Vehicle decision planning method and device, electronic equipment and storage medium

Abstract

The application discloses a vehicle decision planning method and device, an electronic device, and a storage medium. The method is applied to a decision planning module in an automatic driving system. The method comprises the following steps: acquiring information of an obstacle in front of a vehicle and lane information of current driving of the vehicle; and determining a corresponding vehicle planning path of the obstacle at different moving speeds based on an inflation factor of transverse or longitudinal change of the obstacle in the lane, the lane information, and the information of the obstacle. The application can further improve the safety, comfort, and driving efficiency of an automatic driving vehicle, especially an automatic driving commercial vehicle, when coping with an overtaking scene.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to a vehicle decision-making and planning method, device, electronic device, and storage medium. Background Technology

[0002] Obstacle avoidance is a very common scenario in the operation of autonomous vehicles. The most representative derivative scenario is overtaking, especially for highway autonomous heavy trucks / new energy heavy trucks in long-haul logistics. Firstly, trucks (commercial vehicles) are longer and wider than passenger cars; secondly, trucks (commercial vehicles) are heavier and more difficult to control when carrying trailers. If the decision-making and planning algorithm is not handled properly, serious traffic accidents may occur during obstacle avoidance.

[0003] In related technologies, when it is necessary to avoid obstacles, commercial vehicles usually need to manually overtake or detour before continuing to drive, which affects the driving efficiency of commercial vehicles. Summary of the Invention

[0004] This application provides vehicle decision-making and planning methods, devices, electronic devices, and storage media to address safety and comfort during overtaking scenarios, while improving driving efficiency.

[0005] The embodiments of this application adopt the following technical solutions:

[0006] In a first aspect, embodiments of this application provide a vehicle decision-making and planning method, applied to a decision-making and planning module in an autonomous driving system, the method comprising:

[0007] Obtain information about obstacles in front of the vehicle and the lane the vehicle is currently traveling in;

[0008] Based on the expansion factor of the obstacle as it changes laterally or longitudinally in the lane, the vehicle's planned path is determined according to the lane information and the obstacle information at different moving speeds.

[0009] In some embodiments, determining the vehicle's planned path at different movement speeds based on the lane information and the obstacle information, according to the expansion factor of the obstacle's lateral or longitudinal changes in the lane, includes:

[0010] Based on the expansion factor of the obstacle as it changes laterally in the lane, the first autonomous vehicle planning path corresponding to the obstacle at the first moving speed is determined according to the lane width in the lane information and the lateral width of the obstacle in the obstacle information.

[0011] And / or,

[0012] Based on the expansion factor of the obstacle's longitudinal change in the lane, and according to the lane width in the lane information and the longitudinal length of the obstacle in the obstacle information, a second vehicle planning path corresponding to the obstacle at the second moving speed is determined, wherein the first moving speed is less than the second moving speed, and the first moving speed is not greater than a first threshold speed, and the second moving speed is greater than the first threshold speed but not greater than the second threshold speed. The first vehicle planning path is used as an obstacle avoidance planning path, and the second vehicle planning path is used as an overtaking planning path.

[0013] In some embodiments, it also includes:

[0014] When the obstacle moves at the second speed, it is determined whether the acceleration of the obstacle is within the acceleration threshold range;

[0015] If present, the third vehicle planning path is adopted, which is used as the following vehicle planning path.

[0016] If not, the second autonomous vehicle will be used to plan the route.

[0017] In some embodiments, obtaining information about obstacles in front of the vehicle and information about the lane the vehicle is currently traveling in includes:

[0018] Based on the upstream module, obtain any one or more of the following information from the obstacle information in front of the vehicle: obstacle type, obstacle position, obstacle speed, obstacle acceleration, obstacle heading angle, and obstacle predicted trajectory;

[0019] Based on a pre-loaded high-precision map, the system obtains the number of lanes ahead and road surface information from the lane information of the vehicle's current driving lane.

[0020] In some embodiments, before determining the vehicle's planned path corresponding to the obstacle at different moving speeds, the method further includes:

[0021] Based on the expansion factor of the obstacle as it changes laterally or longitudinally in the lane, the lane width in the lane information, and the obstacle width or longitudinal length in the obstacle information, the solvable space for lateral or longitudinal movement during obstacle avoidance is determined.

[0022] In some embodiments, the expansion factor of the obstacle as it changes laterally in the lane is a calibration parameter value.

[0023] In some embodiments, the expansion factor of the obstacle's longitudinal change in the lane is determined based on the expected return time parameter of the vehicle to its original lane and the obstacle's current moving speed, wherein the expected return time parameter of the vehicle to its original lane is a calibration parameter value.

[0024] Secondly, embodiments of this application also provide a vehicle decision-making and planning device, wherein the decision-making and planning module is applied in an autonomous driving system, and the device includes:

[0025] The acquisition module is used to acquire information about obstacles in front of the vehicle and the lane information of the vehicle's current driving lane;

[0026] The planning and determination module is used to determine the planned path of the vehicle corresponding to the obstacle at different moving speeds, based on the expansion factor of the obstacle changing laterally or longitudinally in the lane, and according to the lane information and the obstacle information.

[0027] Thirdly, embodiments of this application also provide an electronic device, including: a processor; and a memory arranged to store computer-executable instructions, which, when executed, cause the processor to perform the above-described method.

[0028] Fourthly, embodiments of this application also provide a computer-readable storage medium that stores one or more programs, which, when executed by an electronic device including multiple applications, cause the electronic device to perform the above-described method.

[0029] The at least one technical solution adopted in this application embodiment can achieve the following beneficial effects: by acquiring information about obstacles in front of the vehicle and the current lane information of the vehicle, the vehicle's planned path can be determined based on the expansion factor of the obstacle's lateral or longitudinal changes in the lane, combined with the lane information and the obstacle information. This not only considers the obstacle's movement speed but also obtains a more optimized planned path based on the expansion factor of the obstacle's lateral or longitudinal changes in the lane. Therefore, after the vehicle starts autonomous driving, the decision-making and planning process ensures safety and comfort while improving driving efficiency when avoiding obstacles. Attached Figure Description

[0030] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0031] Figure 1 This is a flowchart illustrating the vehicle decision-making and planning method in the embodiments of this application;

[0032] Figure 2 This is a schematic diagram of an obstacle avoidance and overtaking scenario of the vehicle decision-making and planning method in this application embodiment;

[0033] Figure 3This is a schematic diagram of another obstacle avoidance and overtaking scenario for the vehicle decision-making and planning method in this application embodiment;

[0034] Figure 4 This is a schematic diagram illustrating the implementation principle of the vehicle decision-making and planning method in the embodiments of this application;

[0035] Figure 5 This is a schematic diagram of the vehicle decision-making and planning device in the embodiments of this application;

[0036] Figure 6 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0037] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0038] In autonomous driving systems, the decision-making and planning module is the core module, connecting to the perception module, high-precision map, and localization and prediction module above, and initiating the control module below. Therefore, the quality of the decision-making and planning module directly affects the safety, comfort, and scalability of the autonomous driving system.

[0039] During their research, the inventors discovered that obstacle avoidance is a very common scenario in the operation of autonomous vehicles, with overtaking being the most representative derivative scenario. Generally speaking, obstacle avoidance scenarios involve avoiding static obstacles and following dynamic obstacles, using perception and prediction modules to identify the position and speed of the obstacle vehicle, as well as the obstacle's trajectory over a future period.

[0040] Furthermore, obstacles with low speed and no significant change in position over a period of time are defined as avoidable static obstacles, while obstacles with high speed and significant change in position, for which a future prediction plan is provided, are defined as dynamic obstacles. The output of the existing decision planning is acceleration / deceleration to follow the vehicle, stopping and starting, etc.

[0041] However, avoidance strategies are mostly seen in passenger cars, and from a certain perspective, there are still very few decision-making plans involving avoiding low- and medium-speed obstacles for high-speed heavy trucks.

[0042] In some scenarios, if the road is blocked by low- to medium-speed obstacles for a long time, the driver usually needs to take over based on the judgment of the surrounding environment, manually overtake / detour and continue driving. Moreover, this situation still occurs quite frequently on current urban roads, affecting the driving efficiency of trucks.

[0043] For Level 4 and above autonomous vehicles, the vehicle must ensure safety during obstacle avoidance scenarios. Secondly, it must return to its original lane while maintaining a safe distance. For trucks with trailers traveling at high speeds, sufficient safety distance must be maintained to avoid serious accidents during overtaking. The decision-making and planning module needs to determine the appropriate overtaking timing based on the specific scenario, taking into account the speed of obstacles, and returning to its own lane to complete the overtaking maneuver while ensuring a safe distance, thus minimizing the risks of autonomous driving.

[0044] To address the lack of decision-making and planning schemes for commercial vehicles in autonomous driving systems, this application proposes a path decision-making and planning method for autonomous driving systems capable of overtaking low-to-medium speed obstacle vehicles. Based on the position and movement information of obstacle vehicles ahead of the vehicle provided by a perception and prediction system, the method employs an overtaking strategy for vehicles obstructing traffic or traveling at speeds significantly below the road speed limit within a certain area ahead of the vehicle. During the approach to the target vehicle, the planned path curve of the vehicle is dynamically adjusted, returning to the original lane while ensuring a certain safety margin, thus ensuring safety while also considering comfort and driving efficiency.

[0045] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0046] This application provides a vehicle decision-making and planning method, such as... Figure 1 The diagram shows a schematic flow chart of a vehicle decision-making and planning method in an embodiment of this application. The method includes at least the following steps S120 to S120:

[0047] Step S110: Obtain information about obstacles in front of the vehicle and information about the lane the vehicle is currently traveling in.

[0048] When the autonomous vehicle is traveling on logistics routes or urban roads, there may be obstacles in front of it. After the vehicle initiates the autonomous driving program, the decision-making and planning module begins to receive information from the upstream module.

[0049] Based on the architecture of autonomous driving systems, the decision-making and planning modules within these systems need to obtain information about obstacles ahead. They also need to obtain lane information for the vehicle's current lane.

[0050] In some embodiments, lane information includes at least the number of lanes ahead and road surface information. Information on obstacles ahead of the vehicle includes at least the type of obstacle and its related motion information. This information can be obtained through upstream modules such as high-precision maps and positioning perception modules, and is not specifically limited in the embodiments of this application.

[0051] It is important to note that in order to meet the activation conditions of the decision-making and planning module in an autonomous driving system, there must be at least two lanes; if there is only one lane, the activation conditions will not be met.

[0052] It can also be understood that when the vehicle and the obstacle in front of it are in the same lane, the vehicle travels along the lane centerline, and the obstacle in front of it is also on the lane centerline of the current lane. When avoiding the obstacle, it is also necessary to use either lane-changing overtaking or obstacle-avoiding overtaking within the boundaries of both lanes, where the conditions for using another lane can be met.

[0053] Step S120: Based on the expansion factor of the obstacle as it changes laterally or longitudinally in the lane, and according to the lane information and the obstacle information, determine the vehicle's planned path corresponding to the obstacle at different moving speeds.

[0054] Taking commercial vehicles as an example, they are not only wider in the horizontal direction than small vehicles, but also longer in the vertical direction. In addition, commercial vehicles are heavier and more difficult to control when carrying trailers. Therefore, when avoiding obstacles or overtaking, it is necessary to consider the expansion of obstacles in the horizontal or vertical direction.

[0055] Considering that obstacles in front of the vehicle move at different speeds, affecting the vehicle's decision-making and planning process, it's necessary to categorize and consider the speed of these obstacles. If the obstacle is moving at a low speed, the decision-making and planning strategy will differ from that used when it's moving at a medium to low speed. In other words, the planned path obtained in the decision-making and planning module of the autonomous driving system will not be the same and can be determined based on the actual situation of the obstacles in front of the vehicle.

[0056] Based on the expansion factor of the obstacle as it changes laterally or longitudinally in the lane, the safety and comfort of the vehicle when overtaking can be guaranteed. At the same time, the corresponding planned path of the vehicle can be obtained according to the obstacle at different moving speeds, which can improve driving efficiency and eliminate the need for frequent intervention by the commercial vehicle driver.

[0057] In the above method, a corresponding overtaking strategy can be adopted for vehicles that are blocking traffic or moving at speeds significantly lower than the road section (the obstacles are moving at different speeds) located in a certain area in front of the vehicle. During the process of approaching the target vehicle, the planned path curve of the vehicle is dynamically adjusted (based on the expansion factor of the lateral or longitudinal changes of the obstacle in the lane). Under the premise of ensuring a certain safety range, the vehicle returns to its original lane, ensuring safety while taking into account comfort and driving efficiency.

[0058] In one embodiment of this application, determining the vehicle planning path corresponding to the obstacle at different moving speeds based on the expansion factor of the obstacle's lateral or longitudinal changes in the lane, according to the lane information and the obstacle information, includes: determining a first vehicle planning path corresponding to the obstacle at a first moving speed based on the expansion factor of the obstacle's lateral changes in the lane, according to the lane width in the lane information and the lateral width of the obstacle in the obstacle information; and / or, determining a second vehicle planning path corresponding to the obstacle at a second moving speed based on the expansion factor of the obstacle's longitudinal changes in the lane, according to the lane width in the lane information and the longitudinal length of the obstacle in the obstacle information, wherein the first moving speed is less than the second moving speed, and the first moving speed is not greater than a first threshold speed, and the second moving speed is greater than the first threshold speed but not greater than the second threshold speed, the first vehicle planning path is used as an obstacle avoidance planning path, and the second vehicle planning path is used as an overtaking planning path.

[0059] Please refer to Figure 2 Where 's' represents the longitudinal direction of vehicle travel, and 'l' represents the direction perpendicular to the path. The road boundary is used as the solution space for the planned path, the lane centerline as the reference line upon which the planning is based, and the line segment buffer represents the outward expansion dimension of the static target vehicle. Since the obstacle ahead is considered a static obstacle, obstacle avoidance requires maintaining a certain longitudinal safety distance, therefore only 'l' is needed. buffer The longitudinal obstacle dimensions are based on the perceived output. At this time, based on the expansion factor of the obstacle's lateral change in the lane, and according to the lane width in the lane information and the lateral width of the obstacle in the obstacle information, the first autonomous vehicle planning path corresponding to the obstacle at the first moving speed is determined.

[0060] Furthermore, before the decision-making and planning module in the autonomous driving system makes its decisions, it needs to determine the current lane information and the information of obstacles ahead. If it receives information that there are two or more lanes ahead, the obstacle is a vehicle, and its speed is lower than a certain target speed (5km / h), then it is regarded as a static target vehicle. Based on the driving status of the vehicle, an obstacle avoidance path is planned, and after obstacle avoidance is completed, the vehicle returns to the path where the original reference line (the reference line is located and generated in the upstream high-precision map module) is located.

[0061] The target speed mentioned above is the anchor speed, which can be configured or selected according to the actual use scenario of those skilled in the art, and is not specifically limited in the embodiments of this application.

[0062] For example, after determining the type of obstacle and its moving speed, if the obstacle in front of the vehicle is considered to be a vehicle and the vehicle is moving at a low speed, then based on the expansion factor of the obstacle's lateral change in the lane, a solution space is established according to the lane width in the lane information and the lateral width of the obstacle in the obstacle information, and then the planned path to avoid the obstacle corresponding to the obstacle at a low speed is determined.

[0063] Please refer to Figure 3 Where 's' is the longitudinal direction of vehicle travel, and 'l' is the direction perpendicular to the path. It is still necessary to follow... Figure 2 The overtaking solution space Road Bound is calculated using the method described above. Furthermore, because the obstacle being overtaken is dynamic, the timing of returning to the vehicle's original lane after overtaking needs to be considered, in addition to lateral expansion of the obstacle. buffer In addition, longitudinal expansion is needed based on the speed of the obstacle vehicle perceived in the system to ensure the truck does not collide with it when returning to its lane. This requires determining not only the first planned path for the vehicle at the first moving speed based on the expansion factor of the obstacle's lateral change within the lane, according to the lane width and the obstacle's lateral width in the lane information, but also the second planned path for the vehicle at the second moving speed based on the expansion factor of the obstacle's longitudinal change within the lane, according to the lane width and the obstacle's longitudinal length in the lane information. In other words, the system considers not only the obstacle avoidance path but also the overtaking path after obstacle avoidance.

[0064] Furthermore, before the decision-making and planning module in the autonomous driving system performs its decision-making and planning, it is necessary to determine the current lane information and the information of obstacles ahead. If it receives information that there are two or more lanes ahead, the obstacle is a vehicle, and its speed is higher than a certain target speed but lower than the vehicle's speed (5km / h~40km / h), then it is considered a dynamic target vehicle. The acceleration 'a' of the target vehicle is determined based on the perception output. obs The system determines whether to overtake or follow the vehicle in front, based on whether the target vehicle's current acceleration is significant or exceeds a certain set range. If the target vehicle's current acceleration is high, to ensure safety—that is, to avoid overtaking an accelerating vehicle—the traditional following strategy is adopted, and a following route is planned. If the target vehicle's current acceleration is within the set range, an overtaking lane strategy is used.

[0065] The aforementioned vehicle speed, used as a standard for judging the moving speed of obstacles, can be selected according to the actual usage scenario. The first moving speed (low speed) is less than the second moving speed (medium-low speed or high speed), and the first moving speed is not greater than a first threshold speed (e.g., 5 km / h), while the second moving speed is greater than the first threshold speed (e.g., 5 km / h) but not greater than the second threshold speed (e.g., 40 km / h), i.e., within the range of 5 km / h to 40 km / h.

[0066] The first vehicle planning path is used as an obstacle avoidance planning path, and the second vehicle planning path is used as an overtaking planning path.

[0067] Please continue to refer to this. Figure 3 Based on the vehicle's driving status and the driving status of obstacles (type: vehicles), an overtaking path curve can be planned. Please continue to refer to [the documentation / reference]. Figure 2 Based on the vehicle's driving status, a path for obstacle avoidance is planned, and after avoiding (stationary) obstacles, the vehicle returns to the path where the original reference line is located.

[0068] The methods described above, when implementing obstacle avoidance decision-making for low-speed target vehicles, place greater emphasis on lateral safety distance considerations. For high-speed target vehicles that obstruct the driver's normal driving, the overtaking decision-making not only considers lateral distance but also the longitudinal safety distance required when the truck carries a trailer, given its increased overall size. Furthermore, the longitudinal distance can be dynamically adjusted based on the target vehicle's speed, as well as the timing of returning to the driver's original lane, making it more rational and safer. Moreover, the core of both decision-making methods (obstacle avoidance path planning and overtaking path planning) can be supported by the same algorithm, representing a lightweight and flexible development strategy.

[0069] In one embodiment of this application, the method further includes: when the obstacle is moving at a second speed, determining whether the acceleration of the obstacle is within an acceleration threshold range; if it is, then using a third vehicle planning path, the third vehicle planning path being used as a following vehicle planning path; if it is not, then using a second vehicle planning path.

[0070] In practice, the system determines whether to overtake or follow the target vehicle based on the perception output, considering whether the target vehicle's acceleration (a_obs) is too high, exceeding a certain set range. If the target vehicle's current acceleration is high, to ensure safety (i.e., not overtaking an accelerating vehicle), a traditional following strategy is adopted, and a following path is planned. If the target vehicle's current acceleration is within the set range, an overtaking lane strategy is used.

[0071] It is important to note that the traditional following strategy involves following the vehicle in the planning and decision-making module according to the following mode, which means maintaining a safe distance from obstacles in the same lane as the vehicle currently traveling.

[0072] In one embodiment of this application, obtaining information about obstacles in front of the vehicle and information about the lane the vehicle is currently traveling in includes: obtaining any one or more of the following information from the obstacle information in front of the vehicle: obstacle type, obstacle position, obstacle speed, obstacle acceleration, obstacle heading angle, and obstacle predicted trajectory, according to the upstream module; and obtaining the number of lanes ahead and road surface information from the lane information the vehicle is currently traveling in, according to the pre-loaded high-precision map.

[0073] In practice, the decision-making and planning module in the autonomous driving system obtains the number of lanes ahead and route information from a high-precision map, as well as information from the perception and prediction module, including but not limited to obstacle type, obstacle position, obstacle speed, obstacle acceleration, obstacle heading, and predicted obstacle trajectory over a future period.

[0074] In one embodiment of this application, before determining the vehicle planning path corresponding to the obstacle at different moving speeds, the method further includes: determining the solvable space in the lateral or longitudinal direction during obstacle avoidance based on the expansion factor of the obstacle changing laterally or longitudinally in the lane, the lane width in the lane information, and the obstacle width or longitudinal length in the obstacle information.

[0075] The above method fully considers the traffic congestion or overtaking difficulties frequently encountered by autonomous trucks in long-haul logistics. It rationally sets lateral and longitudinal safety distances during overtaking and avoidance, and dynamically considers the different time and distance required to overtake obstacles at different speeds, taking into account the solvable space of the entire overtaking and avoidance process. When the obstacle is stationary, the lateral expansion scale of the obstacle still needs to be considered. When avoiding obstacles, it is necessary to use another lane to avoid them and return to the autonomous vehicle's lane.

[0076] For specific implementation, please continue to refer to... Figure 2 The formula for calculating the lateral solvable space during obstacle avoidance is:

[0077]

[0078] Where lane_width is the width of the lane output by the map positioning module, l obs The width of the target vehicle output by the sensing module, l buffer The lateral expansion dimension of the target vehicle.

[0079] Furthermore, within this solution space, common methods such as polynomial fitting or constructing a numerical optimization problem and then solving for the optimization variables are used to solve the path planning curve, thereby achieving obstacle avoidance. buffer The calibration value can be modified based on the vehicle's dimensions and the desired longitudinal distance, greatly enhancing flexibility. It is understood that the methods used to solve path planning curves, such as polynomial fitting or constructing a numerical optimization problem and then solving for the optimization variables, are well-known to those skilled in the art and will not be elaborated further. In other words, the calculation method for the path curve can employ common methods such as polynomial fitting or constructing a numerical optimization problem and then solving for the optimization variables.

[0080] When the speed of the obstacle in front of your vehicle is greater than 5 km / h but less than 40 km / h, meaning the obstacle is traveling at low to medium speed or high speed but causing a blockage, please continue to refer to [the relevant documentation]. Figure 3 The formula for calculating the longitudinal length S of the obstacle vehicle when overtaking is:

[0081] S = s obs +s buffer

[0082] Among them, s obs To sense the longitudinal length of the target vehicle, s buffer This represents the longitudinal expansion dimension. Wherein,

[0083] s buffer =V obs *K previewtime

[0084] S = s obs +V obs *K previewtime

[0085] Among them, V obs The current speed of the obstacle is perceived and output, and its value is less than the speed of the autonomous vehicle, V, K. previewtime This is the expected time parameter for returning to the vehicle's original lane. Considering that commercial vehicles often have trailers and cargo boxes, the longitudinal distance is relatively long. When the obstacle is not stationary and travels at high speed, the longitudinal and lateral expansion dimensions of the obstacle must be considered. When avoiding an obstacle, it is necessary to overtake by using another vehicle's lane and return to the vehicle's own lane.

[0086] It is important to note that the purpose of doing so is twofold: firstly, to adopt the logic and corresponding algorithm for avoiding static obstacles by using the lane; and secondly, to longitudinally expand the target vehicle of the obstacle. The expansion size is a variable that increases with the target vehicle's speed. This makes it possible to overtake low-to-medium speed vehicles in trunk logistics scenarios. Furthermore, it takes into account the situation of driving with a trailer, leaving sufficient safety distance to ensure that the trailer can straighten during the overtaking process (the trailer of the commercial vehicle also returns to the lane). After overtaking, the trailer returns to its original lane to prevent rear-end collisions with vehicles behind.

[0087] In one embodiment of this application, the expansion factor of the obstacle as it changes laterally in the lane is a calibration parameter value.

[0088] In one embodiment of this application, the expansion factor of the obstacle's longitudinal change in the lane is determined based on the expected return time parameter of the vehicle to its original lane and the current moving speed of the obstacle, wherein the expected return time parameter is a calibration parameter value.

[0089] The overall execution process is as follows: Figure 4 As shown, the lateral expansion dimension l of the target vehicle buffer The width of the lane output by the map positioning module. ane_width The expected time parameter K for returning to the original lane. previewtime These are all calibration parameters. For example... Figure 4 The execution flow is as follows:

[0090] Step S1: Receive obstacle target information and lane information from the upstream module.

[0091] Step S2: Determine if the target is a vehicle and if there are multiple lanes. If so, proceed to step S3.

[0092] Step S3: Determine if the obstacle's speed is less than the target's speed. If so, proceed to step S7.

[0093] Step S4: If not, determine whether the target vehicle speed acceleration is greater than the set value. If yes, proceed to step S8. Otherwise, proceed to step S5.

[0094] Step S5: If not, adopt a bypass strategy for the target.

[0095] Step S6: Plan the path curve for the vehicle to overtake by using other vehicles.

[0096] If two or more lanes are detected ahead, the obstacle is a vehicle, and its speed is higher than a target speed but lower than the vehicle's own speed (e.g., 5 km / h to 40 km / h), then it is considered a dynamic target vehicle. The acceleration 'a' of the target vehicle is determined based on the perception output. obsThe decision to overtake or follow a vehicle is determined by whether the target vehicle's current acceleration is significant and exceeds a certain set range. If the target vehicle's current acceleration is significant, to ensure safety—that is, to avoid overtaking an accelerating vehicle—a traditional following strategy is adopted, and a following route is planned. If the target vehicle's current acceleration is within the set range, an overtaking lane strategy is used.

[0097] Based on the driving status of the vehicle and the target vehicle, a path curve is planned for overtaking, as shown in the scenario. Figure 3 As shown, the 's' direction is the longitudinal direction of vehicle travel, and the 'l' direction is perpendicular to the path. The overtaking solution space Road Bound still needs to be calculated, using the same formula as above. Furthermore, because the obstacle being overtaken is dynamic, the timing of returning to the original lane after overtaking needs to be considered, in addition to expanding the obstacle laterally by l. buffer In addition, the longitudinal expansion needs to be calculated based on the speed of the obstacle vehicle sensed to ensure the truck does not collide with it when returning to its lane. The formula for calculating the longitudinal length S of the obstacle vehicle during overtaking is:

[0098] S = s obs +s buffer In the formula, s obs To sense the longitudinal length of the target vehicle, s buffer s represents the longitudinal expansion dimension. buffer =V obs *K previewtime That is, S = s obs+ V obs *K previewtime .

[0099] Step S7: If yes, collect obstacle avoidance strategies for the target and plan the path curve for the vehicle to avoid it by using other lanes.

[0100] like Figure 2 As shown, if there are two or more lanes ahead, the obstacle is a vehicle, and its speed is lower than a certain target speed, such as 5 km / h, then it is considered a static target vehicle. A path for obstacle avoidance is planned based on the vehicle's driving status, and after obstacle avoidance is completed, the vehicle returns to the original path where the reference line was located.

[0101] The formula for calculating the lateral solvable space during obstacle avoidance is as follows:

[0102]

[0103] In the formula, lane_width is the width of the lane output by the map positioning module, l obs To sense the width of the target vehicle, l buffer The lateral expansion dimension of the target vehicle.

[0104] Within this solution space, common methods such as polynomial fitting or constructing a numerical optimization problem and then solving for the optimization variables are used to solve the path planning curve, thereby achieving obstacle avoidance. buffer The calibration value can be modified according to the vehicle's dimensions and the desired longitudinal distance, greatly enhancing flexibility.

[0105] Step S8: Adopt the traditional following strategy to avoid the path curve of the self-following vehicle.

[0106] The above process takes into full account the traffic congestion or inability to overtake that autonomous trucks often encounter in trunk logistics. By reasonably setting the lateral and longitudinal safety distances during the overtaking and avoidance process, and considering the different time and distance required to overtake obstacles of different speeds, the solution space of the entire overtaking and avoidance process is dynamically considered.

[0107] This application also provides a vehicle decision-making and planning device 500, such as... Figure 5 The diagram shows a structural schematic of a vehicle decision-making and planning device in an embodiment of this application. The vehicle decision-making and planning device 500 includes at least: an acquisition module 510 and a planning determination module 520, wherein:

[0108] In one embodiment of this application, the acquisition module 510 is specifically used to: acquire information about obstacles in front of the vehicle and information about the lane the vehicle is currently traveling in.

[0109] When the autonomous vehicle is traveling on logistics routes or urban roads, there may be obstacles in front of it. After the vehicle initiates the autonomous driving program, the decision-making and planning module begins to receive information from the upstream module.

[0110] Based on the architecture of autonomous driving systems, the decision-making and planning modules within these systems need to obtain information about obstacles ahead. They also need to obtain lane information for the vehicle's current lane.

[0111] In some embodiments, lane information includes at least the number of lanes ahead and road surface information. Information on obstacles ahead of the vehicle includes at least the type of obstacle and its related motion information. This information can be obtained through upstream modules such as high-precision maps and positioning perception modules, and is not specifically limited in the embodiments of this application.

[0112] It is important to note that in order to meet the activation conditions of the decision-making and planning module in an autonomous driving system, there must be at least two lanes; if there is only one lane, the activation conditions will not be met.

[0113] It can also be understood that when the vehicle and the obstacle in front of it are in the same lane, the vehicle travels along the lane centerline, and the obstacle in front of it is also on the lane centerline of the current lane. When avoiding the obstacle, it is also necessary to use either lane-changing overtaking or obstacle-avoiding overtaking within the boundaries of both lanes, where the conditions for using another lane can be met.

[0114] In one embodiment of this application, the planning and determination module 520 is specifically used to: determine the vehicle planning path corresponding to the obstacle at different moving speeds based on the expansion factor of the obstacle changing laterally or longitudinally in the lane, according to the lane information and the obstacle information.

[0115] Taking commercial vehicles as an example, they are not only wider in the horizontal direction than small vehicles, but also longer in the vertical direction. In addition, commercial vehicles are heavier and more difficult to control when carrying trailers. Therefore, when avoiding obstacles or overtaking, it is necessary to consider the expansion of obstacles in the horizontal or vertical direction.

[0116] Considering that obstacles in front of the vehicle move at different speeds, affecting the vehicle's decision-making and planning process, it's necessary to categorize and consider the speed of these obstacles. If the obstacle is moving at a low speed, the decision-making and planning strategy will differ from that used when it's moving at a medium to low speed. In other words, the planned path obtained in the decision-making and planning module of the autonomous driving system will not be the same and can be determined based on the actual situation of the obstacles in front of the vehicle.

[0117] Based on the expansion factor of the obstacle as it changes laterally or longitudinally in the lane, the safety and comfort of the vehicle when overtaking can be guaranteed. At the same time, the corresponding planned path of the vehicle can be obtained according to the obstacle at different moving speeds, which can improve driving efficiency and eliminate the need for frequent intervention by the commercial vehicle driver.

[0118] It is understood that the above-mentioned vehicle decision-making and planning device can realize each step of the vehicle decision-making and planning method provided in the foregoing embodiments. The relevant explanations of the vehicle decision-making and planning method are applicable to the vehicle decision-making and planning device, and will not be repeated here.

[0119] Figure 6 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Please refer to it. Figure 6 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and memory. The memory may include main memory, such as high-speed random-access memory (RAM), or non-volatile memory, such as at least one disk drive. Of course, the electronic device may also include other hardware required for other business operations.

[0120] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 6 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0121] Memory is used to store programs. Specifically, programs may include program code, which includes computer operation instructions. Memory may include main memory and non-volatile memory, and provides instructions and data to the processor.

[0122] The processor reads the corresponding computer program from non-volatile memory into main memory and then executes it, forming a vehicle decision-making and planning device at the logical level. The processor executes the program stored in memory and specifically performs the following operations:

[0123] Obtain information about obstacles in front of the vehicle and the lane the vehicle is currently traveling in;

[0124] Based on the expansion factor of the obstacle as it changes laterally or longitudinally in the lane, the vehicle's planned path is determined according to the lane information and the obstacle information at different moving speeds.

[0125] The above is as stated in this application. Figure 1The method executed by the vehicle decision-making and planning device disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0126] The electronic device can also perform Figure 1 The method for executing the vehicle decision-making and planning device, and the realization of the vehicle decision-making and planning device in Figure 1 The functions of the embodiments shown are not described in detail here.

[0127] This application also proposes a computer-readable storage medium that stores one or more programs, the programs including instructions that, when executed by an electronic device including multiple applications, enable the electronic device to perform... Figure 1 The method executed by the vehicle decision-making and planning device in the illustrated embodiment is specifically used to perform:

[0128] Obtain information about obstacles in front of the vehicle and the lane the vehicle is currently traveling in;

[0129] Based on the expansion factor of the obstacle as it changes laterally or longitudinally in the lane, the vehicle's planned path is determined according to the lane information and the obstacle information at different moving speeds.

[0130] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0131] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will 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 program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0132] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0133] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0134] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0135] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0136] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0137] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0138] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0139] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A vehicle decision-making and planning method, wherein, The method, applied to a decision-making and planning module in an autonomous driving system, includes: Obtain information about obstacles in front of the vehicle and the lane the vehicle is currently traveling in; Based on the expansion factor of the obstacle as it changes laterally or longitudinally in the lane, the vehicle's planned path is determined according to the lane information and the obstacle information at different moving speeds. The method of determining the vehicle's planned path at different moving speeds based on the expansion factor of the obstacle's lateral or longitudinal changes in the lane, according to the lane information and the obstacle information, includes: Based on the expansion factor of the obstacle as it changes laterally in the lane, the first autonomous vehicle planning path corresponding to the obstacle at the first moving speed is determined according to the lane width in the lane information and the lateral width of the obstacle in the obstacle information. Based on the expansion factor of the obstacle's longitudinal change in the lane, and according to the lane width in the lane information and the longitudinal length of the obstacle in the obstacle information, a second vehicle planning path corresponding to the obstacle at the second moving speed is determined, wherein the first moving speed is less than the second moving speed, and the first moving speed is not greater than a first threshold speed, and the second moving speed is greater than the first threshold speed but not greater than the second threshold speed. The first vehicle planning path is used as an obstacle avoidance planning path, and the second vehicle planning path is used as an overtaking planning path. Before determining the vehicle's planned path for the obstacle at different moving speeds, the method further includes: Based on the expansion factor of the obstacle's lateral or longitudinal changes in the lane, the lane width in the lane information, and the obstacle width or longitudinal length in the obstacle information, the solvable space for lateral or longitudinal changes during obstacle avoidance is determined. The expansion factor of the obstacle's lateral changes in the lane is a calibration parameter value. The expansion factor of the obstacle's longitudinal changes in the lane is determined based on the expected return time parameter to the vehicle's original lane and the obstacle's current moving speed. The expected return time parameter to the vehicle's original lane is a calibration parameter value. The formula for calculating the longitudinal length S of the obstacle vehicle when overtaking is: S = sobs + sbuffer Where sobs is the longitudinal length of the target vehicle in the perception output, and sbuffer is the longitudinal expansion dimension.

2. The method as described in claim 1, wherein, Also includes: When the obstacle moves at the second speed, it is determined whether the acceleration of the obstacle is within the acceleration threshold range; If present, the third vehicle planning path is adopted, which is used as the following vehicle planning path. If not, the second autonomous vehicle will be used to plan the route.

3. The method as described in claim 1, wherein, The acquisition of information about obstacles in front of the vehicle and the current lane information of the vehicle includes: Based on the upstream module, obtain any one or more of the following information from the obstacle information in front of the vehicle: obstacle type, obstacle position, obstacle speed, obstacle acceleration, obstacle heading angle, and obstacle predicted trajectory; Based on a pre-loaded high-precision map, the system obtains the number of lanes ahead and road surface information from the lane information of the vehicle's current driving lane.

4. A vehicle decision-making and planning device, wherein, A decision-making and planning module applied in an autonomous driving system, the device comprising: The acquisition module is used to acquire information about obstacles in front of the vehicle and the lane information of the vehicle's current driving. The planning and determination module is used to determine the planned path of the vehicle corresponding to the obstacle at different moving speeds based on the expansion factor of the obstacle changing laterally or longitudinally in the lane, according to the lane information and the obstacle information. The method of determining the vehicle's planned path at different moving speeds based on the expansion factor of the obstacle's lateral or longitudinal changes in the lane, according to the lane information and the obstacle information, includes: Based on the expansion factor of the obstacle as it changes laterally in the lane, the first autonomous vehicle planning path corresponding to the obstacle at the first moving speed is determined according to the lane width in the lane information and the lateral width of the obstacle in the obstacle information. Based on the expansion factor of the obstacle's longitudinal change in the lane, and according to the lane width in the lane information and the longitudinal length of the obstacle in the obstacle information, a second vehicle planning path corresponding to the obstacle at the second moving speed is determined, wherein the first moving speed is less than the second moving speed, and the first moving speed is not greater than a first threshold speed, and the second moving speed is greater than the first threshold speed but not greater than the second threshold speed. The first vehicle planning path is used as an obstacle avoidance planning path, and the second vehicle planning path is used as an overtaking planning path. Before determining the vehicle's planned path for the obstacle at different moving speeds, the method further includes: Based on the expansion factor of the obstacle's lateral or longitudinal changes in the lane, the lane width in the lane information, and the obstacle width or longitudinal length in the obstacle information, the solvable space for lateral or longitudinal changes during obstacle avoidance is determined. The expansion factor of the obstacle's lateral changes in the lane is a calibration parameter value. The expansion factor of the obstacle's longitudinal changes in the lane is determined based on the expected return time parameter to the vehicle's original lane and the obstacle's current moving speed. The expected return time parameter to the vehicle's original lane is a calibration parameter value. The formula for calculating the longitudinal length S of the obstacle vehicle when overtaking is: S = sobs + sbuffer Where sobs is the longitudinal length of the target vehicle in the perception output, and sbuffer is the longitudinal expansion dimension.

5. An electronic device, comprising: processor; as well as A memory configured to store computer-executable instructions, which, when executed, cause the processor to perform the method of any one of claims 1 to 3.

6. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of applications, cause the electronic device to perform the method of any one of claims 1 to 3.

Images