Vehicle obstacle avoidance detour method, related driving assistance method and electronic equipment

Abstract

The embodiment of the invention provides a vehicle obstacle avoidance detour method, a related driving assistance method and electronic equipment. The vehicle obstacle avoidance bypassing method according to the embodiment of the invention comprises the following steps: determining an obstacle closest to the current position of a vehicle in a plurality of interested obstacles in front of the vehicle as a target obstacle; performing clustering processing on the target obstacle and each of the one or more adjacent obstacles to determine whether the target obstacle and the adjacent obstacles are clustered into an obstacle group or not so as to obtain one or more obstacle groups; and for each obstacle group, deciding the detouring direction of the vehicle based on the position and the size of each obstacle in the obstacle group.

Description

Technical Field

[0001] The present invention generally relates to the technical field of vehicle driving assistance. Specifically, the present invention relates to a vehicle obstacle avoidance and detour method, as well as related driving assistance methods and electronic devices. Background Art

[0002] The obstacle avoidance and detour function of a vehicle is one of the core functions of a driving assistance system, which usually adopts an independent decision-making mechanism for a single obstacle. However, this discrete decision-making mode has obvious limitations. For example, during continuous obstacle avoidance, the system may frequently change the detour direction. For example, sometimes it decides to detour by borrowing the left lane, and sometimes it decides to detour by borrowing the right lane. This instability of decision-making will affect the driving smoothness of the vehicle, not only resulting in a decline in user experience, but also possibly causing potential safety hazards.

[0003] Therefore, it is desirable to propose a technical solution to solve the above problems in the existing obstacle avoidance and detour technologies. Summary of the Invention

[0004] In view of the above problems in the prior art, according to an embodiment of one aspect of the present invention, there is provided a method for obstacle avoidance and detour for a vehicle, which includes: determining the obstacle closest to the current position of the vehicle among a plurality of obstacles of interest in front of the vehicle as the target obstacle; performing clustering processing on each of the target obstacle and one or more adjacent obstacles thereof to determine whether to cluster the target obstacle and the adjacent obstacle into an obstacle group, thereby obtaining one or more obstacle groups; and for each obstacle group, making a decision on the detour direction of the vehicle based on the positions and sizes of the obstacles within the obstacle group.

[0005] According to an embodiment of another aspect of the present invention, there is provided a driving assistance method for a vehicle, which includes the above-mentioned obstacle avoidance and detour method.

[0006] According to an embodiment of still another aspect of the present invention, there is provided an electronic device, which includes one or more processors configured to execute the above-mentioned obstacle avoidance and detour method.

[0007] According to an embodiment of yet another aspect of the present invention, there is provided a computer program product, which includes instructions that, when executed by one or more processors, cause the one or more processors to execute the above-mentioned obstacle avoidance and detour method.

[0008] According to an embodiment of yet another aspect of the present invention, there is provided a machine-readable storage medium, which stores executable instructions that, when executed, cause one or more processors to execute the above-mentioned obstacle avoidance and detour method.

[0009] According to the vehicle obstacle avoidance and detour solution of the embodiments of the present invention, the passability of the vehicle with respect to adjacent obstacles is evaluated through clustering processing, and adjacent obstacles that the vehicle cannot pass through in the middle are clustered into a group to ensure the continuity and stability of the detour process. The solution of the embodiments of the present invention is particularly applicable to scenarios such as construction areas or temporary road occupations. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 is a schematic block diagram of an obstacle avoidance and detour system for a vehicle according to an embodiment of the present invention.

[0011] Figure 2 is a flowchart of an obstacle avoidance and detour method for a vehicle according to an embodiment of the present invention.

[0012] Figure 3 Schematically shows an exemplary application scenario of the system and method according to the embodiments of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0013] Next, the detailed embodiments of the present invention will be described with reference to the accompanying drawings.

[0014] Figure 1 Shows a system 100 for vehicle obstacle avoidance and detour according to an embodiment of the present invention. The system 100 is disposed on the vehicle and is thus an in-vehicle system. As Figure 1 shown, the system 100 includes a sensor unit 10, a control unit 20, and a communication unit 30.

[0015] The sensor unit 10 includes a variety of environmental perception devices (i.e., multiple in-vehicle environmental sensors) deployed on the vehicle. For example, the sensor unit 10 includes multi-modal sensing such as radar sensors, cameras, and lidar (LiDAR), which can form complementary environmental perception capabilities. Among them, the radar sensor can detect the distance and relative speed of obstacles through electromagnetic waves; the camera can capture high-resolution road scene images and provide rich semantic information; the lidar can generate accurate three-dimensional point cloud data through laser beam scanning.

[0016] The sensor unit 10 is used to collect lane information and obstacle information in the vehicle driving environment. The lane information includes relevant information about the current driving lane of the vehicle. For example, the geometric features of the current driving lane, which include, for example, the trajectory of the lane centerline, the lane width, and the road curvature, etc. The obstacle information includes a description of the obstacles detected in the vehicle driving environment. For example, it includes: the position of each obstacle (e.g., three-dimensional coordinates), size (e.g., the spatial occupancy range in three dimensions of length, width, and height), and category (e.g., vehicle, roadblock, etc.).

[0017] According to an embodiment of the present invention, the main focus is on static obstacles. Static obstacles include immovable obstacles (such as curbs, bollards, buildings, roadblocks, traffic cones, etc.), as well as movable obstacles that are temporarily stationary (such as parked vehicles). Therefore, in the embodiments of the present invention, obstacles, or detected obstacles, or obstacles of interest all refer to static obstacles.

[0018] The control unit 20 is used to implement the vehicle obstacle avoidance and detour method according to the embodiments of the present invention (the specific implementation of this method will be described in detail in the method section below). In one embodiment, the control unit 20 can be implemented as including a memory and a processor, wherein the memory stores executable instructions that, when executed by the processor, implement the vehicle obstacle avoidance and detour method according to the embodiments of the present invention.

[0019] The control unit 20 can be implemented in software, hardware (such as a customized integrated circuit), or a combination of software and hardware.

[0020] In one embodiment, the control unit 20 can be deployed in one of the following ways: 1) integrated into the vehicle's Advanced Driver Assistance System Controller (ADAS ECU); 2) deployed in an on-vehicle chip (such as an autonomous driving dedicated SoC); 3) deployed in the Vehicle Controller (VCU); 4) deployed in a domain controller (such as a chassis domain or an autonomous driving domain controller).

[0021] In another embodiment, the control unit 20 can be divided into multiple functional modules according to functions, and these functional modules can be deployed in multiple ECUs of the vehicle using a distributed architecture design. This distributed deployment method can improve the scalability of functions and make full use of the vehicle's electronic and electrical architecture resources.

[0022] The communication unit 30 enables the vehicle to interact with other traffic objects in the traffic scenario through V2X (Vehicle-to-Everything) communication. For example, the communication unit 30 can interact with surrounding vehicles, roadside facilities, pedestrians, and cloud servers respectively to form a vehicle-road collaborative communication ecosystem.

[0023] Through this high-reliability and low-latency V2X communication mechanism, when multiple vehicles in the traffic scenario are equipped with the obstacle avoidance and detour system according to the embodiments of the present invention, collaborative decision-making between vehicles can be achieved. For example, a detour priority can be assigned to each vehicle. This collaborative mechanism can not only effectively avoid conflicts in obstacle avoidance paths between vehicles, but also optimize the operation efficiency of the overall traffic flow, improve the success rate of obstacle avoidance and road utilization rate under complex road conditions.

[0024] Figure 2The method 200 for obstacle avoidance and detour of a vehicle according to an embodiment of the present invention is shown. The method 200 may be executed by the control unit 20 described above. Figure 3 An exemplary driving environment of the vehicle V is shown. The vehicle V is configured with the system 100 as described above. The current driving lane of the vehicle V is represented by R, that is, the current driving lane of the vehicle V is R. Below, referring to Figure 2 and Figure 3 , taking the control unit 20 executing the method 200 as an example, the specific implementation manner of the method 200 will be introduced.

[0025] In block 202, the control unit 20 obtains lane information and obstacle information in the driving environment of the vehicle V from the sensor unit 10. The lane information includes lane information about the current driving lane of the vehicle V, for example, the center line and lane width of the current driving lane. The obstacle information includes information about each detected obstacle among multiple detected obstacles within the sensing range of the sensor unit 10 (for example, the comprehensive sensing range of multiple sensors in the sensor unit 10), such as the position and size of each detected obstacle.

[0026] In block 204, the control unit 20 determines multiple interested obstacles located within the region of interest from the multiple detected obstacles, and determines the position and size of each interested obstacle from the obtained obstacle information. The region of interest refers to the region covered by a first predetermined distance in front of the vehicle V and a second predetermined distance behind on the current driving lane. Therefore, the interested obstacles include obstacles within a certain distance range in front of and behind the vehicle V on the current driving lane.

[0027] In one embodiment, the region of interest is defined by the following conditions: 1) a first predetermined distance in front of the vehicle V; 2) a second predetermined distance behind the vehicle V; 3) the boundary line of the current driving lane. The first predetermined distance in front of the vehicle is calculated by multiplying the current vehicle speed by a preset multiple of the TTC (Time to Collision). The preset multiple is preset, for example, determined in advance through real vehicle tests and / or model calculations. The second predetermined distance behind the vehicle is a preset fixed value. Therefore, the width of the region of interest is the same as the width of the current lane, its forward extension distance is related to the current vehicle speed and TTC, and the backward extension distance is a fixed value.

[0028] Here, the first predetermined distance refers to the distance starting from the vehicle head and extending longitudinally along the vehicle body in the vehicle driving direction. The second predetermined distance refers to the distance starting from the vehicle tail and extending longitudinally in the direction opposite to the vehicle driving direction.

[0029] Referring to Figure 3, the region of interest (ROI: Region of Interest) is shown by a dashed box. For example, according to the obstacle information received from the sensor unit 10, obstacles 1-5 are detected in the vehicle driving environment, where obstacles 1-3 fall within the region of interest, that is, obstacles 1-3 will be determined as the obstacles of interest by the control unit 20.

[0030] In block 206, the control unit 20 marks these obstacles based on the relative distances between the current position of the vehicle V (i.e., the current position of the vehicle itself) and each obstacle of interest, so as to ensure that all obstacles of interest can be clustered without omission according to the distance in the subsequent clustering process. For example, the control unit 20 sorts the obstacles of interest in the order from the nearest to the farthest from the vehicle itself, and assigns a label corresponding to its sorting position to each obstacle of interest.

[0031] In block 208, the control unit 20 sequentially performs clustering processing on each obstacle of interest in the order from the nearest to the farthest according to the relative distances between each obstacle of interest and the vehicle V, to determine whether the obstacle needs to be clustered with its adjacent obstacles into an obstacle group. In the embodiment of the present invention, an obstacle group refers to a set of multiple obstacles that will be regarded as a whole when the vehicle itself (vehicle V) performs obstacle avoidance and detouring.

[0032] The control unit 20 first takes the obstacle of interest closest to the current position of the vehicle itself (vehicle V) as the target obstacle, and performs clustering processing on the target obstacle and one or more of its adjacent obstacles, thereby obtaining one or more obstacle groups. Hereinafter, embodiments of the clustering processing will be introduced in detail.

[0033] In one embodiment, referring to block 2081, the control unit 20 determines whether to cluster them into an obstacle group based on the straight-line distances between the target obstacle and each of one or more of its adjacent obstacles. Specifically, for each of the target obstacle and one or more of its adjacent obstacles, the control unit 20 determines whether the straight-line distance between the target obstacle and the adjacent obstacle is less than or equal to the straight-line distance threshold; if the judgment result is affirmative, it is determined that the target obstacle and the adjacent obstacle are clustered into an obstacle group. And if the straight-line distances between the target obstacle and multiple adjacent obstacles are all less than or equal to the straight-line distance threshold, these obstacles are jointly clustered into an obstacle group.

[0034] The straight-line distance threshold is pre-calibrated and stored in the control unit 20. For example, according to the body width of the vehicle (i.e., the vehicle itself) equipped with the system 100 (such as a truck, a bus, a private car, etc.), the straight-line distance threshold is pre-calibrated to the body width corresponding to the vehicle type.

[0035] In another embodiment, referring to block 2082, the control unit 20 determines whether to cluster a target obstacle and each of one or more adjacent obstacles into an obstacle group based on the lateral distance difference and the longitudinal distance difference between the target obstacle and each of the one or more adjacent obstacles. Specifically, for each of the target obstacle and one or more adjacent obstacles, the control unit 20 determines whether the lateral distance difference between the target obstacle and the adjacent obstacle is greater than the lateral distance difference threshold; determines whether the longitudinal distance difference between the target obstacle and the adjacent obstacle is greater than the longitudinal distance difference threshold; when the results of the above two determinations are both affirmative, it indicates that there is a sufficiently large space between the target obstacle and the adjacent obstacle for the vehicle V to pass through. At this time, the control unit 20 determines not to cluster the target obstacle and the adjacent obstacle into a group.

[0036] The lateral distance difference refers to the distance difference between the target obstacle and the adjacent obstacle in the direction perpendicular to the lane center line L, where the lane center line L is the center line of the vehicle driving lane R. The longitudinal distance difference refers to the distance difference between the target obstacle and the adjacent obstacle in the direction parallel to the lane center line L.

[0037] The lateral distance difference threshold and the longitudinal distance difference threshold are pre-calibrated and stored in the control unit 20. For example, the lateral distance difference threshold can be calibrated based on the vehicle body width. The longitudinal distance difference threshold can be calibrated based on the vehicle body length. In one embodiment, the control unit 20 can dynamically adjust the lateral distance difference threshold and the longitudinal distance difference threshold according to the current vehicle speed of the vehicle V to ensure the accuracy and safety of the clustering judgment criteria at different vehicle speeds. A specific implementation manner of dynamically adjusting the lateral distance difference threshold and the longitudinal distance difference threshold is introduced below.

[0038] In one implementation manner, the control unit 20 dynamically adjusts the lateral distance difference threshold according to the following formula (1):

[0039] Dlat_th = klat × Wvehicle × (1 + α × v) (1)

[0040] Where: Dlat_th is the lateral distance difference threshold;

[0041] klat is the first preset multiple, representing the preset multiple of the vehicle body width. The first preset multiple value is, for example, 1.2;

[0042] Wvehicle is the vehicle body width of the vehicle V;

[0043] α is the preset first vehicle speed adjustment coefficient (for example, α = 0.01);

[0044] v is the current vehicle speed of the vehicle V.

[0045] For example, according to the above formula (1), when the body width of vehicle V is 2 meters and the current vehicle speed is 10 m / s (36 km / h), the lateral distance difference threshold is 2.64 meters.

[0046] The control unit 20 dynamically adjusts the longitudinal distance difference threshold according to the following formula (2):

[0047] Dlong_th = klong × Lvehicle × (1 + β × v) (2)

[0048] Where: Dlong_th is the longitudinal distance difference threshold;

[0049] klong is the second preset multiple, representing the preset multiple of the vehicle body length, and the second preset multiple value is, for example, 1.5;

[0050] Lvehicle is the vehicle body length of vehicle V;

[0051] β is a predetermined second vehicle speed adjustment coefficient (for example, β = 0.015);

[0052] v is the current vehicle speed of vehicle V.

[0053] For example, according to the above formula (2), when the vehicle body length of vehicle V is 5 meters and the current vehicle speed is 10 m / s (36 km / h), the longitudinal distance difference threshold is 8.625 meters.

[0054] The first and second preset multiples and the first and second vehicle speed adjustment coefficients are all pre-calibrated based on real vehicle tests or model calculations.

[0055] Setting such dynamic adjustment can achieve: when the vehicle speed increases, the lateral distance difference threshold and the longitudinal distance difference threshold increase accordingly to ensure that the vehicle has a larger safety space for obstacle avoidance and detouring when driving at high speed; when the vehicle speed decreases, the lateral distance difference threshold and the longitudinal distance difference threshold will decrease accordingly to meet the obstacle avoidance requirements when driving at low speed. For example, in a high-speed scenario, when vehicle V is traveling at 20 m / s (72 km / h), the lateral distance difference threshold and the longitudinal distance difference threshold will increase to ensure that the vehicle has enough space for safe detouring at high speed. In a low-speed scenario, when vehicle V is traveling at 5 m / s (18 km / h), the lateral distance difference threshold and the longitudinal distance difference threshold will be appropriately reduced to meet the obstacle avoidance requirements at low speed.

[0056] In yet another embodiment, referring to block 2083, when 1) the straight-line distance between the target obstacle and an adjacent obstacle is greater than the straight-line distance threshold, and 2) the lateral distance difference is less than or equal to the lateral distance difference threshold or the longitudinal distance difference is less than or equal to the longitudinal distance difference threshold, the control unit 20 determines whether to cluster the target obstacle and the adjacent obstacle into an obstacle group based on the current body attitude of the vehicle. This embodiment can be regarded as an intermediate case between blocks 2081 and 2082, that is, when the vehicle can barely pass between the target obstacle and an adjacent obstacle, the clustering process is further performed based on the body attitude.

[0057] In one embodiment, the control unit 20 performs the following operations: Based on the current body attitude, predict whether the vehicle can pass through the gap between the target obstacle and the adjacent obstacle within its maximum steering range; if the prediction result is yes, the control unit 20 does not cluster the target obstacle and the adjacent obstacle into a group; if the prediction result is no, the control unit 20 clusters the target obstacle and the adjacent obstacle into a group. The maximum steering range includes the range of the turning radius and the range of the steering angle that the vehicle's steering system can achieve.

[0058] According to an embodiment of the present invention, the control unit 20 first takes the obstacle closest to the vehicle as the target obstacle and performs the clustering process of blocks 2081 - 2083. It should be noted that the present invention does not limit the execution order of blocks 2081, 2082, and 2083. Specifically, blocks 2081, 2082, and 2083 can all run independently, and there is no mutual constraint relationship between them. For example, according to an embodiment of the present invention, there are cases where only one of blocks 2081 - 2083 is executed, cases where two of them are executed, and cases where all three are executed. Subsequently, the control unit 20 will sequentially select the obstacle with the second-closest distance as the new target obstacle, and similarly, perform the clustering process of blocks 2081 - 2083 for the new target obstacle until the clustering process for all interested obstacles is completed.

[0059] In block 210, the control unit 20 makes a detour direction decision for each obstacle group respectively. That is, it determines whether the vehicle detours by borrowing the road from the left or right side of the obstacle group.

[0060] In one embodiment, the control unit 20 first determines the outer contour of each obstacle group. For example, according to the position and size information of each obstacle within the group, the minimum geometric shape of the group of obstacles is calculated as its outer contour. Then, the control unit 20 calculates the boundary distances. For example, the horizontal distance between the leftmost point of the outer contour and the left boundary line of the current driving lane is calculated as the left spacing; and the horizontal distance between the rightmost point of the outer contour and the right boundary line of the current driving lane is calculated as the right spacing. Then, the control unit 20 compares the left spacing and the right spacing; if the comparison result is that the left spacing is greater than the right spacing, it is determined to bypass from the left side of the obstacle group; if the comparison result is that the left spacing is less than the right spacing, it is determined to bypass from the right side of the obstacle group. Here, the leftmost point of the outer contour is the leftmost point of the outer contour of the obstacle group in the direction perpendicular to the center line of the lane; the rightmost point of the outer contour is the rightmost point of the outer contour of the obstacle group in the direction perpendicular to the center line of the lane.

[0061] Here, the minimum circumscribed geometric shape of multiple obstacles refers to the minimum geometric shape that can completely enclose the multiple obstacles. For example, the minimum circumscribed rectangle, the minimum circumscribed circle, or a polygon.

[0062] In addition, if the comparison result is that the left spacing is exactly equal to the right spacing, the control unit 20 can adopt one of the following strategies to decide the bypass direction. 1) There is a default bypass direction preset in the control unit 20. If the left spacing is exactly equal to the right spacing, the control unit 20 automatically selects the default bypass direction. The advantage of this strategy is fast decision-making speed. 2) The control unit 20 decides the bypass direction with relatively higher safety according to the vehicle driving environment information. For example, comprehensively considering oncoming vehicles, pedestrians, traffic signs, etc. on the left and right sides, the side with relatively higher safety is decided as the bypass direction. The advantage of this strategy is intelligent and gives priority to safety. 3) A message indicating that the left spacing is exactly equal to the right spacing is provided to the vehicle user (e.g., the vehicle driver) through the human-machine interface (HMI) on the vehicle, and the user is prompted to select the bypass direction. The control unit 20 decides the bypass direction as the direction selected by the user. The advantage of this strategy is to give the vehicle user more control and improve the user experience.

[0063] According to an embodiment of the present invention, after deciding the bypass direction, the control unit 20 generates a bypass instruction including the bypass direction and sends the bypass instruction to the steering system of the vehicle so that the steering system performs the bypass control according to the bypass instruction. During the process of the steering system executing the bypass instruction, the control unit 20 can monitor the bypass state of the vehicle in real time. The bypass state may include the following stages: 1) Bypass start: The vehicle starts to borrow a lane according to the bypass direction; 2) Bypassing: The vehicle is driving on the bypass path on the left or right side of the obstacle group; 3) Bypass end: The vehicle completes the bypass and returns to near the center line of the current driving lane.

[0064] According to an embodiment of the present invention, there is also provided a strategy for coordinating the obstacle avoidance and detour sequence of multiple vehicles in a traffic environment by means of vehicle-to-vehicle (V2V) communication. In a traffic environment, multiple vehicles are all equipped with an obstacle avoidance and detour system according to an embodiment of the present invention. These vehicles each make a decision on the detour direction, which may lead to conflicts in lane borrowing. For example, vehicle V may decide to detour to the right and needs to borrow the adjacent lane on the right side of its current driving lane; while vehicle V' (not shown) may decide to detour to the left and needs to borrow the adjacent lane on the left side of its current driving lane. If these two adjacent lanes are actually the same lane, a lane borrowing conflict will occur. In this case, the conflict can be resolved by determining the right-of-way priorities of vehicles V and V', and the vehicle with a higher right-of-way priority will have the right to detour first. Through V2V communication via the communication units on each vehicle, the vehicle with a higher detour priority passes first, and then the vehicle with a lower right-of-way priority passes.

[0065] In one implementation, the right-of-way priorities are determined in sequence according to the following factors: (1) vehicle type; (2) type of the current driving lane; (3) timestamp. First, the right-of-way priority is determined according to the vehicle type. For example, an ambulance or a fire truck, as an emergency vehicle, has a higher right-of-way than a private car. If the types of two vehicles are the same, the right-of-way priority is determined according to the type of the current driving lane. For example, the right-of-way priority of a vehicle driving on the main road is higher than that of a vehicle driving on a branch road. If both the vehicle type and the type of the current driving lane are the same, the right-of-way priority is determined according to the timestamp when the obstacle is detected. For example, the vehicle that detects the obstacle first has a higher right-of-way priority.

[0066] According to an embodiment of the present invention, there is also provided a driving assistance method for a vehicle, which includes the above-mentioned obstacle avoidance and detour method. This driving assistance method can be applied to the adaptive cruise control (ACC) or traffic jam assistance (TJA) function module / system of the vehicle. For example, the function implemented by the obstacle avoidance and detour method can be used as an ACC sub-function module (for example, as an obstacle avoidance decision sub-module of the ACC system), or, as a sub-function module of TJA (for example, working in cooperation with the lateral control module of TJA). For another example, the software module based on the obstacle avoidance and detour method can perform data interaction with the ACC or TJA software module through program calls (for example, perform data interaction with the ACC or TJA system through a predefined application programming interface).

[0067] According to an embodiment of the present invention, there is also provided an electronic device, which includes one or more processors for executing the method 200 as described above. This electronic device can be set / deployed in vehicle components. For example, this electronic device is set in the domain controller, body controller, or front view camera of the vehicle.

[0068] According to an embodiment of the present invention, there is also provided a computer program product, which includes instructions that, when executed by one or more processors, cause the one or more processors to execute the method 200 as described above.

[0069] According to an embodiment of the present invention, there is also provided a computer-readable storage medium. The computer-readable storage medium includes instructions that, when executed, cause one or more processors to execute the method 200 as described above.

[0070] It should be understood that a processor can be implemented using electronic hardware, computer software, or any combination thereof. Whether a processor is implemented as hardware or software will depend on the particular application and the overall design constraints imposed on the system. As an example, a processor, any part of a processor, or any combination of processors given in the present invention can be implemented as a microprocessor, a microcontroller, a digital signal processor (DSP), a field-programmable gate array (FPGA), a programmable logic device (PLD), a state machine, gate logic, discrete hardware circuits, and other suitable processing components configured to perform the various functions described in the present invention. The functions of a processor, any part of a processor, or any combination of processors given in the present invention can be implemented as software executed by a microprocessor, a microcontroller, a DSP, or other suitable platform.

[0071] Software should be widely regarded as representing instructions, instruction sets, code, code segments, program code, programs, subroutines, software modules, applications, software applications, software packages, routines, subroutines, objects, running threads, processes, functions, etc. Software can reside in a computer-readable medium. A computer-readable medium can include, for example, a memory, and the memory can be, for example, a magnetic storage device (such as a hard disk, a floppy disk, a magnetic stripe), an optical disk, a smart card, a flash memory device, a random access memory (RAM), a read-only memory (ROM), a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), a register, or a removable disk. Although the memory is shown as being separate from the processor in many aspects given in the present invention, the memory can also be located inside the processor (such as a cache or a register).

[0072] Although some embodiments have been described above, these embodiments are given only by way of example and are not intended to limit the scope of the present invention. The appended claims and their equivalent replacements are intended to cover all modifications, substitutions, and changes made within the scope and spirit of the present invention.

Claims

1. A method for avoiding obstacles for a vehicle, comprising: The obstacle closest to the current position of the vehicle among the multiple obstacles of interest in front of the vehicle is determined as the target obstacle; Performing clustering processing on each of the target obstacle and one or more adjacent obstacles thereof to determine whether to cluster the target obstacle and the adjacent obstacles into one obstacle group, thereby obtaining one or more obstacle groups; as well as For each obstacle group, the detour direction of the vehicle is determined based on the position and size of each obstacle in the obstacle group.

2. The obstacle avoidance method according to claim 1, wherein: The clustering process includes: for each of the target obstacle and one or more adjacent obstacles, Determine whether the straight-line distance between the target obstacle and the adjacent obstacle is less than or equal to a straight-line distance threshold; and If the judgment result is positive, the target obstacle and the adjacent obstacles are clustered into one obstacle group.

3. The obstacle avoidance method according to claim 1, wherein: The clustering process includes: for each of the target obstacle and one or more adjacent obstacles, Determine whether the lateral distance difference between the target obstacle and the adjacent obstacle is greater than a lateral distance difference threshold, wherein the lateral distance difference refers to the distance difference between the target obstacle and the adjacent obstacle in a direction perpendicular to the centerline of the lane in which the vehicle is currently traveling; Determining whether a longitudinal distance difference between the target obstacle and the adjacent obstacle is greater than a longitudinal distance difference threshold, wherein the longitudinal distance difference refers to a distance difference between the target obstacle and the adjacent obstacle in a direction parallel to the centerline of the lane; and When the results of the above two judgments are both affirmative, the target obstacle and the adjacent obstacle are not clustered into one group.

4. The obstacle avoidance method according to claim 3, further comprising: The lateral distance difference threshold and the longitudinal distance difference threshold are dynamically adjusted according to the current vehicle speed, wherein both the lateral distance difference threshold and the longitudinal distance difference threshold increase with the increase of the current vehicle speed.

5. The obstacle avoidance method according to claim 1, wherein: The clustering process includes: for each of the target obstacle and one or more adjacent obstacles, When the straight-line distance between the target obstacle and the adjacent obstacle is greater than the straight-line distance threshold, and the lateral distance difference and the longitudinal distance difference between the target obstacle and the adjacent obstacle are respectively less than the lateral distance difference threshold and the longitudinal distance difference threshold, predict whether the vehicle can pass between the target obstacle and the adjacent obstacle within its maximum turning range under the current vehicle body posture; If the judgment result is positive, the target obstacle and the adjacent obstacle are clustered into an obstacle group. The maximum steering range includes the vehicle's turning radius range and steering angle range.

6. The obstacle avoidance method according to claim 1, further comprising: Acquiring lane information and obstacle information in the vehicle driving environment; wherein the lane information includes the lane width and lane centerline of the lane currently being driven by the vehicle, and the obstacle information includes the position and size of each obstacle among a plurality of obstacles detected in the vehicle driving environment; and The plurality of obstacles of interest located within the region of interest are selected from the plurality of obstacles detected.

7. The obstacle avoidance method according to claim 6, wherein: The region of interest refers to an area on the current driving lane that is covered by a first predetermined distance in front of the vehicle and a second predetermined distance behind the vehicle. The first predetermined distance is associated with the current vehicle speed and the collision time TTC, and the second predetermined distance is a preset fixed value.

8. The obstacle avoidance method according to claim 1, wherein: Decision making on detour direction includes: for each set of obstacles, According to the position and size information of each obstacle in the group, the minimum circumscribed geometric shape of the obstacle group is calculated as its outer contour; Calculate the horizontal distance between the leftmost point of the outer contour and the left boundary line of the current driving lane as the left distance, where the leftmost point of the outer contour is the leftmost point of the outer contour in the direction perpendicular to the center line of the lane; Calculate the horizontal distance between the rightmost point of the outer contour and the right boundary line of the current driving lane as the right distance, where the rightmost point of the outer contour is the rightmost point of the outer contour in the direction perpendicular to the center line of the lane; If the left side distance is greater than the right side distance, it is determined to bypass the obstacle group from the left side; and If the left distance is smaller than the right distance, it is determined to be bypassing from the right side of the obstacle group.

9. The obstacle avoidance method according to claim 1, further comprising: When the detour direction decided by the vehicle conflicts with the detour directions decided by other vehicles in the driving environment on the borrowed lane, the detour order of the vehicle and other vehicles is determined according to their road right priorities.

10. A driving assistance method for a vehicle, comprising the obstacle avoidance method according to any one of claims 1 to 9.

11. The driving assistance method according to claim 10, wherein: The driving assistance method is applicable to an adaptive cruise control (ACC) or a traffic jam assist (TJA) of a vehicle.

12. An electronic device, comprising one or more processors, configured to execute the obstacle avoidance method according to any one of claims 1 to 9.

13. The electronic device as claimed in claim 12, wherein: The electronic device is arranged in a vehicle component, and optionally, the vehicle component is a domain controller, a body controller, or a front-view camera.

14. A computer program product comprising instructions, which, when executed by one or more processors, cause the one or more processors to perform the obstacle avoidance method according to any one of claims 1 to 9.

15. A machine-readable storage medium storing executable instructions, which, when executed, cause one or more processors to perform the obstacle avoidance method according to any one of claims 1 to 9.

Images