Control method and device of unmanned device, electronic device and storage medium

Abstract

The present disclosure provides a control method and device of an unmanned device, an electronic device and a storage medium, relates to the technical field of computers, and particularly relates to the technical field of artificial intelligence such as automatic driving and intelligent traffic. The method comprises the following steps: if it is detected that path planning of the unmanned device fails at a current time, determining a first position, a first speed, an obstacle around the unmanned device and a corresponding first predicted trajectory of the unmanned device; determining a target braking strategy according to the first position, the first speed, the obstacle and the corresponding first predicted trajectory; in the case that the target braking strategy is slow braking, determining a target slow braking duration; and generating a slow braking trajectory based on the target slow braking duration, and then controlling the unmanned device. Thus, in the case that path planning of the unmanned device fails, the target braking strategy can be accurately determined, and in the case that the target braking strategy is slow braking, the target slow braking time can be determined, so that the unmanned device can be accurately controlled.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and in particular to the field of artificial intelligence technology such as autonomous driving and intelligent transportation, specifically to a control method, device, electronic device and storage medium for unmanned driving equipment. Background Technology

[0002] In the field of autonomous driving, to ensure safe operation, autonomous vehicles need to control themselves based on the surrounding environment and predicted obstacle trajectories. Therefore, accurately controlling autonomous vehicles has become a key research direction. Summary of the Invention

[0003] This disclosure provides a control method, device, electronic equipment, and storage medium for unmanned driving equipment.

[0004] According to a first aspect of this disclosure, a control method for an unmanned driving device is provided, comprising:

[0005] If the path planning of the autonomous driving device fails at the current moment, determine the first position of the autonomous driving device, the first speed of the autonomous driving device, the obstacles around the autonomous driving device, and the corresponding first predicted trajectory at the current moment;

[0006] Based on the first position, the first speed, the obstacle, and the corresponding first predicted trajectory, the target braking strategy corresponding to the unmanned driving device is determined;

[0007] When the target braking strategy is gentle braking, determine the target gentle braking duration of the unmanned driving device;

[0008] Based on the target braking duration, a braking trajectory is generated;

[0009] The unmanned driving device is controlled based on the braking trajectory.

[0010] According to a second aspect of this disclosure, a control device for an unmanned driving device is provided, comprising:

[0011] The first determining module is used to determine the first position of the autonomous driving device, the first speed of the autonomous driving device, the obstacles around the autonomous driving device and the corresponding first predicted trajectory at the current time when the path planning of the autonomous driving device is detected to be failed at the current time.

[0012] The second determining module is used to determine the target braking strategy corresponding to the unmanned driving device based on the first position, the first speed, the obstacle and the corresponding first predicted trajectory.

[0013] The third determining module is used to determine the target braking duration of the unmanned driving device when the target braking strategy is gentle braking.

[0014] The generation module is used to generate a braking trajectory based on the target braking duration;

[0015] The control module is used to control the unmanned driving equipment based on the braking trajectory.

[0016] According to a third aspect of this disclosure, an electronic device is provided, comprising:

[0017] At least one processor; and

[0018] A memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the control method of the unmanned vehicle as described in the first aspect.

[0020] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions for causing the computer to perform a control method for an unmanned vehicle as described in the first aspect.

[0021] According to a fifth aspect of this disclosure, a computer program product is provided, including computer instructions that, when executed by a processor, implement the steps of the control method for an unmanned vehicle as described in the first aspect.

[0022] The control method, device, electronic equipment, and storage medium for unmanned driving equipment disclosed herein have the following beneficial effects:

[0023] In this embodiment, when path planning failure of the autonomous driving device is detected at the current moment, the first position, first speed, surrounding obstacles, and corresponding first predicted trajectory of the autonomous driving device at the current moment are determined. Then, based on the first position, first speed, obstacles, and corresponding first predicted trajectory, the target braking strategy corresponding to the autonomous driving device is determined. If the target braking strategy is gradual braking, the target gradual braking duration of the autonomous driving device is determined. Then, based on the target gradual braking duration, a gradual braking trajectory is generated. Finally, the autonomous driving device is controlled based on the gradual braking trajectory. Therefore, even when path planning of the autonomous driving device fails at the current moment, the target braking strategy of the autonomous driving device can be accurately determined based on the current state of the autonomous driving device and the state of the surrounding obstacles. If the target braking strategy is gradual braking, the target gradual braking time can be determined, thereby enabling accurate control of the autonomous driving device. This ensures safety while reducing the number of sudden braking events, improving the traffic efficiency and driving comfort of the autonomous vehicle.

[0024] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0025] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0026] Figure 1 This is a schematic flowchart of a control method for an unmanned driving device according to an embodiment of the present disclosure;

[0027] Figure 2 This is a flowchart illustrating a control method for an unmanned driving device according to yet another embodiment of the present disclosure;

[0028] Figure 3 This is a flowchart illustrating a control method for an unmanned driving device according to yet another embodiment of the present disclosure;

[0029] Figure 4 This is a schematic diagram of the structure of a control device for an unmanned driving device according to an embodiment of the present disclosure;

[0030] Figure 5 This is a block diagram of an electronic device used to implement the control method of the unmanned driving device according to the embodiments of the present disclosure. Detailed Implementation

[0031] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0032] This disclosure relates to the fields of artificial intelligence technology, such as autonomous driving and intelligent transportation.

[0033] Artificial Intelligence (AI) is a new technological science that studies and develops theories, methods, technologies, and application systems to simulate, extend, and expand human intelligence.

[0034] Automatic driving generally refers to automatic driving systems. Automatic driving systems utilize advanced communication, computer, network, and control technologies to achieve real-time, continuous control of trains. An automatic driving system is a highly centralized train operation system where the work performed by the train driver is fully automated. Automatic driving systems possess functions such as automatic train wake-up and start-up, automatic entry and exit from the depot, automatic cleaning, automatic driving, automatic stopping, automatic door opening and closing, and automatic fault recovery. They also have multiple operating modes, including normal operation, degraded operation, and operation interruption. Achieving fully automated operation can save energy and optimize the rational matching of system energy consumption and speed.

[0035] Intelligent transportation effectively integrates advanced science and technology (information technology, computer technology, data communication technology, sensor technology, electronic control technology, automatic control theory, operations research, artificial intelligence, etc.) into transportation, service control, and vehicle manufacturing, strengthening the connection between vehicles, roads, and users, thereby forming a comprehensive transportation system that ensures safety, improves efficiency, improves the environment, and saves energy.

[0036] The control method, apparatus, electronic device, and storage medium of the unmanned driving equipment according to embodiments of the present disclosure are described below with reference to the accompanying drawings.

[0037] It should be noted that the execution subject of the control method of the unmanned driving equipment in this embodiment is the control device of the unmanned driving equipment. This device can be implemented by software and / or hardware. This device can be configured in an electronic device, which may include, but is not limited to, a terminal, a server, etc.

[0038] Figure 1 This is a schematic flowchart of a control method for an unmanned driving device according to an embodiment of the present disclosure.

[0039] like Figure 1 As shown, the control method of this unmanned driving device includes:

[0040] S101: If the path planning of the autonomous driving device fails at the current moment, determine the first position of the autonomous driving device, the first speed of the autonomous driving device, the obstacles around the autonomous driving device, and the corresponding first predicted trajectory at the current moment.

[0041] It should be noted that in situations with numerous obstacles around the vehicle, or due to insufficient robustness of the autonomous driving path planning module, the autonomous driving system may fail to plan its path. In the event of path planning failure, directly applying sudden braking may result in accidental sudden braking. Therefore, in this embodiment, when path planning by the autonomous driving device fails, the system can further determine whether to apply gentle braking or sudden braking based on the surrounding environment, thereby enabling more accurate control of the autonomous driving device and avoiding accidental sudden braking.

[0042] Optionally, the current location of the autonomous vehicle can be obtained through the positioning module in the autonomous vehicle.

[0043] Optionally, the initial speed of the autonomous vehicle at the current moment can be obtained through the motion sensor module in the autonomous vehicle.

[0044] The obstacle can be any object that is less than a preset value in distance from the vehicle. The preset value can be 10 meters, 6 meters, etc.

[0045] For example, if the preset value is 10 meters, then a person 5 meters away from a vehicle can be considered an obstacle, and a vehicle 9 meters away can also be considered an obstacle. This disclosure does not impose any limitations on this.

[0046] The first predicted trajectory can be the trajectory predicted by the prediction module of the autonomous driving device for obstacles around the vehicle.

[0047] S102: Determine the target braking strategy corresponding to the unmanned driving equipment based on the first position, first speed, obstacle and corresponding first predicted trajectory.

[0048] The target braking strategy can be either emergency braking or gradual braking.

[0049] Optionally, based on the first predicted trajectory corresponding to the obstacle, the second position of the obstacle at the current moment can be determined. Then, based on the first and second positions, the relative positional relationship between the obstacle and the autonomous driving equipment can be determined. The relative positional relationship can include collision, with the obstacle located directly in front of / to the left front of / to the right front of / to the left side of / to the right side / to the left rear of / to the right rear of / to the right rear of the autonomous driving equipment, etc., and the direction directly in front being the direction of travel of the autonomous driving equipment.

[0050] For obstacles whose relative positional relationship is one of collision, the target braking strategy is emergency braking.

[0051] For obstacles that are directly in front of the autonomous vehicle, the system can determine whether the distance between the obstacle and the autonomous vehicle will be less than the safe distance within a certain period of time (e.g., 1.5 seconds) after the current moment, based on the first speed of the autonomous vehicle and the first predicted trajectory of the obstacle. If the distance is less than the safe distance, the target braking strategy is emergency braking; if not, the target braking strategy is gradual braking.

[0052] For obstacles whose relative position is to the left front / right front / left side / right side / left rear / right rear / directly behind the autonomous driving equipment, the first predicted trajectory of the obstacle can be used to determine whether the obstacle will appear in front of the autonomous driving equipment within a certain period of time (e.g., 1.5 seconds) after the current moment. If it appears in front of the obstacle, the steps for determining the target braking strategy when the relative position is directly in front of the autonomous driving equipment are adopted.

[0053] S103: When the target braking strategy is gentle braking, determine the target gentle braking duration of the autonomous driving equipment.

[0054] Among them, the target braking duration is the braking time of the unmanned vehicle from the current moment to the moment of stopping under the condition of slow braking.

[0055] Optionally, the target braking duration will vary depending on the current state of the autonomous driving device. For example, the target braking duration will differ depending on the vehicle's initial speed. The higher the initial speed, the longer the target braking duration.

[0056] Optionally, a mapping table between vehicle speed and braking duration can be pre-established under slack braking conditions, and then the target slack braking duration can be determined based on the mapping table.

[0057] S104: Generate the braking trajectory based on the target braking duration.

[0058] Understandably, once the target braking duration is determined, the braking trajectory can be generated based on that duration.

[0059] Specifically, based on the first speed, first position of the autonomous driving equipment, and the first predicted trajectory of the obstacle, as well as information such as lane lines, pedestrian crossings, and intersections within a certain range around the autonomous driving equipment provided by the high-precision map, a fifth-order polynomial is used to generate a cluster of easing braking trajectories. Then, the braking trajectory with the highest score in the cluster of easing braking trajectories is taken as the easing braking trajectory.

[0060] In this embodiment of the disclosure, if the target braking strategy is emergency braking, the minimum braking deceleration can be obtained based on the braking capability of the autonomous driving equipment. Then, sampling is performed within the feasible braking deceleration range of the autonomous driving equipment (e.g., [-5,0]). Then, a braking trajectory cluster is generated based on the sampled deceleration using a fifth-order polynomial. Then, trajectories that will collide are screened out based on collision detection. If a portion of safe trajectories remain, the trajectory with the smallest absolute value of braking deceleration is selected as the emergency braking trajectory to reduce the risk of rear-end collisions. If all sampled trajectories are screened out, full braking is performed based on the minimum braking deceleration.

[0061] S105: Controls unmanned driving equipment based on the braking trajectory.

[0062] In this embodiment of the disclosure, after the braking trajectory is generated, the autonomous driving equipment can be controlled according to the braking trajectory to avoid accidental emergency braking caused by the failure of the autonomous driving equipment's path planning.

[0063] In this embodiment, when path planning failure of the autonomous driving device is detected at the current moment, the first position, first speed, surrounding obstacles, and corresponding first predicted trajectory of the autonomous driving device at the current moment are determined. Then, based on the first position, first speed, obstacles, and corresponding first predicted trajectory, the target braking strategy corresponding to the autonomous driving device is determined. If the target braking strategy is gradual braking, the target gradual braking duration of the autonomous driving device is determined. Then, based on the target gradual braking duration, a gradual braking trajectory is generated. Finally, the autonomous driving device is controlled based on the gradual braking trajectory. Therefore, even when path planning of the autonomous driving device fails at the current moment, the target braking strategy of the autonomous driving device can be accurately determined based on the current state of the autonomous driving device and the state of the surrounding obstacles. If the target braking strategy is gradual braking, the target gradual braking time can be determined, thereby enabling accurate control of the autonomous driving device. This ensures safety while reducing the number of sudden braking events, improving the traffic efficiency and driving comfort of the autonomous vehicle.

[0064] Figure 2 This is a flowchart illustrating a control method for an unmanned driving device according to yet another embodiment of the present disclosure;

[0065] like Figure 2As shown, the control method of this unmanned driving device includes:

[0066] S201: If the path planning of the unmanned vehicle fails at the current moment, determine the first position of the unmanned vehicle, the first speed of the unmanned vehicle, the obstacles around the unmanned vehicle, and the corresponding first predicted trajectory.

[0067] The specific implementations of S201 and S202 can be found in the detailed descriptions of other embodiments in this disclosure, and will not be repeated here.

[0068] S202: Identify at least one point in the corresponding first predicted trajectory that is located in the direction of travel of the autonomous vehicle within a first preset time period after the current moment and whose first distance from the autonomous vehicle is less than a first distance threshold as a candidate obstacle.

[0069] The first preset duration can be a short period of time after the current moment. For example, the first preset duration can be 1.5 seconds (s), 2 seconds, etc. This disclosure does not limit it.

[0070] The direction of travel for the unmanned vehicle can be in front of the vehicle (including directly in front, to the left, or to the right).

[0071] The first distance between the autonomous driving device and the autonomous driving device can be the straight-line distance between each trajectory point on the first predicted trajectory and the first position of the autonomous driving device.

[0072] The first distance threshold can be a pre-set distance value used to determine whether the distance between the obstacle and the autonomous driving equipment is too close. For example, 3 meters (m), 2.5 meters, etc. This disclosure does not limit it.

[0073] The candidate obstacles are those that, within a first preset time period, may appear in the direction of travel of the autonomous vehicle and are too close to the autonomous vehicle; in other words, obstacles that may collide with the autonomous vehicle.

[0074] S203: The candidate obstacle with the smallest first distance is identified as the target obstacle.

[0075] It is understandable that the candidate obstacle with the smallest first distance is the candidate obstacle most likely to collide with the autonomous vehicle. Therefore, the candidate obstacle with the smallest first distance is identified as the target obstacle.

[0076] S204: Determine the minimum second distance between the target obstacle and the unmanned vehicle within a second preset time period after the current moment, and the relative speed between the target obstacle and the unmanned vehicle at the minimum second distance, wherein the second preset time period is less than the first preset time period.

[0077] The second preset duration can be a short period of time after the current moment, but the second preset duration is shorter than the first preset duration. For example, the first preset duration can be 2 seconds and the second preset duration can be 1.5 seconds. This disclosure does not impose any limitations on this.

[0078] Optionally, the acceleration of the autonomous vehicle at the current moment can be obtained first, and then the reference trajectory of the autonomous vehicle within a second preset time period can be determined based on the acceleration, the first position, and the first velocity. Then, the minimum second distance can be determined based on the first predicted trajectory of the target obstacle and the reference trajectory of the autonomous vehicle.

[0079] It should be noted that after identifying the target obstacle, since the path planning of the autonomous driving device fails at the current moment and there is no predicted trajectory for the autonomous driving device, a reference trajectory for the autonomous driving device within a second preset time period may be determined based on the current acceleration, first position, and first velocity of the autonomous driving device.

[0080] Among these, acceleration can be the acceleration of the autonomous vehicle at the current moment. Optionally, the acceleration of the autonomous vehicle at the current moment can be obtained through the motion sensor module in the autonomous vehicle.

[0081] It is understandable that after determining the reference trajectory of the autonomous driving equipment and the first trajectory of the target obstacle, the minimum second distance within a second preset time period can be determined based on the second distance between the position of the autonomous driving equipment and the position of the target obstacle at the same time.

[0082] Optionally, after determining the minimum second distance, the second speed of the autonomous vehicle and the third speed of the target obstacle at the minimum second distance can be further determined, and then the relative speed between the autonomous vehicle and the target obstacle can be determined based on the second speed and the third speed.

[0083] Specifically, the time corresponding to the minimum second distance can be determined first. Then, based on the acceleration and the first velocity, the second velocity of the autonomous driving device at the time corresponding to the minimum second distance can be determined. The third velocity of the target obstacle can be determined based on the first predicted trajectory.

[0084] In this embodiment of the disclosure, a reference trajectory of the unmanned driving device within a second preset time period can be determined based on the acceleration, first position, and first speed of the unmanned driving device. Based on the reference trajectory and the first predicted trajectory, a minimum second distance and the relative speed between the target obstacle and the unmanned driving device at the minimum second distance can be determined, thereby making the determined minimum second distance and relative speed more accurate, and providing conditions for subsequently determining the target braking strategy based on the minimum second distance and relative speed.

[0085] S205: If the first ratio between the minimum second distance and the relative speed is greater than or equal to the time threshold, the target braking strategy is determined to be slow braking.

[0086] The time threshold can be a preset value, such as 1.5s, 2s, etc. This disclosure does not limit it.

[0087] It is understandable that the first ratio between the minimum second distance and the relative speed can represent the time when the two will collide after the second preset time. If the first ratio is greater than or equal to the time threshold, it means that the time when the two will collide is after the time threshold, and the collision will not occur even if the braking is slow.

[0088] Therefore, when the distance between the target obstacle and the vehicle is relatively close, but the ratio of the minimum second distance to the relative distance between the autonomous driving device and the target obstacle is greater than or equal to the time threshold, the target braking strategy is determined to be gentle braking. This can avoid collisions between the two while avoiding the unpleasant experience caused by accidental emergency braking, thus improving ride comfort.

[0089] S206: If the first ratio is less than the time threshold, determine the type of the target obstacle.

[0090] The target obstacle can be classified into two types: Type 1 and Type 2. Type 1 obstacles are physical obstacles that may collide with the autonomous vehicle, such as people or vehicles. Type 2 obstacles are virtual obstacles that will not collide with the autonomous vehicle, but which the autonomous vehicle needs to stop, such as red lights.

[0091] S207: If the target obstacle is of type 1, determine the target braking strategy as emergency braking.

[0092] In cases where the target obstacle is a physical obstacle, emergency braking is required to prevent the unmanned vehicle from colliding with the physical obstacle.

[0093] In this embodiment of the present disclosure, if the first ratio is less than the time threshold, the target braking strategy can be further determined based on the type of the target obstacle. If the type of the target obstacle is a physical obstacle, the target braking strategy is determined to be emergency braking, thereby avoiding collisions between the autonomous driving device and the physical obstacle.

[0094] S208: If the target obstacle is of type 2, determine the third distance between the target obstacle and the nearest pedestrian crossing.

[0095] Optionally, based on the location of the pedestrian crossing provided by the high-precision map, the nearest pedestrian crossing to the target obstacle can be determined, and then a third distance between the target obstacle and the nearest pedestrian crossing can be determined.

[0096] S209: If the third distance is less than the second distance threshold, determine the target braking strategy as emergency braking.

[0097] The second distance threshold can be a pre-set distance used to determine whether a target obstacle is close to the pedestrian crossing. For example, the second distance threshold can be 2m, 3m, etc. This disclosure does not limit it.

[0098] Understandably, if the third distance is less than the second distance threshold, it indicates that the target obstacle is approaching the pedestrian crossing, for example, when pedestrians are crossing the road. In this case, emergency braking is necessary to avoid a collision.

[0099] S210, if the third distance is greater than or equal to the second distance threshold, determine the target braking strategy as mild braking.

[0100] If the third distance is less than the second distance threshold, it means that the target obstacle is not close to the pedestrian crossing, and a gentle braking measure is required.

[0101] In this embodiment of the disclosure, when the target obstacle is of the second type, a third distance between the target obstacle and the pedestrian crossing can be further obtained. If the third distance is less than the second distance threshold, the target braking strategy is determined to be emergency braking. Alternatively, if the third distance is greater than or equal to the second distance threshold, the target braking strategy is determined to be gentle braking, thereby avoiding collisions between the autonomous driving equipment and pedestrians.

[0102] S211, when the target braking strategy is gentle braking, determine the target gentle braking duration of the autonomous driving equipment.

[0103] S212, Generate braking trajectory based on target braking duration.

[0104] S213 controls unmanned vehicles based on the braking trajectory.

[0105] The specific implementations of S211 and S213 can be found in the detailed descriptions of other embodiments in this disclosure, and will not be repeated here.

[0106] In this embodiment, when path planning failure of the autonomous driving device is detected at the current moment, the first position, first speed, obstacles around the autonomous driving device, and corresponding first predicted trajectories of the autonomous driving device at the current moment are determined. Then, based on the first position, first speed, obstacles, and corresponding first predicted trajectories, it is determined whether there is a target obstacle that appears in the direction of travel of the autonomous driving device within a first preset time period, and has the smallest first distance from the autonomous driving device, and the smallest first distance threshold is also within the first preset time period. If such an obstacle exists, a target braking strategy is further determined by combining the type of the target obstacle and the third distance between the obstacle and the pedestrian crossing. Thus, when path planning of the autonomous driving device fails at the current moment, the target braking strategy of the autonomous driving device can be determined more accurately, thereby further improving the control of the autonomous driving device.

[0107] Figure 3 This is a flowchart illustrating a control method for an unmanned driving device according to yet another embodiment of the present disclosure;

[0108] like Figure 3 As shown, the control method of this unmanned driving device includes:

[0109] In the event of a planning failure, determine the current position of the autonomous vehicle, its initial speed, the obstacles around the autonomous vehicle, and the corresponding initial predicted trajectory.

[0110] S302: Determine the target braking strategy corresponding to the unmanned driving equipment based on the first position, first speed, obstacle and corresponding first predicted trajectory.

[0111] The specific implementations of S301 and S302 can be found in the detailed descriptions of other embodiments in this disclosure, and will not be repeated here.

[0112] S303: Obtain the second predicted trajectory of the autonomous driving device at the previous moment adjacent to the current moment.

[0113] In this embodiment, when the target braking strategy is gradual braking, a second predicted trajectory corresponding to the autonomous driving device at the previous moment adjacent to the current moment can be further obtained. Then, by combining the second predicted trajectory corresponding to the autonomous driving device, the target gradual braking duration of the autonomous driving device can be determined. This makes the determined target gradual braking duration more accurate.

[0114] S304: If the speed at the end of the second predicted trajectory is not zero, obtain the target length of the second predicted trajectory, the preset first parking time, and the first reference coefficient.

[0115] It should be noted that if the speed at the end of the second predicted trajectory is not zero, it means that the second predicted trajectory of the autonomous driving device in the previous moment was not a parking trajectory.

[0116] The target length of the second predicted trajectory can be the distance between the endpoint of the second predicted trajectory and the autonomous driving device at the previous moment.

[0117] The preset first parking duration can be the duration corresponding to a standard parking trajectory, such as 8 seconds, but this disclosure does not limit it.

[0118] The first reference coefficient can be a pre-set reference coefficient corresponding to the condition that the velocity at the end of the second predicted trajectory is not zero. For example, 2, etc. This disclosure does not limit it.

[0119] S305: Determine the second ratio of the target length to the first velocity.

[0120] The second ratio of the target length to the first speed can represent the fastest time for the autonomous vehicle to stop at the current speed.

[0121] S306: The first product between the second ratio and the first reference coefficient is determined as the second parking duration.

[0122] S307: The minimum of the first parking time and the second parking time is determined as the target slow braking time.

[0123] In this embodiment of the disclosure, if the second parking time determined based on the target length of the second predicted trajectory, the first speed, and the first reference coefficient is greater than the preset first parking time, then the target easing braking time is determined as the first parking time. That is, the target easing braking time cannot be less than the preset first parking time.

[0124] If the second parking time is less than the first parking time, it means that the autonomous vehicle needs to stop for a shorter period than the preset first parking time. Therefore, the second parking time is determined as the target braking duration. This allows the minimum of the first parking time and the second parking time determined based on the second predicted trajectory to be used as the target braking duration, when the speed at the end of the second predicted trajectory is zero. This makes the determined target braking duration more suitable for the current scenario of the autonomous vehicle.

[0125] S308: When the speed at the end of the second predicted trajectory is zero, obtain the shortest braking time of the autonomous driving device, the third stopping time corresponding to the second predicted trajectory, and the path planning result corresponding to the previous moment.

[0126] It should be noted that if the speed at the end of the second predicted trajectory is not zero, it means that the second predicted trajectory of the autonomous driving device at the previous moment was a parking trajectory.

[0127] The shortest braking time is the fastest time it takes for the autonomous vehicle to stop under emergency braking. Optionally, the shortest braking time can be determined by the ratio of the autonomous vehicle's current initial speed to the maximum absolute value of the braking deceleration.

[0128] The third parking duration corresponding to the second predicted trajectory is the duration of the second predicted trajectory.

[0129] The path planning result can be either a failure or a success. If the path planning result is a failure, it means that the parking trajectory is a slow braking trajectory determined under the condition of path planning failure; if the path planning result is a success, it means that the parking trajectory is a parking trajectory to the destination determined under the condition of path planning success.

[0130] S309: If the path planning result is a failure, obtain the total number of consecutive path planning failures adjacent to the current time and the second reference coefficient.

[0131] In this embodiment of the disclosure, if the path planning result is a failure, the total number of consecutive path planning failures adjacent to the current time can be further obtained. The total number of consecutive path planning failures can represent the current level of crisis. The greater the total number of consecutive path planning failures, the more urgent the situation, and the shorter the target deceleration time needs to be.

[0132] The second reference coefficient can be 0.02, 0.1, etc. This disclosure does not limit it.

[0133] For example, if the current time is 3 seconds and the path planning frequency is once every 0.1 seconds, the path planning fails at 2.9 seconds, 2.8 seconds, and 2.7 seconds, but succeeds at 2.6 seconds. Therefore, the total number of consecutive path planning failures is 4.

[0134] S310: Determine the first difference between the third stopping time and the shortest braking time.

[0135] S311: Determine the target braking duration based on the shortest braking time, the first difference, the total number of braking attempts, and the second reference coefficient.

[0136] Optionally, a second product is determined between the first difference, the third reference coefficient, and the target number of failures. The sum of the shortest braking time and the first difference is determined as a reference value. Finally, the second difference between the reference value and the second product is determined as the target easing braking time. This allows for an accurate determination of the target easing braking time at the current moment, assuming the path planning result at the previous moment was a failure.

[0137] In summary, if the path planning result in the previous time step was unsuccessful, the formula for calculating the target braking time is as follows:

[0138] stop_t=min_stop_t+(t_pre–min_stop_t)*(1–β*fail_count)

[0139] Where stop_t is the target braking duration, min_stop_t is the shortest braking duration, t_pre is the third stopping duration, β is the second reference coefficient, and fail_count is the total number of consecutive path planning failures adjacent to the current time.

[0140] In this embodiment of the disclosure, when the speed at the end of the second predicted trajectory is zero, the path planning result corresponding to the previous moment can be further determined. If the path planning result is a failure, the target braking duration can be determined by combining the total number of consecutive failures of path planning. The larger the total number of failures, the shorter the target braking duration. In other words, the target braking duration can be determined according to the current crisis level of the autonomous driving equipment, so that the determined target braking duration is more accurate.

[0141] It should be noted that the technical solutions of steps S308 to S311 and steps S304 to S307 are parallel technical solutions. In this embodiment of the disclosure, the order of steps S308 to S311 and steps S304 to S307 is not limited.

[0142] S312: If the path planning result is successful, obtain the third reference coefficient and the preset first parking time.

[0143] The second reference coefficient can be 0.8, 0.7, etc. This disclosure does not limit it.

[0144] S313: Determine the third difference between the preset first parking time and the shortest braking time.

[0145] S314: Determine the third product between the third difference and the third reference coefficient.

[0146] S315: The sum of the third product and the shortest braking time is determined as the target easing braking time.

[0147] In summary, assuming the path planning result was successful in the previous time step, the formula for calculating the target braking time of the autonomous driving device can be:

[0148] stop_t=min_stop_t+f*(t_planning–min_stop_t)

[0149] Where stop_t is the target braking duration, min_stop_t is the shortest braking duration, t_planning is the first stopping duration, and f is the third reference coefficient.

[0150] In this embodiment of the disclosure, the target braking time of the autonomous driving device can be accurately determined when the path planning result of the previous moment is successful, based on the third reference coefficient, the preset first parking time and the shortest braking time.

[0151] It should be noted that the technical solutions of steps S312 to S315 and the technical solutions of steps S310 to S311 are parallel technical solutions. In this embodiment of the disclosure, the order of steps S312 to S315 and steps S310 to S311 is not limited.

[0152] S316: Generate a braking trajectory based on the target braking duration.

[0153] S317: Controlling unmanned driving equipment based on the braking trajectory.

[0154] The specific implementations of S316 and S317 can be found in the detailed descriptions of other embodiments in this disclosure, and will not be repeated here.

[0155] In this embodiment of the disclosure, when the target strategy is easing braking, the second predicted trajectory corresponding to the autonomous driving device at the previous moment adjacent to the current moment is obtained. Then, based on the speed of the end point of the second predicted trajectory and the path planning result of the previous moment, the target easing braking time under different conditions is determined, so that the determined easing braking time is more in line with the current scenario. Thus, the autonomous driving device can be controlled more accurately based on the target easing braking time, which reduces the number of sudden braking while ensuring safety, and improves the traffic efficiency and driving comfort of the autonomous vehicle.

[0156] Figure 4 This is a schematic diagram of the structure of a control device for an unmanned driving device according to an embodiment of the present disclosure;

[0157] like Figure 4 As shown, the control device 400 of the unmanned driving equipment includes:

[0158] The first determining module 410 is used to determine the first position of the unmanned driving device, the first speed of the unmanned driving device, the obstacles around the unmanned driving device and the corresponding first predicted trajectory when the path planning of the unmanned driving device fails at the current time.

[0159] The second determining module 420 is used to determine the target braking strategy corresponding to the unmanned driving equipment based on the first position, the first speed, the obstacle and the corresponding first predicted trajectory.

[0160] The third determining module 430 is used to determine the target braking duration of the unmanned vehicle when the target braking strategy is gentle braking.

[0161] The generation module 440 is used to generate a braking trajectory based on the target braking duration;

[0162] The control module 450 is used to control the unmanned driving equipment based on the braking trajectory.

[0163] In some embodiments of this disclosure, the second determining module 420 is specifically used for:

[0164] At least one point in the corresponding first predicted trajectory is identified as a candidate obstacle if it is located in the direction of travel of the autonomous vehicle within a first preset time period after the current moment and the first distance between it and the autonomous vehicle is less than a first distance threshold.

[0165] The candidate obstacle with the smallest corresponding first distance is identified as the target obstacle;

[0166] Determine the minimum second distance between the target obstacle and the unmanned vehicle within a second preset time period after the current moment, and the relative speed between the target obstacle and the unmanned vehicle at the minimum second distance, wherein the second preset time period is less than the first preset time period;

[0167] If the first ratio between the minimum second distance and the relative speed is greater than or equal to the time threshold, the target braking strategy is determined to be mild braking.

[0168] In some embodiments of this disclosure, the second determining module 420 is specifically used for:

[0169] Obtain the acceleration of the autonomous vehicle at the current moment;

[0170] Based on the acceleration, the first position, and the first velocity, determine the reference trajectory of the unmanned vehicle within the second preset time period;

[0171] The minimum second distance is determined based on the first predicted trajectory of the target obstacle and the reference trajectory of the unmanned vehicle.

[0172] Determine the second speed of the unmanned vehicle and the third speed of the target obstacle at the minimum second distance;

[0173] The relative speed between the unmanned vehicle and the target obstacle is determined based on the second and third speeds.

[0174] In some embodiments of this disclosure, the second determining module 420 is further specifically used for:

[0175] If the first ratio is less than a time threshold, determine the type of the target obstacle;

[0176] If the target obstacle is of type 1, the target braking strategy is determined to be emergency braking.

[0177] In some embodiments of this disclosure, the second determining module 420 is further specifically used for:

[0178] If the target obstacle is of type two, determine the third distance between the target obstacle and the nearest pedestrian crossing;

[0179] If the third distance is less than the second distance threshold, the target braking strategy is determined to be emergency braking; or if the third distance is greater than or equal to the second distance threshold, the target braking strategy is determined to be gradual braking.

[0180] In some embodiments of this disclosure, the third determining module 430 is specifically used for:

[0181] Obtain the second predicted trajectory of the autonomous driving device at the previous moment adjacent to the current moment;

[0182] If the speed at the end of the second predicted trajectory is not zero, obtain the target length of the second predicted trajectory, the preset first parking time, and the first reference coefficient.

[0183] Determine a second ratio between the target length and the first velocity;

[0184] The first product between the second ratio and the first reference coefficient is determined as the second parking duration;

[0185] The minimum of the first and second parking times is determined as the target braking duration.

[0186] In some embodiments of this disclosure, the third determining module 430 is further specifically used for:

[0187] When the speed at the end of the second predicted trajectory is zero, obtain the shortest braking time of the autonomous driving device, the third parking time corresponding to the second predicted trajectory, and the path planning result corresponding to the previous moment.

[0188] If the path planning result is a failure, obtain the total number of consecutive path planning failures adjacent to the current time and the second reference coefficient;

[0189] Determine the first difference between the third parking time and the shortest braking time;

[0190] The target braking duration is determined based on the shortest braking time, the first difference, the total number of braking attempts, and the second reference coefficient.

[0191] In some embodiments of this disclosure, the third determining module 430 is further specifically used for:

[0192] Determine the second product between the first difference, the third reference coefficient, and the target number of failures;

[0193] The sum of the shortest braking time and the first difference is determined as the reference value;

[0194] The second difference between the reference value and the second product is determined as the target braking duration.

[0195] In some embodiments of this disclosure, the third determining module 430 is further specifically used for:

[0196] If the path planning result is successful, obtain the third reference coefficient and the preset first parking duration;

[0197] Determine the third difference between the preset first parking time and the shortest braking time;

[0198] Determine the third product between the third difference and the third reference coefficient;

[0199] The sum of the third product and the shortest braking time is determined as the target easing time.

[0200] It should be noted that the foregoing explanation of the control method for unmanned driving equipment also applies to the control device of the unmanned driving equipment in this embodiment, and will not be repeated here.

[0201] In this embodiment, when path planning failure of the autonomous driving device is detected at the current moment, the first position, first speed, surrounding obstacles, and corresponding first predicted trajectory of the autonomous driving device at the current moment are determined. Then, based on the first position, first speed, obstacles, and corresponding first predicted trajectory, the target braking strategy corresponding to the autonomous driving device is determined. If the target braking strategy is gradual braking, the target gradual braking duration of the autonomous driving device is determined. Then, based on the target gradual braking duration, a gradual braking trajectory is generated. Finally, the autonomous driving device is controlled based on the gradual braking trajectory. Therefore, even when path planning of the autonomous driving device fails at the current moment, the target braking strategy of the autonomous driving device can be accurately determined based on the current state of the autonomous driving device and the state of the surrounding obstacles. If the target braking strategy is gradual braking, the target gradual braking time can be determined, thereby enabling accurate control of the autonomous driving device. This ensures safety while reducing the number of sudden braking events, improving the traffic efficiency and driving comfort of the autonomous vehicle.

[0202] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0203] Figure 5 A schematic block diagram of an example electronic device 500 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0204] like Figure 5 As shown, device 500 includes a computing unit 501, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 502 or a computer program loaded from storage unit 508 into random access memory (RAM) 503. RAM 503 may also store various programs and data required for the operation of device 500. The computing unit 501, ROM 502, and RAM 503 are interconnected via bus 504. Input / output (I / O) interface 505 is also connected to bus 504.

[0205] Multiple components in device 500 are connected to I / O interface 505, including: input unit 506, such as keyboard, mouse, etc.; output unit 507, such as various types of monitors, speakers, etc.; storage unit 508, such as disk, optical disk, etc.; and communication unit 509, such as network card, modem, wireless transceiver, etc. Communication unit 509 allows device 500 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0206] The computing unit 501 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 501 performs the various methods and processes described above, such as the control methods of an autonomous driving device. For example, in some embodiments, the control methods of an autonomous driving device may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on device 500 via ROM 502 and / or communication unit 509. When the computer program is loaded into RAM 503 and executed by the computing unit 501, one or more steps of the control methods of the autonomous driving device described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to perform the control methods of an autonomous driving device by any other suitable means (e.g., by means of firmware).

[0207] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0208] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0209] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0210] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0211] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), the Internet, and blockchain networks.

[0212] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service ecosystem, addressing the shortcomings of traditional physical hosts and VPS (Virtual Private Server, or simply "VPS") services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0213] It should be understood that the various forms of processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0214] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this disclosure, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified. In the description of this disclosure, the words "if" and "suppose" as used may be interpreted as "when," "when," "in response to determination," or "in the circumstances."

[0215] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A control method for an unmanned driving device, comprising: If the path planning of the autonomous driving device fails at the current moment, determine the first position of the autonomous driving device, the first speed of the autonomous driving device, the obstacles around the autonomous driving device and the corresponding first predicted trajectory at the current moment; Based on the first position, the first speed, the obstacle, and the corresponding first predicted trajectory, a target braking strategy for the unmanned driving device is determined, including: At least one point in the corresponding first predicted trajectory is identified as a candidate obstacle if it is located in the direction of travel of the unmanned vehicle within a first preset time period after the current moment and the first distance between it and the unmanned vehicle is less than a first distance threshold. The candidate obstacle with the smallest corresponding first distance is identified as the target obstacle; Determine the minimum second distance between the target obstacle and the unmanned driving device within a second preset time period after the current moment, and the relative speed between the target obstacle and the unmanned driving device at the minimum second distance, wherein the second preset time period is less than the first preset time period; If the first ratio between the minimum second distance and the relative speed is greater than or equal to a time threshold, the target braking strategy is determined to be easing braking. When the target braking strategy is gentle braking, determine the target gentle braking duration of the unmanned driving device; Based on the target braking duration, a braking trajectory is generated; The unmanned driving device is controlled based on the braking trajectory.

2. The method according to claim 1, wherein, The minimum second distance between the target obstacle and the unmanned vehicle within a second preset time period after the current moment is determined, and the relative speed between the target obstacle and the unmanned vehicle at the minimum second distance, include: Obtain the acceleration of the autonomous vehicle at the current moment; Based on the acceleration, the first position, and the first velocity, a reference trajectory of the unmanned driving device is determined within the second preset time period; The minimum second distance is determined based on the first predicted trajectory of the target obstacle and the reference trajectory of the unmanned vehicle. Determine the second speed of the unmanned vehicle and the third speed of the target obstacle at the minimum second distance; The relative speed between the unmanned vehicle and the target obstacle is determined based on the second speed and the third speed.

3. The method according to claim 1, wherein, Also includes: If the first ratio is less than the time threshold, the type of the target obstacle is determined; If the type of the target obstacle is Type 1, the target braking strategy is determined to be emergency braking.

4. The method according to claim 3, wherein, Also includes: If the target obstacle is of type two, determine a third distance between the target obstacle and the nearest pedestrian crossing; If the third distance is less than the second distance threshold, the target braking strategy is determined to be emergency braking; or if the third distance is greater than or equal to the second distance threshold, the target braking strategy is determined to be gradual braking.

5. The method according to claim 1, wherein, Determining the target braking duration of the unmanned vehicle includes: Obtain the second predicted trajectory of the unmanned driving device at the previous time adjacent to the current time. If the speed at the end of the second predicted trajectory is not zero, obtain the target length of the second predicted trajectory, the preset first parking time, and the first reference coefficient. Determine a second ratio between the target length and the first velocity; The first product between the second ratio and the first reference coefficient is determined as the second parking duration; The minimum value between the first parking time and the second parking time is determined as the target braking duration.

6. The method according to claim 5, wherein, Also includes: When the speed at the end of the second predicted trajectory is zero, obtain the shortest braking time of the autonomous driving device, the third parking time corresponding to the second predicted trajectory, and the path planning result corresponding to the previous moment. If the path planning result is a failure, obtain the total number of consecutive path planning failures adjacent to the current time and the second reference coefficient; Determine the first difference between the third parking time and the shortest braking time; The target braking duration is determined based on the shortest braking time, the first difference, the total number of braking attempts, and the second reference coefficient.

7. The method according to claim 6, wherein, The step of determining the target braking duration based on the shortest braking time, the first difference, the total number of braking attempts, and the second reference coefficient includes: Determine the second product between the first difference, the second reference coefficient, and the target number of failures; The sum of the shortest braking time and the first difference is determined as a reference value; The second difference between the reference value and the second product is determined as the target braking duration.

8. The method according to claim 6, wherein, Also includes: If the path planning result is successful, obtain the third reference coefficient and the preset first parking time; Determine a third difference between the preset first parking time and the shortest braking time; Determine the third product between the third difference and the third reference coefficient; The sum of the third product and the shortest braking time is determined as the target easing time.

9. A control device for an unmanned driving system, comprising: The first determining module is used to determine the first position of the autonomous driving device, the first speed of the autonomous driving device, the obstacles around the autonomous driving device and the corresponding first predicted trajectory at the current time when the path planning of the autonomous driving device is detected to be failed at the current time. The second determining module is used to determine the target braking strategy corresponding to the unmanned driving device based on the first position, the first speed, the obstacle and the corresponding first predicted trajectory. The third determining module is used to determine the target braking duration of the unmanned driving device when the target braking strategy is gentle braking. The generation module is used to generate a braking trajectory based on the target braking duration; The control module is used to control the unmanned driving device based on the braking trajectory. The second determining module is specifically used for: At least one point in the corresponding first predicted trajectory is identified as a candidate obstacle if it is located in the direction of travel of the unmanned vehicle within a first preset time period after the current moment and the first distance between it and the unmanned vehicle is less than a first distance threshold. The candidate obstacle with the smallest corresponding first distance is identified as the target obstacle; Determine the minimum second distance between the target obstacle and the unmanned driving device within a second preset time period after the current moment, and the relative speed between the target obstacle and the unmanned driving device at the minimum second distance, wherein the second preset time period is less than the first preset time period; If the first ratio between the minimum second distance and the relative speed is greater than or equal to a time threshold, the target braking strategy is determined to be easing braking.

10. The apparatus according to claim 9, wherein, The second determining module is specifically used for: Obtain the acceleration of the autonomous vehicle at the current moment; Based on the acceleration, the first position, and the first velocity, a reference trajectory of the unmanned driving device is determined within the second preset time period; The minimum second distance is determined based on the first predicted trajectory of the target obstacle and the reference trajectory of the unmanned vehicle. Determine the second speed of the unmanned vehicle and the third speed of the target obstacle at the minimum second distance; The relative speed between the unmanned vehicle and the target obstacle is determined based on the second speed and the third speed.

11. The apparatus according to claim 9, wherein, The second determining module is further specifically used for: If the first ratio is less than the time threshold, the type of the target obstacle is determined; If the type of the target obstacle is Type 1, the target braking strategy is determined to be emergency braking.

12. The apparatus according to claim 11, wherein, The second determining module is further specifically used for: If the target obstacle is of type two, determine a third distance between the target obstacle and the nearest pedestrian crossing; If the third distance is less than the second distance threshold, the target braking strategy is determined to be emergency braking; or if the third distance is greater than or equal to the second distance threshold, the target braking strategy is determined to be gradual braking.

13. The apparatus according to claim 9, wherein, The third determining module is specifically used for: Obtain the second predicted trajectory of the unmanned driving device at the previous time adjacent to the current time. If the speed at the end of the second predicted trajectory is not zero, obtain the target length of the second predicted trajectory, the preset first parking time, and the first reference coefficient. Determine a second ratio between the target length and the first velocity; The first product between the second ratio and the first reference coefficient is determined as the second parking duration; The minimum value between the first parking time and the second parking time is determined as the target braking duration.

14. The apparatus according to claim 13, wherein, The third determining module is further specifically used for: When the speed at the end of the second predicted trajectory is zero, obtain the shortest braking time of the autonomous driving device, the third parking time corresponding to the second predicted trajectory, and the path planning result corresponding to the previous moment. If the path planning result is a failure, obtain the total number of consecutive path planning failures adjacent to the current time and the second reference coefficient; Determine the first difference between the third parking time and the shortest braking time; The target braking duration is determined based on the shortest braking time, the first difference, the total number of braking attempts, and the second reference coefficient.

15. The apparatus according to claim 14, wherein, The third determining module is further specifically used for: Determine the second product between the first difference, the second reference coefficient, and the target number of failures; The sum of the shortest braking time and the first difference is determined as a reference value; The second difference between the reference value and the second product is determined as the target braking duration.

16. The apparatus according to claim 14, wherein, The third determining module is further specifically used for: If the path planning result is successful, obtain the third reference coefficient and the preset first parking time; Determine a third difference between the preset first parking time and the shortest braking time; Determine the third product between the third difference and the third reference coefficient; The sum of the third product and the shortest braking time is determined as the target easing time.

17. An electronic device comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.

18. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-8.

19. A computer program product comprising computer instructions that, when executed by a processor, implement the steps of the method according to any one of claims 1-8.

Images