Vehicle passing method, electronic device and program product

Abstract

The invention provides a vehicle passing method, electronic equipment and a program product, and relates to the technical field of intelligent driving. The method comprises the steps that under the scene that a self vehicle meets an opposite vehicle and needs to reverse to give way, the behavior of the opposite vehicle is monitored within the observation duration of the self vehicle, the reverse to give way vehicle is determined according to the behavior of the opposite vehicle, and the reverse to give way vehicle is the self vehicle or the opposite vehicle; and in the reversing and yielding process of the reversing and yielding vehicle, forward passing planning is conducted on the own vehicle at least once, and when the planning result is that forward passing of the own vehicle can be contained, forward passing of the own vehicle is controlled. The method and the device are used for improving the vehicle passing efficiency under the condition that two vehicles meet and need backing to give way.

Description

Technical Field

[0001] This disclosure relates to the field of intelligent driving technology, specifically to a vehicle passage method, electronic device, and software product. Background Technology

[0002] In the wave of automotive intelligence, autonomous driving technology is developing at an unprecedented pace, receiving widespread attention and in-depth exploration from theoretical research to engineering practice. As autonomous driving technology continues to advance from low-level to mid-to-high-level, the complex scenarios and tasks it needs to handle are becoming increasingly diverse, with reversing to yield to pedestrians being one of them.

[0003] like Figure 1 The image shows a scenario where a vehicle needs to reverse to yield to another vehicle. When the longitudinal distance between the two oncoming vehicles is too close, even turning the steering wheel to its dynamic limits will not allow for lateral clearance. Figure 2 The image shows a second scenario where reversing is required to yield to another vehicle. The passage width is less than the combined width of the two vehicles, making it impossible for them to pass side-by-side. Both scenarios trigger reversing to yield. The rationality and efficiency of the triggering logic and decision-making process directly affect the safety, comfort, and traffic flow efficiency of the reversing process. Defects in the triggering logic and decision-making process can lead to minor collisions or scrapes, or discomfort due to frequent braking and steering; in severe cases, it can cause localized traffic congestion or even a chain reaction of accidents. Summary of the Invention

[0004] In view of this, embodiments of the present disclosure provide a vehicle passage method, electronic device, and program product to improve vehicle passage efficiency in scenarios where two vehicles meet and need to reverse to yield.

[0005] Firstly, this disclosure provides a method for vehicle passage, including:

[0006] In a scenario where a vehicle encounters an oncoming vehicle and needs to reverse to yield, the behavior of the oncoming vehicle is monitored during the observation period of the vehicle. The vehicle to reverse to yield is determined based on the behavior of the oncoming vehicle. The vehicle to reverse to yield is either the vehicle or the oncoming vehicle.

[0007] During the process of the vehicle reversing to yield, the vehicle's forward passage is planned at least once, and when the planning result indicates that the vehicle can accommodate the vehicle's forward passage, the vehicle's forward passage is controlled.

[0008] Secondly, this disclosure provides an electronic device, including:

[0009] At least one processor; and

[0010] A memory communicatively connected to the at least one processor; wherein,

[0011] The memory stores at least one computer program that can be executed by the at least one processor, the at least one computer program being executed by the at least one processor to enable the at least one processor to perform the vehicle passage method as described in the first aspect.

[0012] Thirdly, this disclosure provides a computer program product, which includes a computer program that, when run in a processor, implements the vehicle passage method described in the first aspect.

[0013] The embodiments provided in this disclosure, in scenarios where a vehicle encounters an oncoming vehicle and needs to reverse to yield, monitor the behavior of the oncoming vehicle within the observation period of the vehicle, and determine the vehicle to reverse and yield based on the behavior of the oncoming vehicle. The reversing vehicle to yield is either the vehicle itself or the oncoming vehicle. During the reversing process, forward traffic planning is performed on the vehicle at least once, and if the planning result indicates that the vehicle can accommodate forward traffic, the vehicle is controlled to move forward. This method, by monitoring the behavior of oncoming vehicles within a short observation period and determining the vehicle to reverse and yield, avoids blind reversing, excessive reversing, and standoffs, laying the foundation for improved traffic efficiency. Furthermore, repeatedly attempting forward traffic planning during the reversing process allows for the early detection of passable lanes, further improving traffic efficiency. Attached Figure Description

[0014] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0015] Figure 1 The diagram shows a scenario where a vehicle needs to reverse to yield in the relevant technology.

[0016] Figure 2 The diagram shown is a schematic representation of a second scenario in the relevant technology where vehicles need to reverse to yield the right-of-way.

[0017] Figure 3 The diagram shown is a schematic diagram of a vehicle passage method in a reversing yielding scenario according to an embodiment of this disclosure;

[0018] Figure 4a The diagram shows the key points of the reversing path in a scenario where the distance is too close, according to an embodiment of this disclosure.

[0019] Figure 4bThe diagram shown is a schematic representation of the key points of the reversing path in a narrow passage scenario according to an embodiment of this disclosure.

[0020] Figure 4c The diagram shown is a schematic representation of the reversing path in a scenario where the distance is too close, according to an embodiment of this disclosure.

[0021] Figure 4d The diagram shown is a schematic diagram of the reversing path in a narrow passage scenario according to an embodiment of this disclosure;

[0022] Figure 5 The diagram shown is a schematic representation of the process of a vehicle reversing to yield to another vehicle in an embodiment of this disclosure.

[0023] Figure 6 The diagram shown is a block diagram of a vehicle passage device according to an embodiment of this disclosure;

[0024] Figure 7 The diagram shown is a structural schematic of an electronic device in an embodiment of this disclosure. Detailed Implementation

[0025] The technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0026] Where there is no conflict, the various embodiments of this disclosure and the features thereof in the embodiments may be combined with each other.

[0027] As used herein, the term “and / or” includes any and all combinations of one or more related enumerated entries.

[0028] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. As used herein, the singular forms “a” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that when the terms “comprising” and / or “made of” are used in this specification, the presence of the stated feature, integral, step, operation, element, and / or component is specified, but the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof is not excluded. Words such as “connected” or “linked” are not limited to physical or mechanical connections but can include electrical connections, whether direct or indirect.

[0029] Unless otherwise specified, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and this disclosure, and will not be interpreted as having an idealized or overly formal meaning, unless expressly so defined herein.

[0030] Overview

[0031] In related technologies, the two mainstream solutions for reversing to yield to pedestrians are:

[0032] 1. Goal-oriented path search scheme

[0033] Relying on an environmental perception system, the system searches for target points in areas such as the right rear of the vehicle that meet the conditions for oncoming traffic to pass, requiring that the target points be connected to the current lane. Using path planning algorithms such as A* algorithm and fast search random tree, a reversing trajectory from the vehicle's current position to the target point is constructed. This trajectory includes segmented control of longitudinal speed (acceleration-constant speed-deceleration) and a lateral steering strategy. After planning, the autonomous driving system executes reversing along this trajectory until it reaches the target point and completes the yielding maneuver.

[0034] This method requires searching the entire area behind the vehicle, such as a 108° sector, to find space that allows oncoming vehicles to pass. The search is time-consuming and computationally intensive, which cannot meet the real-time requirements of autonomous driving.

[0035] 2. Reversing along the original route to find a parking space and yield to other vehicles.

[0036] After the vehicle triggers the reverse yielding maneuver, it defaults to recalling its historical driving trajectory and reverses along the "path it came from." Simultaneously, it continuously senses and scans the surrounding environment to identify roadside parking spaces. If an available parking space is found, it initiates parallel parking, angled parking, or other parking procedures. After parking, it waits for oncoming traffic to pass before proceeding forward to resume traffic flow.

[0037] This method relies on available parking spaces near the original road. In scenarios without standardized parking spaces, such as narrow rural roads or curves, the system is prone to getting stuck in an ineffective reversing loop, causing delays in the yielding process and significantly reducing traffic efficiency. It cannot adapt to diverse and complex road environments. Furthermore, it requires invoking complex parking processes such as parallel parking and angled parking. The parking process involves precise location recognition, multi-stage trajectory planning, and highly dynamic control, increasing the system's computational burden and time cost. If parking fails, it is necessary to reverse again and search for parking spaces again, further exacerbating the yielding time and collision risk, resulting in poor process robustness.

[0038] In summary, the relevant technologies simplify reversing to yielding as a one-way decision-making behavior of the vehicle itself, lacking the interactive logic of actively waiting for oncoming vehicles to reverse and yield. They do not consider scenarios where oncoming vehicles have the intention to reverse or cooperate in yielding. If the vehicle blindly reverses, it may result in a situation where "the oncoming vehicle has actively yielded, but the vehicle continues to reverse, causing a waste of resources," failing to achieve efficient collaborative yielding between the two vehicles and impacting overall traffic efficiency.

[0039] Exemplary methods

[0040] To improve the passage efficiency of both vehicles meeting, this disclosure provides a vehicle passage method for scenarios where a vehicle encounters an oncoming vehicle and needs to reverse to yield.

[0041] The vehicle passage method provided in this disclosure can be applied to the main controller of a vehicle, or to other terminals, servers, etc., capable of communicating with the vehicle and / or sensors installed on the vehicle. Here, a detailed description is given using the execution of the vehicle passage method provided in this disclosure embodiment for a self-owned vehicle as an example.

[0042] The vehicle passage method provided in this disclosure embodiment, such as Figure 3 As shown, the main steps include:

[0043] Step 301: In a scenario where the vehicle encounters an oncoming vehicle and needs to reverse to yield, monitor the behavior of the oncoming vehicle within the observation period of the vehicle, and determine the vehicle to reverse to yield based on the behavior of the oncoming vehicle. The vehicle to reverse to yield is either the vehicle or the oncoming vehicle.

[0044] In some embodiments, the vehicle remains stationary during the observation period. That is, the vehicle remains stationary during the observation period, monitors the behavior of oncoming vehicles, and determines whether the vehicle should proactively reverse to yield based on the monitored behavior of the oncoming vehicles.

[0045] For example, the observation duration can be configured as needed, or determined by technicians based on multiple trials to optimize traffic flow. For instance, the observation duration can be set to N seconds, where N is a single-digit or two-digit number, such as N = 2, 3, or 5. It is understood that the observation duration should not be too long to avoid a standoff between the vehicle and oncoming vehicles.

[0046] In some embodiments, monitoring the behavior of the oncoming vehicle during the observation period of the vehicle itself includes: capturing the behavior of the oncoming vehicle in real time using multiple sensors of the vehicle itself.

[0047] Multiple sensors include, but are not limited to:

[0048] Millimeter-wave radar can detect the relative distance, relative speed, and relative direction of travel between oncoming and off-road vehicles. By analyzing changes in relative distance, relative speed, and relative direction of travel, or any combination of these three factors, it can infer whether an oncoming vehicle is reversing.

[0049] LiDAR can detect the relative distance between oncoming vehicles and one's own vehicle, and infer whether the oncoming vehicle is reversing by analyzing changes in the relative distance.

[0050] The camera infers whether an oncoming vehicle is reversing by continuously capturing images showing changes in its position.

[0051] It should be noted that this is just an example; other types of sensors can also be used to monitor the behavior of oncoming vehicles, which will not be listed here.

[0052] In some embodiments, determining the vehicle reversing to yield based on the behavior of the oncoming vehicle includes: determining the oncoming vehicle as a vehicle reversing to yield when the oncoming vehicle begins to reverse based on the behavior of the oncoming vehicle; and determining the vehicle reversing to yield when the oncoming vehicle stops or continues to move forward based on the behavior of the oncoming vehicle.

[0053] During the observation period, the vehicle waits for the oncoming vehicle to reverse. If the oncoming vehicle reverses, it is treated as a vehicle reversing to give way, and the vehicle continues to wait for the oncoming vehicle to reverse until the oncoming vehicle leaves enough road space for the vehicle to pass. If the oncoming vehicle does not reverse, in order to avoid further reducing traffic efficiency, the vehicle will proactively reverse to give way, leaving enough road space for the oncoming vehicle to pass.

[0054] There are multiple ways to determine whether an oncoming vehicle has started reversing based on its behavior, and the specific method used is not limited here. A concrete example illustrates the process of identifying whether an oncoming vehicle has started reversing. Specifically, determining whether an oncoming vehicle has started reversing based on its behavior includes: determining that the oncoming vehicle accelerates while reversing during a first time period within the observation period, and that the oncoming vehicle's reversing speed is not zero during a second time period within the observation period; in this case, the oncoming vehicle has started reversing. For example, if the oncoming vehicle's acceleration is negative for five consecutive frames (approximately 0.5 seconds) within the first time period, the process proceeds to the second level of judgment. Considering that the oncoming vehicle's reversing behavior might involve rapid acceleration and maintaining a constant speed, the judgment is that the oncoming vehicle's acceleration is negative during the first time period within the observation period, and zero during the second time period, but reversing at a constant speed; during the second waiting period, the oncoming vehicle's speed is negative, indicating it is reversing.

[0055] Compared to the mechanical reversing to yield in related technologies, this embodiment achieves dynamic coordination between oncoming vehicles through an interactive mechanism of "waiting during the observation period + oncoming vehicle behavior recognition." The vehicle observes the oncoming vehicle's intentions within a limited observation window, only initiating reversing to yield when the oncoming vehicle does not actively yield. This avoids both vehicles reversing simultaneously and the waste of resources caused by excessive reversing. This interactive logic makes reversing to yield more aligned with the game-theoretic needs of actual oncoming traffic scenarios, improving overall traffic efficiency.

[0056] Step 302: During the process of the vehicle reversing to yield, the vehicle's forward passage is planned at least once, and when the planning result is that the vehicle can accommodate the vehicle's forward passage, the vehicle's forward passage is controlled.

[0057] In some embodiments, the step of planning forward passage for the vehicle at least once during the process of the reversing vehicle yielding includes: when the reversing vehicle is the oncoming vehicle, while waiting for the oncoming vehicle to reversing to yield, planning forward passage for the vehicle at preset time intervals.

[0058] The preset time interval before proceeding with forward traffic planning is used to wait for oncoming vehicles to reverse or pass, so as to free up enough space for the vehicle to pass forward.

[0059] In some embodiments, the step of performing forward traffic planning for the vehicle at least once during the process of the reversing vehicle yielding to another vehicle includes: when the reversing vehicle is the vehicle itself, when the vehicle reverses to yield according to the planned reversing path and reaches the destination position of the planned reversing path, performing forward traffic planning for the vehicle at preset time intervals.

[0060] The vehicle will convert the final reversing plan into a drive-by-wire command and send it to the chassis control system to reverse.

[0061] In some embodiments, the forward traffic planning for the vehicle at preset time intervals includes:

[0062] The process of planning forward traffic for the aforementioned vehicle each time is as follows:

[0063] After the vehicle has been waiting for a preset time, a forward traffic plan is performed for the vehicle. If the result of the current plan is that the vehicle cannot pass forward, the next forward traffic plan is executed until the result of the current plan is that the vehicle can pass forward, or until the cumulative number of forward traffic plans for the vehicle during the reversing and yielding process reaches a threshold.

[0064] In some embodiments, the process of planning forward traffic for the vehicle each time includes:

[0065] After the vehicle has been waiting for a preset time, it is determined whether the cumulative number of planning attempts has reached a threshold.

[0066] If the threshold number of occurrences is reached, a manual takeover process will be triggered.

[0067] If the number of attempts has not reached the threshold, the vehicle will be planned for the next forward passage. If the result of the current planning is that the vehicle cannot pass through, the cumulative number of planning attempts will be incremented by a preset step size, and the next forward passage planning process will be executed. If the result of the current planning is that the vehicle can pass through, the cumulative number of planning attempts will be cleared to zero.

[0068] After the vehicle's forward traffic planning is successfully completed, it will resume driving in the default mode, which can be either cruise mode or normal oncoming traffic mode.

[0069] The preset waiting time at the initial stage of each forward passage plan for a self-driving vehicle is used to wait for oncoming vehicles to reverse or pass, so as to free up enough space for the self-driving vehicle to pass forward.

[0070] Successful forward traffic planning means finding a road passage that can accommodate your vehicle's forward movement; failure to plan forward means not reaching a road passage that can accommodate your vehicle's forward movement. If there is a risk of collision if you proceed forward, you will still block the road, indicating that oncoming vehicles and your vehicle have not been effectively separated.

[0071] In some embodiments, the process of obtaining the reversing planning path includes: sampling a sequence of preset longitudinal driving parameter values ​​and a sequence of preset lateral parameter values ​​to obtain multiple combinations of longitudinal driving parameter values ​​and lateral parameter values; for each combination, estimating N key points on the candidate reversing path based on the combination and the current position of the vehicle, and obtaining a candidate reversing path that sequentially passes through the N key points; N is an integer greater than 1; when the set of candidate reversing paths includes a candidate reversing path that can satisfy the passage of the oncoming vehicle, the candidate reversing path that can satisfy the passage of the oncoming vehicle is used as the reversing planning path; when the set of candidate reversing paths does not include a candidate reversing path that can satisfy the passage of the oncoming vehicle, the value of N is increased and the process of obtaining the reversing planning path is re-executed.

[0072] For example, the longitudinal driving parameter value is the longitudinal acceleration value, and the lateral driving parameter value is the lateral offset angle value. Sampling of the sequence of longitudinal acceleration values ​​can be performed within the acceleration range [-3 m / s²]. 2 3m / s 2 The sampling of the sequence of lateral offset angle values ​​can cover the angle range [-π / 6 rad, 0 rad].

[0073] For example, the sequences of longitudinal acceleration values ​​and lateral offset angle values ​​can be obtained by filtering a real-world driving dataset, which includes the longitudinal acceleration and lateral offset angle values ​​of the vehicle in oncoming traffic scenarios. After filtering, only representative data from different driving modes are retained. These representative data can realistically reflect the vehicle's behavioral characteristics under different driving styles, such as aggressive, conservative, and stable driving styles. The filtered sequences of longitudinal acceleration values ​​and lateral offset angle values ​​can cover various driving modes while maintaining data conciseness, thus improving the efficiency of subsequent traversal and inference.

[0074] When sampling based on sequences of longitudinal acceleration values ​​and lateral offset angle values, sampling can be performed from subsequences of longitudinal acceleration values ​​and lateral offset angle values ​​that match the driving style of the driver of the vehicle. Based on the sampled longitudinal angle values ​​and lateral offset angle values, N steps of deduction are performed to obtain N key points on the alternative reversing path that match the driving style.

[0075] In this method, firstly, samples are taken from a preset sequence of longitudinal acceleration values ​​to deduce the longitudinal distance value of the key point. Secondly, multiple lateral offset angle values ​​are obtained by sampling from a preset sequence of lateral offset angle values. The longitudinal distance value is combined with each lateral offset angle value to determine multiple different lateral positions of the vehicle based on each combination. Based on the combination of longitudinal distance value and lateral offset angle value, N-step calculations are performed, with each step calculating the position of one key point. The N-step calculations yield the positions of N key points, and the planned path that sequentially passes through these N key points is used as the alternative reversing path.

[0076] In each calculation step, assuming the vehicle operates for a time step based on longitudinal distance and lateral offset angle values, the location of the keypoint is calculated using kinematic equations. After continuing for another time step from that keypoint, the location of the next keypoint is calculated, and so on, until the locations of N keypoints are obtained. This time step is configurable as needed, for example, set to 2 seconds.

[0077] For example, the kinematic equation is: The longitudinal distance value obtained from the nth time step derivation is expressed as:

[0078] x n =x n-1 +v n-1 Δt+a(Δt) 2 / 2;

[0079] v n-1 The position obtained after the (n-1)th time step is the longitudinal distance value, where n-1 = 0 represents the initial position, Δt represents the time step, and a represents the longitudinal acceleration value.

[0080] Based on the longitudinal distance value and combined with the sampled lateral offset angle value, the lateral offset of the vehicle at each step is calculated. The lateral offset obtained at the nth step after the nth time step is: Δy n =Δxtanθ n =(x n -x n-1 )tanθ n ;

[0081] Δy n The lateral offset is based on the lateral offset obtained in the (n-1)th step of the derivation, where Δx represents the longitudinal positional deviation between two adjacent time intervals, and Δx = x. n -x n-1 x n x represents the longitudinal position of the vehicle at the nth time step. n-1 θ represents the longitudinal position of the vehicle at time step n-1. nThis represents the lateral offset angle value at the nth time step.

[0082] From the set of multiple alternative reversing paths obtained, those alternative reversing paths that pose a risk of collision (such as collision with surrounding static obstacles) or do not meet vehicle dynamics constraints (such as exceeding the limit of the steering angle) are eliminated.

[0083] An alternative reversing path that can accommodate oncoming vehicles refers to a path that poses no collision risk, meets vehicle dynamics constraints, and has sufficient remaining lane width at its endpoint to allow oncoming vehicles to pass smoothly. When multiple alternative reversing paths exist that can accommodate oncoming vehicles, the path with the highest comfort level (e.g., the path with the gentlest change in steering angle) is selected as the final reversing path. Sufficient remaining lane width at the endpoint of the reversing path to allow oncoming vehicles to pass smoothly can specifically mean that the remaining lane width at the endpoint of the reversing path is not less than the sum of the oncoming vehicle's body width and a preset width margin.

[0084] When the set of alternative reversing paths obtained in this study does not include alternative reversing paths that can satisfy the passage of oncoming vehicles, the value of N is increased (e.g., the value of N is increased from 3 to 5), and the combination of longitudinal acceleration value and lateral offset angle value is obtained by resampling. Based on each combination, N steps are performed to calculate N key points, and thus multiple alternative reversing paths are obtained.

[0085] For example, using T seconds as the time step, first calculate the position of a key point after T seconds based on the values ​​of longitudinal acceleration and lateral offset angle; then calculate the position after 2T seconds. Generally, T is set to 2 and N is set to 3, such as... Figure 4a , Figure 4b , Figure 4c and Figure 4d The diagram shows the planning process of alternative reversing routes. The three key points are the three positions after 2 seconds, 4 seconds, and 6 seconds. Figure 4a The diagram shows the key points of the reversing path in a scenario where the distance is too close. Figure 4b The diagram shows the key points of the reversing path in a narrow passage scenario. Figure 4c The diagram shows the reversing path in a scenario where the distance is too close. Figure 4d The diagram shows a reversing path in a narrow passage scenario. The solid lines connecting the key points represent the reversing path. If, after the preset 3-step calculation, there is still not enough space for oncoming vehicles to pass at the endpoint, N is increased to 4, which means adding one more calculation step, equivalent to the vehicle reversing for an additional 2 seconds.

[0086] This method accurately matches vehicle dynamics and channel space changes by independently sampling longitudinal and lateral driving parameter values. By increasing the number of calculation steps, it improves the efficiency of searching and planning reversing routes and avoids the problem of not being able to find a parking space when returning to the original route. It ensures that the reversing trajectory is continuously output and the endpoint meets the passage requirements of oncoming vehicles, thereby improving the success rate and efficiency of yielding in complex scenarios.

[0087] By initiating forward traffic planning when a vehicle reverses to its destination, or while waiting for oncoming vehicles to reverse and yield, the system achieves coordination between reversing and forward traffic. Through cyclical re-planning of forward traffic and the waiting mechanism, and by leveraging changes in the traffic environment after oncoming vehicles have passed or after reversing, the system enhances the vehicle's ability to autonomously handle complex scenarios, ensuring the continuity and robustness of the entire traffic flow.

[0088] Here, the feasibility of forward passage is incorporated into the yielding success criterion to avoid secondary congestion caused by reversing but still being unable to continue. After forward passage planning is identified, the system continues to wait to observe the passing status of oncoming vehicles and wait for passable space to emerge. Manual intervention is triggered only after the retry exceeds a threshold number, reducing the probability of invalid interruptions. This closed-loop control logic ensures the continuity of the entire process from triggering reversing to resuming forward passage, and is more robust in complex dynamic scenarios.

[0089] In one exemplary embodiment, such as Figure 5 The diagram shows the process of a vehicle reversing to yield to another vehicle, which mainly includes:

[0090] When a vehicle meets an oncoming vehicle, its perception system periodically and continuously collects environmental information, including static and dynamic information. The static information includes at least one of the following: road width, obstacle distribution, road boundaries, etc. The dynamic information includes the vehicle's position, speed, acceleration, etc., as well as the oncoming vehicle's position, speed, acceleration, etc.

[0091] The vehicle determines whether it is too close to oncoming vehicles or the passage is too narrow. Specifically, the vehicle calculates the longitudinal distance to oncoming vehicles and the width of the passage in real time, and calculates the relationship between the longitudinal distance and the safety distance threshold in real time. If the longitudinal distance is less than the safety distance threshold, or the passage width does not meet the conditions for two vehicles to pass, the reversing and yielding process is triggered; otherwise, normal passing is maintained. The conditions for two vehicles to pass include that the passage width is not less than the width threshold, which is the sum of the width of the vehicle and the width of the oncoming vehicle, plus a safety margin. This safety margin is configured as needed, for example, 0.3 meters.

[0092] When there is insufficient distance to oncoming vehicles or the passage is too narrow, the vehicle should either stop comfortably or urgently. When passing through a narrow passage, it should brake to a stop with a comfortable deceleration; when approaching an oncoming vehicle, it should stop urgently. For example, in a narrow passage scenario, the vehicle should use a fixed deceleration (e.g., a comfortable deceleration value of 0.3g, where g = 0.98 m / s²). 2 This is a typical value for comfortable braking of the vehicle (the comfortable deceleration value can also be set according to the actual vehicle speed). If the vehicle's speed is v0 when comfortable braking is triggered, according to the kinematic formula: v(t) = v0 + a comf *t,a comf For the comfortable deceleration value, let v(t) = 0, i.e., stop. Solving for the stopping time, we get: t comf =|v0| / |a comf In practical applications, the deceleration value is dynamically adjusted based on the vehicle dynamics model to ensure a smooth stop within 2 seconds; for example, in scenarios where the distance to other vehicles is too close, the maximum deceleration value, such as a, is used. emerg = -0.5g (the maximum deceleration value is determined by the physical limits of the chassis braking system, based on the shortest achievable braking distance of the vehicle or the actual vehicle model setting), if the trigger is an emergency stop and the vehicle speed is v0, t emerg =|v0| / |a emerg In actual systems, the anti-lock braking system (ABS) will work in conjunction with the control to ensure effective braking within 1 second and reduce the collision risk window.

[0093] The duration of observation after a vehicle stops, for example, 2 seconds;

[0094] During the waiting observation period, observe whether oncoming vehicles are reversing. If so, wait for the specified time (e.g., 2 seconds) before proceeding with the forward traffic plan. If not, initiate the reversing yielding decision for your own vehicle.

[0095] The decision-making process for reversing to yield is as follows:

[0096] Initialize the cumulative number of forward traffic planning iterations i to 0; the vehicle makes reversing behavior decisions and plans reversing paths, and determines whether the end of the reversing path meets the yielding space requirements. If not, the number of iterations is increased and the reversing behavior decisions and reversing path planning are repeated until the planned reversing path meets the yielding space requirements; reversing motion control and execution are performed according to the planned reversing path, and forward path planning is executed after reaching the end of the reversing path; the cumulative number of forward path planning iterations i = i + 1 is updated; it is determined whether the current forward path planning is successful. If successful, the default driving mode is restored. If unsuccessful, it is determined whether i > the number of iterations threshold. If it is greater than the threshold, manual intervention is triggered. If it is not greater than the threshold, the forward path planning is executed again after waiting for a preset time.

[0097] The embodiments provided in this disclosure, in scenarios where a vehicle encounters an oncoming vehicle and needs to reverse to yield, monitor the behavior of the oncoming vehicle within the observation period of the vehicle, and determine the vehicle to reverse and yield based on the behavior of the oncoming vehicle. The reversing vehicle to yield is either the vehicle itself or the oncoming vehicle. During the reversing process, forward traffic planning is performed on the vehicle at least once, and if the planning result indicates that the vehicle can accommodate forward traffic, the vehicle is controlled to move forward. This method, by monitoring the behavior of oncoming vehicles within a short observation period and determining the vehicle to reverse and yield, avoids blind reversing, excessive reversing, and standoffs, laying the foundation for improved traffic efficiency. Furthermore, repeatedly attempting forward traffic planning during the reversing process allows for the early detection of passable lanes, further improving traffic efficiency.

[0098] It is understood that the various method embodiments mentioned above in this disclosure can be combined with each other to form combined embodiments without violating the principle and logic. Due to space limitations, this disclosure will not elaborate further. Those skilled in the art will understand that in the above methods of specific implementation, the specific execution order of each step should be determined by its function and possible internal logic, and the execution order between steps is not limited to implementation according to step number.

[0099] In addition, this disclosure also provides apparatus, electronic equipment, and computer program products, all of which can be used to implement any of the vehicle passage methods provided in this disclosure. The corresponding technical solutions and descriptions are described in the corresponding records in the method section and will not be repeated here.

[0100] Figure 6 This is a block diagram of a vehicle passage device provided in an embodiment of the present disclosure. The vehicle passage device mainly includes:

[0101] The determination module 601 is used to monitor the behavior of the oncoming vehicle within the observation time of the self-vehicle when the self-vehicle encounters an oncoming vehicle and needs to reverse to yield, and to determine the vehicle to reverse to yield based on the behavior of the oncoming vehicle, wherein the vehicle to reverse to yield is the self-vehicle or the oncoming vehicle.

[0102] The control module 602 is used to perform forward traffic planning for the vehicle at least once during the process of the vehicle reversing to yield, and control the vehicle to move forward when the planning result is that the vehicle can accommodate the vehicle moving forward.

[0103] Figure 7 This is a block diagram of an electronic device provided in an embodiment of the present disclosure.

[0104] Reference Figure 7This disclosure provides an electronic device, which includes: at least one processor 701; at least one memory 702; and one or more I / O interfaces 703 connected between the processor 701 and the memory 702; wherein the memory 702 stores one or more computer programs that can be executed by the at least one processor 701, and the one or more computer programs are executed by the at least one processor 701 to enable the at least one processor 701 to perform the above-described vehicle passage method.

[0105] The modules in the aforementioned electronic devices can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0106] This disclosure also provides a computer program product, including a computer program that, when run in a processor, implements the above-described vehicle passage method.

[0107] The computer program may be stored on a readable storage medium of a computer device or in the cloud; the processor of the computer device reads the computer program from the readable storage medium or in the cloud.

[0108] The aforementioned computer program product can be implemented through hardware, software, or a combination thereof. In one optional embodiment, the computer program product is specifically manifested as a computer storage medium; in another optional embodiment, the computer program product is specifically manifested as a software product, such as a software development kit (SDK), etc.

[0109] Those skilled in the art will understand that all or some of the steps, systems, and apparatuses disclosed above, and their functional modules / units, can be implemented as software, firmware, hardware, or suitable combinations thereof. In hardware implementations, the division between functional modules / units mentioned above does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software can be distributed on a computer-readable storage medium, which may include computer storage media (or non-transitory media) and communication media (or transient media).

[0110] As is known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable program instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), static random access memory (SRAM), flash memory or other memory technologies, portable compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, it is known to those skilled in the art that communication media typically contain computer-readable program instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0111] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0112] Computer program instructions used to perform the operations of this disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing the status information of the computer-readable program instructions to implement various aspects of this disclosure.

[0113] The computer program product described herein can be implemented specifically through hardware, software, or a combination thereof. In one alternative embodiment, the computer program product is specifically embodied in a computer storage medium; in another alternative embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.

[0114] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0115] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0116] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0117] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0118] The above description is merely a preferred embodiment of this disclosure and is not intended to limit this disclosure. Any modifications or equivalent substitutions made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for vehicle passage, characterized in that, include: In a scenario where a vehicle encounters an oncoming vehicle and needs to reverse to yield, the behavior of the oncoming vehicle is monitored during the observation period of the vehicle. The vehicle to reverse to yield is determined based on the behavior of the oncoming vehicle. The vehicle to reverse to yield is either the vehicle or the oncoming vehicle. During the process of the vehicle reversing to yield, the vehicle's forward passage is planned at least once, and when the planning result indicates that the vehicle can accommodate the vehicle's forward passage, the vehicle's forward passage is controlled.

2. The method according to claim 1, characterized in that, The step of determining the vehicle to reverse and yield based on the behavior of the oncoming vehicle includes: When it is determined from the behavior of the oncoming vehicle that the oncoming vehicle begins to reverse, the oncoming vehicle is identified as a vehicle reversing to yield. When the behavior of the oncoming vehicle determines whether the oncoming vehicle stops or continues to move forward, the vehicle itself is identified as reversing to yield.

3. The method according to claim 2, characterized in that, The step of determining that the oncoming vehicle has started reversing based on the behavior of the oncoming vehicle includes: Based on the behavior of the oncoming vehicle, it is determined that the oncoming vehicle accelerates in reverse during the first time period within the observation period, and the reversing speed of the oncoming vehicle is not zero during the second time period within the observation period, thus determining that the oncoming vehicle has started reversing.

4. The method according to claim 1, characterized in that, During the process of the vehicle reversing to yield, at least one forward traffic planning is performed on the vehicle itself, including: When the vehicle reversing to yield is an oncoming vehicle, while waiting for the oncoming vehicle to reversing to yield, the vehicle's forward passage is planned at preset time intervals.

5. The method according to claim 1, characterized in that, During the process of the vehicle reversing to yield, at least one forward traffic planning is performed on the vehicle itself, including: When the vehicle being reversed to yield is the self-vehicle, when the self-vehicle reverses to yield according to the reverse planning path and reaches the destination position of the reverse planning path, the self-vehicle is planned to move forward at preset time intervals.

6. The method according to claim 4 or 5, characterized in that, The pre-set time interval for planning the forward passage of the vehicle includes: The process of planning forward traffic for the aforementioned vehicle each time is as follows: After the vehicle has been waiting for a preset time, a forward traffic plan is performed for the vehicle. If the result of the current plan is that the vehicle cannot pass forward, the next forward traffic plan is executed until the result of the current plan is that the vehicle can pass forward or the cumulative number of forward traffic plans during the reversing process reaches a threshold.

7. The method according to claim 6, characterized in that, Each forward traffic planning process for the aforementioned vehicle includes: After the vehicle has been waiting for a preset time, it is determined whether the cumulative number of planning attempts has reached a threshold. If the threshold number of occurrences is reached, a manual takeover process will be triggered. If the number of attempts has not reached the threshold, the vehicle will be planned for the next forward passage. If the result of the current planning is that the vehicle cannot pass through, the cumulative number of planning attempts will be incremented by a preset step size, and the next forward passage planning process will be executed. If the result of the current planning is that the vehicle can pass through, the cumulative number of planning attempts will be cleared to zero.

8. The method according to claim 5, characterized in that, The process of obtaining the reversing planning path includes: The preset sequences of longitudinal driving parameter values ​​and lateral parameter values ​​are sampled separately to obtain multiple combinations of longitudinal driving parameter values ​​and lateral parameter values; For each combination, based on the combination and the current position of the vehicle, estimate N key points on the candidate reversing path, and obtain the candidate reversing path that sequentially passes through N key points; where N is an integer greater than 1. When the set of alternative reversing paths includes alternative reversing paths that can satisfy the passage of oncoming vehicles, the alternative reversing paths that can satisfy the passage of oncoming vehicles are used as the reversing planning path. If the set of alternative reversing paths does not include an alternative reversing path that can satisfy the passage of the oncoming vehicle, the value of N is increased and the process of obtaining the reversing planning path is re-executed.

9. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores at least one computer program that can be executed by the at least one processor, the at least one computer program being executed by the at least one processor to enable the at least one processor to perform the vehicle passage method as described in any one of claims 1-8.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when run in a processor, implements the vehicle passage method according to any one of claims 1-8.

Images