skirt, and the distance from the ground is greater than or equal to 200mm.

The vehicle state sensor 30 is used to sense the vehicle state and generate vehicle state information. The vehicle state sensor 30 may include a steering angle sensor, a vehicle speed sensor, a displacement sensor, a hydraulic pressure sensor, and the like. Vehicle status information can include information representing vehicle status such as vehicle speed, vehicle acceleration, and body yaw angle, which can be directly measured by vehicle status sensors or calculated from data sensed by vehicle status sensors. .

The communication unit 40 is used to receive or transmit information required for vehicle control from or to the outside of the vehicle. The communication unit 40 is, for example, an in-vehicle transceiver, which can determine the environmental information by receiving the time delay of the signal or according to the time stamp information in the signal. With the help of the communication unit 40, the vehicle end can receive environmental information from sensors outside the vehicle, for example, when the vehicle is driving on a narrow urban road, cameras at roadside facilities capture the environmental information and communicate via vehicle-to-everything (for example, V2X ) to send the captured environmental information to the vehicle. With the aid of the communication unit 40, the vehicle end can also receive environmental information from the cloud server. For example, the cloud server receives the location information reported by the vehicle end and sends the stored environment information related to the location to the vehicle end.

The vehicle control device 50 is communicatively connected to the sensor 10, receives environmental information and vehicle status information from the sensor 10, processes and analyzes the information, and generates control signals for steering the vehicle, such as a steering request and a vehicle speed request, so that the vehicle The steering system 200 and the vehicle body stability system 300 steer the vehicle according to control signals from the vehicle control device 50 .

The vehicle control device 50 may be provided in an electronic control unit (ECU) of the vehicle, ie the control strategy according to the invention is implemented by means of the ECU. The vehicle control device 50 may also be constructed as a control device independent of and communicatively connected to the ECU.

The vehicle control device 50 may be implemented in hardware or software or a combination of software and hardware. For the hardware implemented part, it can be implemented in one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), data signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs) ), a processor, a controller, a microcontroller, a microprocessor, an electronic unit designed to perform its functions, or a combination thereof. For the part implemented in software, it can be implemented by means of microcode, program code or code segments, which can also be stored in a machine-readable storage medium such as a storage component.

In one embodiment, the vehicle control device 50 is implemented to include a memory and a processor. The memory contains instructions that, when executed by the processor, cause the processor to perform a control strategy/control method according to an embodiment of the present invention.

In one embodiment, the vehicle control device 50 is implemented as a plurality of software modules. One or more of the multiple software modules may be implemented in one chip or circuit, or may be provided in multiple chips or multiple circuits.

FIG. 4 shows a vehicle control method 400 according to an embodiment of the present invention. The method 400 can be implemented in the above-mentioned vehicle control device 50 or in the above-mentioned vehicle control system 100 , and therefore, the above related descriptions are also applicable to this.

In block 402, the vehicle control device 50 receives environmental information and vehicle state information.

The environmental information and vehicle state information are collected by the sensor 10 and transmitted to the vehicle control device 50 . The environmental information may include road information, obstacle information (eg, the type and state of the obstacle), distance information between the vehicle and the obstacle, weather information. The vehicle state information may include vehicle speed information, acceleration information, vehicle yaw angle information, and steering speed information.

In block 404, the vehicle control device 50 determines that the vehicle is in a narrow turn area. The vehicle is in a tight turn area includes the vehicle is about to enter the tight turn area, the vehicle is in the narrow turn path, and the vehicle has just left the tight turn path. When the vehicle is about to enter a narrow turning area, the distance between the front of the vehicle and the area is less than 2 body lengths. The vehicle has just left the narrow turning path when the rear of the vehicle is less than 2 body lengths from the area.

In one embodiment, narrow turning scenes that the vehicle often passes through are pre-stored in the storage device of the vehicle, and the vehicle control device 50 can identify the scene where the vehicle is currently located based on the received environmental information, and match the stored narrow turning scene with the stored narrow turning scene. Scenarios are matched, from which it can be determined that the vehicle is entering a tight turning area.

In another embodiment, the judgment criteria of the narrow turning scene, such as the road width range and the road turning angle range, are pre-stored in the storage device of the vehicle, and the vehicle control device 50 can analyze and process the received environmental information and determine the When the current scene where the vehicle is located meets the judgment standard, it is determined that the vehicle enters the narrow turning area.

In addition, when the vehicle control device 50 determines that the vehicle enters a narrow turning area, it can control all on-board environment sensors to be turned on, so as to monitor the environment around the vehicle. It can be understood that, for the situation where the vehicle is in other scenarios, it may not be necessary to turn on all the on-board environmental sensors, but only the environmental sensors that can respond to the current scenario need to be turned on, so as to save computing power.

In block 406 , the vehicle control device 50 determines whether the vehicle has a potential collision risk or whether an automated driving request has been received from the driver.

In one embodiment, the vehicle control device 50 determines whether the vehicle has a potential collision risk by judging whether the following conditions (1) to (3) are satisfied, and when at least one of the following conditions (1) to (3) is satisfied, It is determined that the vehicle has a potential collision risk.

(1) The distance between the vehicle and the potential collision object is less than the safe distance threshold. In other words, where the distance between the vehicle and the potential collision object is so close that it is less than the safe distance threshold, the vehicle is at risk of a current collision. This condition (1) can be judged by the following subconditions (1a) to (1b).

(1a) The sum of the distances between the two sides of the vehicle and the potential collision object is less than the bilateral distance threshold. For example, the distance between the left side of the vehicle and the obstacle on the left side of the vehicle and the distance between the right side of the vehicle and the obstacle on the right side of the vehicle are calculated, and when the sum is less than a predetermined bilateral distance threshold, it is determined as the distance between the vehicle and the vehicle. The distance between potential collision objects is less than the safe distance threshold. In this way, it can be ensured that there is a certain redundancy in the width of the road relative to the width of the vehicle body.

(1b) The distance between the left or right side of the vehicle and the potential collision object is less than the one-sided distance threshold. For example, calculating the distance between the left side of the vehicle and the obstacle on the left side of the vehicle and the distance between the right side of the vehicle and the obstacle on the right side of the vehicle, when either of these two distances is smaller than the predetermined one-sided distance threshold, It is determined that the distance between the vehicle and the potential collision object is less than the safe distance threshold. In this way, it can be ensured that the left and right sides of the vehicle have a certain redundancy with the obstacles respectively, and there will be no collision or demarcation of the road (on a small road without guardrails or curbs on the side of the road, if the vehicle does not drive in the middle of the road, it is extremely easy to draw the way).

(1c) Based on the planned path of the vehicle and the estimated trajectory of the moving object, it is determined that the vehicle will collide with the moving object. For example, if the potential collision object is a moving object (for example, a moving pet or pedestrian), although the current vehicle will not collide with the moving object, it is judged that the two may collide according to the planned path of the vehicle and the predicted trajectory of the moving object. It is determined that the distance between the vehicle and the potential collision object is less than the safe distance threshold.

(2) An environment unfavorable for driving occurs. The driving-unfavorable environment may include a driving-unfavorable weather environment and a lighting environment. These unfavorable environmental factors can be quantitatively calibrated and judged by setting corresponding thresholds, so as to establish a unified judgment standard and improve the judgment accuracy.

In one embodiment, the weather conditions that are not conducive to driving may include fog, rain, snow, or hail. In addition, corresponding degree thresholds can be set for weather conditions based on weather information, for example, visibility thresholds are set for foggy weather; rainfall thresholds are set for rainy weather, and when it is judged based on the corresponding degree thresholds that the weather is not conducive to driving to a certain extent, It is determined that there is a weather environment unfavorable for driving.

In one embodiment, the lighting environment that is not conducive to driving may include insufficient lighting or strong reflections. In addition, a corresponding light intensity threshold may be set for the lighting environment, and when it is determined based on the corresponding light intensity threshold that the lighting is unfavorable for driving to a certain extent, it is determined that a lighting environment unfavorable for driving occurs.

(3) The running behavior of the vehicle reciprocates. Back-and-forth in the vehicle's behavior, which can manifest as alternating left and right turns and/or alternating forward and reverse, indicates that the driver is trying repeatedly, likely because the vehicle is stuck somewhere in a tight turning area. The running behavior of the vehicle can be obtained by detecting the trajectory of the vehicle or detecting the operating behavior of the driver.

When the driver feels that the narrow road or curve is difficult to drive, the driver can send an automatic driving request by pressing a button in the car or touching a virtual button on the touch screen in the car to request to start the automatic driving. Narrow turn mode of driving, i.e., requesting the Autopilot system to take over the vehicle, assisting the vehicle through the area through the Narrow Turn Mode feature of Autopilot.

In the event that the determination in block 406 is "No", that is, the driver's automatic driving request has not been received, and the vehicle has not been determined to have a potential collision risk, the method 400 returns to block 402 and continues to receive environmental information and vehicle status information for real-time monitoring of vehicle surroundings and vehicle status.

In the event that the determination in block 406 is "Yes", ie, a driver's request for automatic driving is received, or it is determined that the vehicle is at a potential collision risk, the method 400 proceeds to block 408 .

In block 408 , the vehicle control device 50 turns on the tight turn mode for automatic driving.

In block 410, it is determined whether the vehicle is in a location that does not have sufficient clearance to pass. A location that does not have enough space for passage can be understood as a vehicle being "stuck" somewhere on a narrow road, and it is impossible to directly plan a path from the current location to pass through the narrow turning area.

In the case of a "YES" determination in block 410, the vehicle control device 50 controls the vehicle to retract back into the position at the beginning of the narrow turn area.

In one embodiment, the vehicle control device 50 controls the vehicle to return along the original path according to the recorded vehicle travel track and the obstacle information on the way. During the return process, the vehicle control device 50 determines whether there is a change between the newly acquired obstacle information and the recorded obstacle information based on the environment information monitored by the environment sensor in real time, for example, the change is caused by a system error or a change in the position of the obstacle cause. When it is determined that there is a change in the obstacle information and the change is favorable for the vehicle to pass (for example, the newly acquired obstacle position is farther from the recorded vehicle trajectory than the recorded position), the vehicle is controlled to return according to the original trajectory. In the case that it is determined that there is a change in the obstacle information and the change is not conducive to the passage of the vehicle (for example, the newly acquired obstacle position is closer to the recorded vehicle trajectory than the recorded position), the vehicle is controlled to adjust the return path or send a message to the driver. Obstacle information.

It can be understood that when the vehicle is "stuck" somewhere and cannot be driven out, the vehicle control device 50 can generate prompt information and present it to the driver in the form of voice or image or text, and if possible, The driver can get out of the car to move the obstacle; or, report the information that the vehicle is "stuck" somewhere to a remote server.

In the event that the determination in block 410 is NO, or, after passing block 412 , the vehicle has returned to the position at which it entered the narrow turn area, the method proceeds to block 414 .

In block 414, the vehicle control device 50 plans a path for the vehicle to guide the vehicle through the narrow turn area.

In one embodiment, the vehicle control device 50 may plan a driving route through the narrow turn area based on driver preferences, vehicle preferences, and real-time environmental conditions. The vehicle control device 50 can implement such planning by means of a machine learning model.

In another embodiment, a planned route set is stored at the vehicle end, and the planned route set includes a plurality of planned routes respectively corresponding to a scene. The vehicle control device 50 identifies the scene corresponding to the narrow turning area, selects a planned route corresponding to the identified scene from the planned route set, and guides the vehicle through the narrow turning area using the planned route.

In block 416, the vehicle control device 50 plans the steering and speed requests in real time, sends a steering request to the vehicle's steering system, and sends a speed request to the vehicle's stability system to guide the vehicle through the narrow turn area according to the planned path.

One aspect of the purpose of planning steering requests and speed requests in real time is to take into account the feelings of the occupants of the vehicle so that the vehicle does not experience stop-and-go, sharp shifting, sharp steering, and sharp braking. Considering only from machine thinking, it may be the most efficient or most suitable vehicle behavior for the planned path, but such a situation can cause discomfort to the driver and passenger, so avoid these by planning steering requests and speed requests in real time. A situation that can cause discomfort to the occupants.

In the planning of steering request and vehicle speed request, some or all of the following conditions (1) to (5) are satisfied, so that the mechanical system of the vehicle can better follow the planned route when it is electronically controlled to perform actions, Deviations can be corrected when they occur, rather than accumulating deviations in the direction of increasing deviations.

(1) The difference between the requested steering angle and the current body yaw angle is less than a predetermined angle difference threshold.

For example, the vehicle control device 50 obtains the current vehicle body yaw angle from the vehicle state information, determines the steering angle that the vehicle needs to perform at the current position based on the planned path, and adjusts the determined steering angle based on the angle difference threshold, so that the steering The difference between the requested steering angle sent by the system and the current body yaw angle is less than the angle difference threshold.

(2) The requested steering speed (ie, the speed of the angle change) is less than a predetermined steering speed threshold.

For example, determining the steering speed of the vehicle to realize the planned path based on the planned path and the current vehicle speed, and adjusting the determined steering speed based on the steering speed threshold, so that the rotational speed request sent to the steering system is less than the steering speed threshold, so that the vehicle implements the driving The route can be as close as possible to the planned path, while the steering speed does not exceed the steering speed threshold.

(3) The difference between the current request angle and the previous request angle is less than a predetermined continuous angle change threshold.

For example, based on the frequency with which the system sends steering commands, the difference between the last requested steering angle and the immediately following current requested steering angle should not be too large, so that vehicle behavior does not abruptly change due to the actions of the vehicle's mechanical components or its The actions of the stored energy components (eg, spring systems, hydraulic systems) are not suitable for performing sharp transitions.

(4) The acceleration of the requested vehicle in the direction of travel is less than a predetermined acceleration threshold.

For example, based on the planned path and the current vehicle speed, determine the acceleration of the vehicle to realize the planned path (this acceleration refers to the acceleration in the direction of the vehicle's travel. If it is accelerating, the acceleration is positive, if it is decelerating, the acceleration is negative. The acceleration can be the absolute value of the acceleration), and the determined acceleration is adjusted based on the acceleration threshold, so that the driving route implemented by the vehicle can conform to the planned route as much as possible, and the change of the vehicle speed will not be too sudden.

Additionally, the requested steering angle increment may be associated with vehicle speed. In one embodiment, the requested steering angle increment is matched to the vehicle speed rating such that the greater the requested steering angle, the lower the vehicle speed is controlled. For example, when the steering increment is less than 50 degrees, the vehicle speed can be controlled at 10km/h; when the steering increment is greater than 50 degrees and less than 100 degrees, the vehicle speed can be controlled at 5km/h; when the requested steering increment is greater than 100 degrees, the vehicle speed can be controlled at 5km/h. The vehicle speed can be controlled to be less than 3km/h.

It is understandable that although the planned path is executed, but the planned path fails, that is, the vehicle cannot pass the narrow turn anyway. Obstacles that cannot be moved, etc. At this time, the vehicle can be controlled to pull over to stop and report the situation to the remote server.

The present invention also provides a machine-readable storage medium storing executable instructions that, when executed, cause a machine to perform the method 400 as described above.

It will be understood that all operations in the above-described methods are merely exemplary, and the present invention is not limited to any operations in the methods or the order of these operations, but should cover all other equivalent transformations under the same or similar concepts .

It can be understood that the control units described above can all be implemented in various ways. For example, it may be implemented as hardware, software, or a combination thereof.

The vehicle control device may include one or more processors. These processors may be implemented using electronic hardware, computer software, or any combination thereof. Whether these processors are implemented as hardware or software will depend on the specific application and the overall design constraints imposed on the system. As an example, a processor, any portion of a processor, or any combination of processors presented in this disclosure may be implemented as a microprocessor, microcontroller, digital signal processor (DSP), field programmable gate array (FPGA) ), programmable logic devices (PLDs), state machines, gate logic, discrete hardware circuits, and other suitable processing components configured to perform the various functions described in this disclosure. The functions of a processor, any portion of a processor, or any combination of processors presented herein can be implemented as software executed by a microprocessor, microcontroller, DSP, or other suitable platform.

Software can be broadly viewed as representing instructions, sets of instructions, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, threads of execution, processes , functions, etc. Software may reside on computer readable media. Computer readable media may include, for example, memory, which may be, for example, magnetic storage devices (eg, hard disks, floppy disks, magnetic stripes), optical disks, smart cards, flash memory devices, random access memory (RAM), read only memory (ROM), memory Programmable ROM (PROM), Erasable PROM (EPROM), Electrically Erasable PROM (EEPROM), Register or Removable Disk. Although memory is shown as separate from the processor in the aspects presented herein, the memory may also be internal to the processor (eg, a cache or register).

The above description is provided to enable any person skilled in the art to practice the various aspects described herein. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects. Therefore, the claims are not intended to be limited to the aspects shown herein. All structural and functional equivalents to the elements of the described aspects of the invention that are known or come to be known to those skilled in the art are expressly incorporated herein by reference and are intended to be covered by the claims .

Claims (15)

1. A vehicle control apparatus for narrow turning mode, configured to:

receiving environmental information around a vehicle and vehicle state information;

turning on a narrow turning mode of autonomous driving when it is determined that a vehicle in a narrow turning area has a potential collision risk or an autonomous driving request of a driver is received, wherein the narrow turning is defined as a lane width less than 1.5 times a vehicle body width and a lane steering greater than 70 °; and

in the narrow turning mode, a planned path through the narrow turning area is determined, and in controlling the vehicle to realize the planned path based on the environmental information and the vehicle state information, the vehicle speed request and the steering request are dynamically adjusted so that part or all of the following items satisfy respective thresholds:

-a difference between the requested steering angle and the current body yaw angle;

-a requested steering speed;

-a difference between a current requested steering angle and a last requested steering angle;

-requested acceleration in the direction of travel of the vehicle.

2. The vehicle control apparatus according to claim 1, wherein the vehicle control apparatus is configured to dynamically adjust the steering request and the vehicle speed request such that the larger the requested steering angle, the smaller the requested vehicle speed.

3. The vehicle control apparatus according to any one of claims 1-2, wherein the vehicle control apparatus is further configured to:

when the vehicle is judged to collide with the moving object based on the planned path and the predicted track of the moving object, controlling the vehicle to decelerate or brake so as to avoid collision with the moving object; and/or

And when the static object appears on the planned path based on the planned path and the environment information, sending object reminding information to a driver or adjusting the planned path so as to avoid the static object.

4. The vehicle control apparatus according to any one of claims 1-3, wherein the vehicle control apparatus is configured to determine whether or not the following is satisfied, and determine that the vehicle has a potential collision risk when at least one of the following is satisfied:

-the distance between the vehicle and the potential collision object is less than a safe distance threshold;

-the presence of unfavorable driving conditions; and

the running behavior of the vehicle is reciprocated.

5. The vehicle control apparatus according to claim 4, wherein the distance between the vehicle and the potential collision object being less than the safe distance threshold includes at least one of:

the sum of the distances between the respective vehicle sides and the potential collision object is smaller than a bilateral distance threshold;

-the distance between the left or right side of the vehicle and the potential collision object is less than a unilateral distance threshold;

-determining that the vehicle will collide with the moving object based on the planned path and the predicted trajectory of the moving object.

6. The vehicle control apparatus according to claim 4 or 5, wherein the environment unfavorable for driving includes a weather environment unfavorable for driving and a lighting environment,

optionally, the driving adverse weather or lighting environment comprises at least one of:

-the presence of foggy, raining, snowing or hail weather;

insufficient light or intense reflection.

7. The vehicle control apparatus according to any one of claims 4 to 6, wherein the occurrence of reciprocation of the running behavior of the vehicle includes at least one of:

-the number of vehicle left and right turns alternating exceeds a predetermined number;

-the number of alternations of advancing the vehicle in one direction and backing it in an opposite direction exceeds a predetermined number.

8. The vehicle control apparatus of any of claims 1-7, wherein the vehicle control apparatus is further configured to determine the planned path by:

determining a scene of the narrow turning area based on the environment information, and selecting a planned path corresponding to the determined scene from a stored planned path set; or

The planned path is determined based on real-time environmental conditions, vehicle preferences and driver preferences, optionally as input parameters to a machine learning model, and a model output comprising the planned path is obtained.

9. The vehicle control apparatus according to any one of claims 1 to 8, wherein the vehicle control apparatus is further configured to:

after the narrow turning mode is started, judging whether the vehicle is in a position without enough passing space before determining the planned path;

and when the judgment result is positive, controlling the vehicle to retreat to the position at the beginning of entering the narrow turning area based on the vehicle running track record and the obstacle information record in the middle.

10. The vehicle control apparatus according to any one of claims 1 to 8, wherein the narrow turning area includes a path of an approximately quarter turn.

11. A vehicle control system for narrow turn mode, comprising:

sensors including an environment sensor for sensing an environment around the vehicle and generating environment information and a vehicle state sensor for sensing a vehicle state and generating vehicle state information; and

the vehicle control apparatus according to any one of claims 1 to 10, configured to be connected in communication with the sensor, and to start a narrow turning mode of autonomous driving when it is determined that the vehicle in a narrow turning area has a potential collision risk or receives an autonomous driving request from a driver, wherein the narrow turning is defined as a lane width less than 1.5 times a vehicle body width and a lane steering greater than 70 °; in the narrow turning mode, a planned path through the narrow turning area is determined, and in controlling the vehicle to realize the planned path based on the environmental information and the vehicle state information, the vehicle speed request and the steering request are dynamically adjusted so that part or all of the following items satisfy respective thresholds:

-a difference between the requested steering angle and the current body yaw angle.

-a requested steering speed;

-a difference between a current requested steering angle and a last requested steering angle;

-requested acceleration in the direction of travel of the vehicle.

12. The vehicle control system of claim 11, wherein the environmental sensor comprises a plurality of environmental sensors disposed about a periphery of the vehicle,

optionally, the plurality of environmental sensors comprise an ultrasonic sensor and a look-around camera;

further optionally, the ultrasonic sensors include a plurality of ultrasonic sensors disposed at front, rear, left and right sides of the vehicle, and the look-around camera includes a plurality of look-around cameras disposed at left and right sides of the vehicle.

13. The vehicle control system according to claim 11 or 12, wherein the number of sensors disposed on the left and right sides of the vehicle increases as the distance between the front and rear wheels of the vehicle increases.

14. A vehicle control method for narrow turning mode, optionally performed by a vehicle control apparatus according to any of claims 1-10 and/or a vehicle control system according to any of claims 11-13, the method comprising:

receiving environmental information around a vehicle and vehicle state information;

turning on a narrow turning mode of autonomous driving when it is determined that a vehicle in a narrow turning area has a potential collision risk or an autonomous driving request of a driver is received, wherein the narrow turning is defined as a lane width less than 1.5 times a vehicle body width and a lane steering greater than 70 °; and

in the narrow turning mode, a planned path through the narrow turning area is determined, and in controlling the vehicle to realize the planned path based on the environmental information and the vehicle state information, the vehicle speed request and the steering request are dynamically adjusted so that part or all of the following items satisfy respective thresholds:

-a difference between the requested steering angle and the current body yaw angle.

-requested steering speed;

-a difference between a current requested steering angle and a last requested steering angle;

-requested acceleration in the direction of travel of the vehicle.

15. A machine-readable storage medium storing executable instructions that, when executed, cause a machine to perform the method of claim 14.

Images