Active speed limiting system and method for autonomous vehicle

Abstract

The invention discloses an active speed limiting system and method for an automatic driving vehicle, which are used for solving the problem of how to enable the automatic driving vehicle to flexibly adjust the driving speed according to a real-time environment on the premise of obeying traffic laws and regulations. The active speed limiting system comprises a planner, a controller, a sensor and a high-precision map, wherein the controller, the sensor and the high-precision map are connected with the planner. The road condition of the automatic driving vehicle is sensed through the sensor, and peripheral obstacle information is generated and transmitted to the planner; map information of the autonomous vehicle is obtained from the high-precision map through a planner, risk speed limit information is calculated based on surrounding obstacle information, a driving track is generated in combination with the risk speed limit information and the map information, and the driving track is converted into a control instruction to be issued to a controller so that the controller can execute an active speed limit action based on the control instruction.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to an active speed limiting system for an autonomous driving vehicle, an active speed limiting method for an autonomous driving vehicle, an electronic device, and a storage medium. Background Art

[0002] Autonomous vehicles on public roads typically strictly adhere to speed limits posted on traffic signs or relevant traffic regulations. These speed limits are typically pre-set based on static road attributes (such as road grade and functional zoning). The system utilizes onboard cameras, sensors, and map data to identify and respond to speed limits posted on traffic signs in real time. However, in certain circumstances, such as on roads without speed limit signs, autonomous vehicles may operate according to the maximum permitted speed for the road.

[0003] In reality, speed limit information obtained from road signs or road regulations is inherently mechanical and static, often failing to adapt well to complex and dynamic road environments. For example, during actual driving, factors such as road traffic conditions, pedestrian density, and vehicle volume can all affect safe driving speeds. Traditional speed limit mechanisms are often unable to adapt to these changes in real time.

[0004] Therefore, how to enable autonomous vehicles to flexibly adjust their driving speed according to the real-time environment while complying with traffic regulations has become an important issue that needs to be addressed in current technological development and lawmaking. Summary of the Invention

[0005] The present invention provides an active speed limit system for an autonomous driving vehicle, an active speed limit method for an autonomous driving vehicle, an electronic device, and a storage medium, which are used to solve or partially solve the technical problem of how to enable an autonomous driving vehicle to flexibly adjust its driving speed according to the real-time environment while complying with traffic regulations.

[0006] The present invention provides an active speed limiting system for an autonomous driving vehicle, the active speed limiting system comprising a planner, a controller connected to the planner, a sensor, and a high-precision map; wherein,

[0007] The sensor is configured to sense the road conditions of the autonomous vehicle, generate surrounding obstacle information, and transmit the surrounding obstacle information to the planner;

[0008] The planner is configured to obtain map information of the autonomous driving vehicle from the high-precision map, calculate risk speed limit information based on the surrounding obstacle information, generate a driving trajectory based on the risk speed limit information and the map information, and convert the driving trajectory into a control instruction and send it to the controller, so that the controller can perform an active speed limit action based on the control instruction.

[0009] Optionally, the surrounding obstacle information includes static obstacle information and dynamic obstacle information; and the planner is specifically configured to:

[0010] Obtaining vehicle speed limit information, current operating route, current driving scenario, and vehicle planned path of the autonomous driving vehicle;

[0011] Obtaining preset global speed limit information based on the current operating route, and obtaining preset scenario speed limit information based on the current driving scenario;

[0012] Determining the autonomous driving state of the autonomous driving vehicle and determining abnormal state speed limit information based on the determination result;

[0013] Calculating curvature speed limit information of the planned vehicle path;

[0014] According to the planned vehicle path, discrete sampling point analysis is performed in combination with the static obstacle information and the dynamic obstacle information to obtain narrow path speed limit information, static obstacle speed limit information, dynamic obstacle speed limit information, and courtesy speed limit information;

[0015] The vehicle speed limit information, the global speed limit information, the scene speed limit information, the abnormal state speed limit information, the curvature speed limit information, the narrow path speed limit information, the static obstacle speed limit information, the dynamic obstacle speed limit information and the courtesy speed limit information are comprehensively smoothed, and the speed limit information obtained after the smoothing process is used as the risk speed limit information.

[0016] Optionally, the planner is specifically configured to:

[0017] Determining the autonomous driving state of the autonomous driving vehicle according to the abnormal status code;

[0018] When the driving state of the automatic driving vehicle is normal, determining that the abnormal state speed limit information is empty;

[0019] When the driving state of the autonomous driving vehicle is abnormal, the preset speed limit information under the abnormal state is obtained as the abnormal state speed limit information of the autonomous driving vehicle in the current driving scenario.

[0020] Optionally, the high-precision map is in communication with the sensor; the sensor is further configured to locate the position of the autonomous driving vehicle in the high-precision map; and the planner is specifically configured to:

[0021] discretely sampling the planned vehicle path to obtain a plurality of path sampling points;

[0022] For each sampling point on the path:

[0023] Calculating the boundary width of the path at the path sampling point, and obtaining preset narrow path speed limit information according to the boundary width;

[0024] Extracting at least one static obstacle located at and around the path sampling point from the static obstacle information, and obtaining static obstacle speed limit information by traversing each of the static obstacles;

[0025] Extracting at least one dynamic obstacle located at and around the path sampling point, and a predicted obstacle trajectory of the at least one dynamic obstacle from the dynamic obstacle information, and obtaining dynamic obstacle speed limit information by traversing each of the dynamic obstacles based on the predicted obstacle trajectory;

[0026] A map element of the path sampling point is obtained, a courtesy judgment is performed based on the map element and in combination with the at least one dynamic obstacle, and courtesy speed limit information is obtained according to the courtesy judgment result.

[0027] Optionally, the map information includes lane speed limit information; and the planner is specifically configured to:

[0028] Combining the risk speed limit information and the lane speed limit information, a final driving trajectory of the autonomous driving vehicle is generated through planning and solving.

[0029] Optionally, the controller is communicatively connected to a chassis of the autonomous driving vehicle; the controller is specifically configured to:

[0030] The control instruction sent by the planner is received, and the control instruction is converted into an actual control action for the vehicle chassis, so that the vehicle chassis performs corresponding active speed limit based on the actual control action.

[0031] Optionally, the actual control actions include at least acceleration, braking, a left turn lever, and a right turn lever.

[0032] The present invention also provides a method for active speed limiting of an autonomous vehicle, the method being applied to the active speed limiting system of an autonomous vehicle as described in any of the preceding items, the active speed limiting system comprising a planner, a controller respectively connected to the planner, a sensor, and a high-precision map; the method comprising:

[0033] sensing the road condition of the autonomous driving vehicle through the sensor, generating surrounding obstacle information, and transmitting the surrounding obstacle information to the planner;

[0034] The planner obtains map information of the autonomous driving vehicle from the high-precision map, calculates risk speed limit information based on the surrounding obstacle information, generates a driving trajectory by combining the risk speed limit information and the map information, and converts the driving trajectory into a control instruction and sends it to the controller, so that the controller can perform active speed limit actions based on the control instruction.

[0035] The present invention further provides an electronic device, comprising a processor and a memory:

[0036] The memory is used to store program code and transmit the program code to the processor;

[0037] The processor is used to execute the active speed limiting method for the autonomous driving vehicle as described above according to the instructions in the program code.

[0038] The present invention also provides a computer-readable storage medium, which is used to store program code, and the program code is used to execute the active speed limiting method for the autonomous driving vehicle as described above.

[0039] It can be seen from the above technical solutions that the present invention has the following advantages:

[0040] An active speed limit system and method for autonomous vehicles are provided. The active speed limit system includes a planner, a controller connected to the planner, sensors, and a high-precision map. The sensors sense the road conditions of the autonomous vehicle, generate surrounding obstacle information, and transmit this information to the planner. The planner obtains the autonomous vehicle's map information from the high-precision map, calculates risky speed limit information based on the surrounding obstacle information, combines the risky speed limit information with the map information to generate a driving trajectory, and converts the driving trajectory into control instructions that are transmitted to the controller, which then executes active speed limit actions based on the control instructions. Thus, by real-time sensing of the road environment surrounding the autonomous vehicle, risk areas are determined to predict potential risks within the autonomous vehicle's future driving trajectory. Furthermore, to reduce risks, an active speed limit strategy is designed by comprehensively considering environmental conditions. Reasonable speed limits provide sufficient safety margins, enabling autonomous vehicles on public roads to use defensive driving to navigate risky sections and avoid traffic accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0042] Figure 1 This is a schematic diagram of the structure of an active speed limit system for an autonomous vehicle;

[0043] Figure 2 A flowchart of a method for actively limiting speed of an autonomous vehicle;

[0044] Figure 3 The figure is a schematic diagram of the overall process of an active speed limiting method for an autonomous driving vehicle. DETAILED DESCRIPTION

[0045] Embodiments of the present invention provide an active speed limit system for an autonomous driving vehicle, an active speed limit method for an autonomous driving vehicle, an electronic device, and a storage medium, which are used to solve or partially solve the technical problem of how to enable an autonomous driving vehicle to flexibly adjust its driving speed according to the real-time environment while complying with traffic regulations.

[0046] In order to make the purpose, features, and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0047] For example, autonomous vehicles on public roads typically strictly adhere to speed limits posted on traffic signs or relevant traffic regulations. These speed limits are typically pre-set based on static road attributes (such as road grade and functional zoning). The system utilizes onboard cameras, sensors, and map data to identify and respond to speed limit information posted on traffic signs in real time. However, in certain circumstances, such as on roads without speed limit signs, autonomous vehicles may operate according to the maximum permitted speed for the road.

[0048] In reality, speed limit information obtained from road signs or road regulations is inherently mechanical and static, often failing to adapt well to complex and dynamic road environments. For example, during actual driving, factors such as road traffic conditions, pedestrian density, and vehicle volume can all affect safe driving speeds. Traditional speed limit mechanisms are often unable to adapt to these changes in real time.

[0049] Therefore, how to enable autonomous vehicles to flexibly adjust their driving speed according to the real-time environment while complying with traffic regulations has become an important issue that needs to be addressed in current technological development and lawmaking.

[0050] Therefore, one of the core inventive aspects of the embodiments of the present invention is to design an active speed limit system and method for autonomous vehicles. Taking into account road traffic regulations and signboard speed limit information, the system perceives the road environment surrounding the autonomous vehicle in real time to determine risk areas and predict potential risks within the autonomous vehicle's future driving trajectory. Furthermore, to reduce risk, an active speed limit strategy is designed by comprehensively considering environmental conditions. By providing sufficient safety redundancy distance through reasonable speed limits, autonomous vehicles on public roads can use defensive driving to pass risky sections and avoid traffic accidents.

[0051] Reference Figure 1 , shows a structural schematic diagram of an active speed limiting system for an autonomous driving vehicle provided by an embodiment of the present invention.

[0052] Combine Figure 1 The active speed limiting system 100 may mainly include a planner 101, a controller 102, a sensor 103 and a high-precision map 104 respectively connected to the planner 101. The high-precision map 104 is in communication with the sensor 103.

[0053] In actual applications, sensor 103 is used to sense the road conditions of the autonomous vehicle, generate surrounding obstacle information, and transmit this surrounding obstacle information to planner 101. Planner 101 is used to obtain map information of the autonomous vehicle from high-precision map 104, calculate risk speed limit information based on the surrounding obstacle information, combine the risk speed limit information and map information to generate a driving trajectory, and convert the driving trajectory into control instructions and send them to controller 102, so that controller 102 can execute active speed limit actions based on the control instructions.

[0054] Specifically, the high-precision map 104 is primarily used to store map information (primarily map speed limit information, which can also be understood as lane speed limit information) for autonomous vehicle drivable areas. This map information may include at least lane information, traffic light information, and ground marking information. Furthermore, lane information may include lane type, lane speed limit, number, number, width, and other information. Traffic light information may include information such as traffic light location and the lane number corresponding to the traffic light. Ground marking information may include information such as intersection stop lines, sidewalk markings, no-parking zone markings, solid boundary lines, and dashed boundary lines.

[0055] For example, lanes stored in high-precision maps will include their speed limits. For example, the speed limit on urban roads in downtown areas is generally 40-60 km / h. The speed limit on ramps or country roads is generally 20-30 km / h. Roads within residential communities generally have a speed limit of 5-10 km / h. This speed limit information is automatically added to the corresponding lane type during map creation.

[0056] Sensor 103 is used to sense the road conditions in front and behind the vehicle and generate obstacle information near the vehicle, namely, surrounding obstacle information. The surrounding obstacle information may include obstacle type, projection of the obstacle boundary on the map, and predicted obstacle trajectory (mainly for dynamic obstacles). Obstacle types can be divided into static obstacles and dynamic obstacles. Static obstacles and dynamic obstacles can be further divided into specific obstacles. Static obstacles include cones and private vehicles parked on the roadside. Dynamic obstacles include vehicles coming from behind, oncoming vehicles in narrow sections, pedestrians, and non-motorized vehicles crossing the road. These people and objects are encoded and stored as structural information, including but not limited to position, shape, speed, and future predicted trajectory.

[0057] Sensor 103 can be used to locate the autonomous vehicle's position on the high-precision map 104. Sensor 103 can also be used to communicate with planner 101, providing processed road environment perception data (i.e., surrounding obstacle information) so that planner 101 can update the autonomous vehicle's drivable area.

[0058] The planner 101 is used to receive processed road environment perception data transmitted by the sensor 103. Based on the received data, it calculates risk area information within a certain distance of the autonomous vehicle's future travel. It then calculates corresponding risk speed limit information based on this risk area information. Combined with the speed limit information obtained from the high-precision map, the planner calculates the vehicle's driving trajectory after active speed limit after comprehensive consideration. The planner 101 can also be used to communicate with the controller 102, converting the vehicle's driving trajectory into control instructions and sending them to the controller 102, so that the controller 102 can execute active speed limit actions based on the control instructions.

[0059] Among them, after comprehensive consideration of the planning, the vehicle driving trajectory after active speed limit is obtained. The general process is: for each path sampling point s i Using various strategies, we obtain speed limits v1, v2, v3, ... and take the minimum value. By traversing these path sampling points, we obtain a series of discrete speed limit points (s, v). These are connected by line segments and then smoothed to form a risk speed limit curve. The risk speed limit curve and lane speed limit information are used as speed constraints in the optimization problem. After solving the speed limit through planning, we obtain a speed curve, which is combined with the path to form the final driving trajectory.

[0060] In a specific implementation, the surrounding obstacle information may include static obstacle information and dynamic obstacle information. The planner 101 is specifically configured to: obtain the vehicle speed limit information, current operating route, current driving scenario, and vehicle planned path of the autonomous driving vehicle; obtain preset global speed limit information based on the current operating route, and obtain preset scenario speed limit information based on the current driving scenario; determine the autonomous driving state of the autonomous driving vehicle and, based on the determination result, determine abnormal state speed limit information; calculate curvature speed limit information of the vehicle planned path; perform discrete sampling point analysis based on the vehicle planned path and in combination with static obstacle information and dynamic obstacle information to obtain narrow path speed limit information, static obstacle speed limit information, dynamic obstacle speed limit information, and courtesy speed limit information; and perform a smoothing process on the vehicle speed limit information, global speed limit information, scenario speed limit information, abnormal state speed limit information, curvature speed limit information, narrow path speed limit information, static obstacle speed limit information, dynamic obstacle speed limit information, and courtesy speed limit information, and use the speed limit information obtained after the smoothing process as risk speed limit information.

[0061] Furthermore, for the judgment of the autonomous driving state of the autonomous driving vehicle and the determination of the abnormal state speed limit information, the planner 101 is specifically used to: judge the autonomous driving state of the autonomous driving vehicle according to the abnormal state code; when the driving state of the autonomous driving vehicle is normal, determine that the abnormal state speed limit information is empty; when the driving state of the autonomous driving vehicle is abnormal, obtain the preset speed limit information under the abnormal state as the abnormal state speed limit information of the autonomous driving vehicle in the current driving scenario.

[0062] Furthermore, to determine various types of speed limit information, the planner 101 discretely samples the planned vehicle path to obtain multiple path sampling points. For each path sampling point: the boundary width of the path at the path sampling point is calculated, and the preset narrow path speed limit information is obtained based on the boundary width. At least one static obstacle located at and around the path sampling point is extracted from the static obstacle information, and the static obstacle speed limit information is obtained by traversing each static obstacle. At least one dynamic obstacle located at and around the path sampling point and the predicted obstacle trajectory of the at least one dynamic obstacle are extracted from the dynamic obstacle information, and the dynamic obstacle speed limit information is obtained by traversing each dynamic obstacle in combination with the predicted obstacle trajectory. Map elements are obtained for the path sampling point, and a courtesy judgment is performed based on the map elements and in combination with the at least one dynamic obstacle, and the courtesy speed limit information is obtained based on the courtesy judgment result.

[0063] For static obstacles, such as when the autonomous vehicle is about to circumvent a static obstacle, or when a stationary vehicle ahead may be attempting to start, speed limits for the static obstacle should be considered. For example, assume there is an illegally parked private vehicle 20 meters ahead. If the autonomous vehicle determines it will circumvent the private vehicle in the future, and assuming its current speed is 40 km / h, a speed limit of 20 km / h is set at the 20-meter mark. "Setting a speed limit of 20 km / h at the 20-meter mark" represents the pre-set speed limit for the illegally parked private vehicle at the current speed. This allows the autonomous vehicle to slowly apply the brakes over the 20-meter distance, ensuring its speed has dropped to approximately 20 km / h by the time it reaches the private vehicle. This speed limit strategy primarily reduces the braking distance for the autonomous vehicle in the event of a pedestrian, bicycle, or other vehicle suddenly appearing in front of the preceding vehicle, or if the preceding vehicle suddenly opens its door or starts moving.

[0064] For dynamic obstacles, such as vehicles that want to overtake from behind, non-motor vehicles crossing the road randomly, or pedestrians walking in front, speed limits for dynamic obstacles need to be considered. For example, suppose there is a pedestrian walking 10 meters ahead. Then set a speed limit of 15km / h at 10 meters. When the autonomous driving vehicle gets closer and closer to the pedestrian, once the pedestrian starts to cross the road, it can also ensure that the autonomous driving vehicle can immediately brake and give way. Assuming that the pedestrian has no intention of crossing the road, when the autonomous driving vehicle passes the pedestrian, the 15km / h speed limit is automatically cancelled and then it starts to accelerate.

[0065] For map elements, if there are special scenarios such as crosswalks and intersections, consider courteous speed limits based on whether there are vehicles or pedestrian obstacles in the surrounding area. For example, assume that the autonomous vehicle needs to cross a crosswalk without traffic lights. When there are pedestrians or non-motorized vehicles on both sides (regardless of whether these obstacles are currently moving or not), set a speed limit of 15km / h at the corresponding distance of the crosswalk, and drive slowly through the crosswalk, ready to give way at any time. Assuming there is nothing on both sides of the crosswalk, the autonomous vehicle can pass normally.

[0066] In conjunction with the previous discussion, map information may include lane speed limit information. The planner 101 can then be specifically used to: combine risk speed limit information and lane speed limit information to generate the final driving trajectory of the autonomous driving vehicle through planning and solving. In this step, by integrating multi-source speed limit information, noise and inconsistencies are eliminated, and speed limit information fusion is achieved. During the smoothing process, a smooth speed curve can be generated through low-pass filtering, weighted averaging, or optimization algorithms. Finally, combined with the path planning results, a final trajectory that meets the speed limit constraints can be generated, achieving trajectory optimization. In addition, in a dynamic environment, new speed limit information can be continuously acquired and the trajectory updated to ensure safe vehicle driving.

[0067] Controller 102 is communicatively connected to the chassis of the autonomous vehicle. Controller 102 is specifically configured to receive control commands from planner 101 and convert them into actual control actions for the vehicle chassis, enabling the chassis to execute corresponding active speed limits based on the actual control actions. The actual control actions include at least acceleration, braking, and turning the left and right turn levers.

[0068] In an embodiment of the present invention, an active speed limit system for an autonomous driving vehicle is provided. Based on the active speed limit system, the road environment surrounding the autonomous driving vehicle is perceived in real time, taking into account the road traffic regulations and speed limit information on signboards, to determine the risk area, so as to predict the potential risks within the future driving trajectory of the autonomous driving vehicle. Furthermore, in order to reduce the risk, an active speed limit strategy is designed by comprehensively considering environmental conditions, and sufficient safety redundancy distance is provided through reasonable speed limits, so that autonomous driving vehicles on public roads can use defensive driving to pass through risky sections and avoid traffic accidents. By adopting the technical solution of the present invention, autonomous driving vehicles can adapt to complex actual road conditions on the basis of complying with traffic regulations, and effectively implement defensive driving for possible traffic participants who do not comply with traffic regulations.

[0069] Reference Figure 2, shows a flowchart of the steps of an active speed limiting method for an autonomous driving vehicle provided by an embodiment of the present invention. The method is applied to the active speed limiting system of the autonomous driving vehicle as described in any of the previous embodiments. The active speed limiting system includes a planner, a controller respectively connected to the planner, a sensor, and a high-precision map; the method may specifically include the following steps:

[0070] Step 201: sensing the road condition of the autonomous driving vehicle through the sensor, generating surrounding obstacle information, and transmitting the surrounding obstacle information to the planner;

[0071] In step 202, the planner obtains map information of the autonomous driving vehicle from the high-precision map, calculates risk speed limit information based on the surrounding obstacle information, generates a driving trajectory by combining the risk speed limit information and the map information, and converts the driving trajectory into a control instruction and sends it to the controller, so that the controller can perform active speed limit actions based on the control instruction.

[0072] In an optional embodiment, the surrounding obstacle information includes static obstacle information and dynamic obstacle information; and the execution process of calculating the risk speed limit information based on the surrounding obstacle information in the planner includes:

[0073] Obtaining vehicle speed limit information, current operating route, current driving scenario, and vehicle planned path of the autonomous driving vehicle;

[0074] Obtaining preset global speed limit information based on the current operating route, and obtaining preset scenario speed limit information based on the current driving scenario;

[0075] Determining the autonomous driving state of the autonomous driving vehicle and determining abnormal state speed limit information based on the determination result;

[0076] Calculating curvature speed limit information of the planned vehicle path;

[0077] According to the planned vehicle path, discrete sampling point analysis is performed in combination with the static obstacle information and the dynamic obstacle information to obtain narrow path speed limit information, static obstacle speed limit information, dynamic obstacle speed limit information, and courtesy speed limit information;

[0078] The vehicle speed limit information, the global speed limit information, the scene speed limit information, the abnormal state speed limit information, the curvature speed limit information, the narrow path speed limit information, the static obstacle speed limit information, the dynamic obstacle speed limit information and the courtesy speed limit information are comprehensively smoothed, and the speed limit information obtained after the smoothing process is used as the risk speed limit information.

[0079] In an optional embodiment, the planner determines the autonomous driving state of the autonomous driving vehicle and, based on the determination result, determines an execution process of abnormal state speed limit information, including:

[0080] Determining the autonomous driving state of the autonomous driving vehicle according to the abnormal status code;

[0081] When the driving state of the automatic driving vehicle is normal, determining that the abnormal state speed limit information is empty;

[0082] When the driving state of the autonomous driving vehicle is abnormal, the preset speed limit information under the abnormal state is obtained as the abnormal state speed limit information of the autonomous driving vehicle in the current driving scenario.

[0083] In an optional embodiment, the high-precision map is communicatively connected to the sensor; the sensor is further used to locate the position of the autonomous driving vehicle in the high-precision map; the planner performs discrete sampling point analysis based on the vehicle's planned path and in combination with the static obstacle information and the dynamic obstacle information to obtain narrow path speed limit information, static obstacle speed limit information, dynamic obstacle speed limit information, and courtesy speed limit information, including:

[0084] discretely sampling the planned vehicle path to obtain a plurality of path sampling points;

[0085] For each sampling point on the path:

[0086] Calculating the boundary width of the path at the path sampling point, and obtaining preset narrow path speed limit information according to the boundary width;

[0087] Extracting at least one static obstacle located at and around the path sampling point from the static obstacle information, and obtaining static obstacle speed limit information by traversing each of the static obstacles;

[0088] Extracting at least one dynamic obstacle located at and around the path sampling point, and a predicted obstacle trajectory of the at least one dynamic obstacle from the dynamic obstacle information, and obtaining dynamic obstacle speed limit information by traversing each of the dynamic obstacles based on the predicted obstacle trajectory;

[0089] A map element of the path sampling point is obtained, a courtesy judgment is performed based on the map element and in combination with the at least one dynamic obstacle, and courtesy speed limit information is obtained according to the courtesy judgment result.

[0090] In an optional embodiment, the map information includes lane speed limit information; and the execution process of the planner generating a driving trajectory by combining the risk speed limit information and the map information includes:

[0091] Combining the risk speed limit information and the lane speed limit information, a final driving trajectory of the autonomous driving vehicle is generated through planning and solving.

[0092] In an optional embodiment, the controller is communicatively connected to a vehicle chassis of the autonomous driving vehicle; and the method further comprises:

[0093] The controller receives the control instruction sent by the planner and converts the control instruction into an actual control action for the vehicle chassis, so that the vehicle chassis performs corresponding active speed limit based on the actual control action.

[0094] In an optional embodiment, the actual control action includes at least acceleration, braking, a left turn lever, and a right turn lever.

[0095] As for the method embodiment, since it is basically similar to the system embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the aforementioned system embodiment.

[0096] In an embodiment of the present invention, based on the active speed limit system of the autonomous driving vehicle provided in the aforementioned embodiment, a corresponding active speed limit method is provided. With respect to the autonomous driving process of the autonomous driving vehicle, the road traffic regulations and speed limit information on the signboards are taken into consideration, and the surrounding environment of the road where the autonomous driving vehicle is located is perceived in real time to determine the risk area, so as to predict the potential risks within the future driving trajectory of the autonomous driving vehicle. Furthermore, in order to reduce the risk, an active speed limit strategy is designed by comprehensively considering environmental conditions, and sufficient safety redundancy distance is provided through reasonable speed limits, so that autonomous driving vehicles on public roads can use defensive driving to pass through risky sections and avoid traffic accidents. By adopting the technical solution of the present invention, autonomous driving vehicles can adapt to complex actual road conditions on the basis of complying with traffic regulations, and effectively implement defensive driving for possible traffic participants who do not comply with traffic regulations.

[0097] For better explanation, take the unmanned delivery vehicle in the field of autonomous driving as an example. Figure 3 , which shows a schematic diagram of the overall process of a method for active speed limiting of an autonomous vehicle provided by an embodiment of the present invention. It should be noted that this embodiment only briefly describes the general process of active speed limiting of an autonomous vehicle. The specific implementation process of each step can be understood by referring to the relevant content of the aforementioned embodiments and will not be repeated here. It is understood that the present invention is not limited to this.

[0098] Step 301: Use sensors to sense the surroundings of the unmanned delivery vehicle in the autonomous driving state, generate surrounding obstacle information of the vehicle, and transmit the surrounding obstacle information to the planner;

[0099] Step 302: Obtain lane speed limit information through the high-precision map and transmit it to the planner;

[0100] Step 303: Obtain the speed limit information of the unmanned delivery vehicle (i.e., the maximum speed information designed for the vehicle, which serves as the upper speed limit), the current operating route, the current driving scenario, and the planned vehicle path through the planner;

[0101] Step 304: Obtain global speed limit information for the vehicle's current operating route, and obtain preset scenario speed limit information based on the current driving scenario. The operating speed requirements for unmanned delivery vehicles may vary from user to user in different cities.

[0102] Step 305: Determine the current automatic driving state of the vehicle and obtain preset abnormal state speed limit information based on the abnormal state code; wherein, there is no such speed limit when the vehicle is in a normal state;

[0103] Step 306: Calculate the curvature speed limit information for the path based on vehicle dynamics. Perform discrete sampling point analysis based on the vehicle's planned path and combined with static and dynamic obstacle information to obtain narrow path speed limit information, static obstacle speed limit information, dynamic obstacle speed limit information, and courtesy speed limit information.

[0104] The implementation process for analyzing discrete sampling points based on a planned vehicle path in combination with static and dynamic obstacle information to obtain narrow path speed limit information, static obstacle speed limit information, dynamic obstacle speed limit information, and courtesy speed limit information includes: discretely sampling the planned vehicle path to obtain multiple path sampling points; for each path sampling point, calculating the boundary width of the path at the path sampling point and obtaining preset narrow path speed limit information based on the boundary width; extracting at least one static obstacle located at and around the path sampling point from the static obstacle information and obtaining static obstacle speed limit information by traversing each static obstacle; extracting at least one dynamic obstacle located at and around the path sampling point and the predicted obstacle trajectory of the at least one dynamic obstacle from the dynamic obstacle information, and obtaining dynamic obstacle speed limit information by traversing each dynamic obstacle in combination with the predicted obstacle trajectory; obtaining map elements at the path sampling point, performing a courtesy judgment based on the map elements and in combination with the at least one dynamic obstacle, and obtaining courtesy speed limit information based on the courtesy judgment result.

[0105] Step 307: Perform a smoothing process on all the above speed limit information. According to the smoothed speed limit information and the lane speed limit information, a final driving trajectory is obtained through planning and solving. The driving trajectory is converted into a control instruction and sent to the controller for execution.

[0106] In this embodiment, considering the current lack of vigilance of human traffic participants towards autonomous vehicles, and the fact that some do not proactively yield or avoid them even when they have the right of way, a series of proactive speed-limiting strategies are designed to implement defensive autonomous driving, taking into account the practical needs of autonomous delivery vehicles. Furthermore, a smoothing method is used to address the issue of untimely speed reduction at some speed limit points, thus preventing the impact or danger to traffic participants behind the vehicle caused by sudden braking.

[0107] An embodiment of the present invention further provides an electronic device, the device including a processor and a memory:

[0108] The memory is used to store program codes and transmit the program codes to the processor;

[0109] The processor is used to execute the active speed limiting method for an autonomous driving vehicle according to any embodiment of the present invention according to the instructions in the program code.

[0110] An embodiment of the present invention also provides a computer-readable storage medium, which is used to store program code, and the program code is used to execute the active speed limiting method for an autonomous driving vehicle according to any embodiment of the present invention.

[0111] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0112] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0113] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0114] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0115] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0116] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments can still be modified, or some of the technical features thereof can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An active speed limit system for an autonomous vehicle, characterized in that: The active speed limit system includes a planner, a controller, a sensor and a high-precision map connected to the planner respectively; wherein, The sensor is configured to sense the road conditions of the autonomous vehicle, generate surrounding obstacle information, and transmit the surrounding obstacle information to the planner; The planner is configured to obtain map information of the autonomous driving vehicle from the high-precision map, calculate risk speed limit information based on the surrounding obstacle information, generate a driving trajectory based on the risk speed limit information and the map information, and convert the driving trajectory into a control instruction and send it to the controller, so that the controller can perform an active speed limit action based on the control instruction.

2. The active speed limiting system according to claim 1, characterized in that: The surrounding obstacle information includes static obstacle information and dynamic obstacle information; the planner is specifically used to: Obtaining vehicle speed limit information, current operating route, current driving scenario, and vehicle planned path of the autonomous driving vehicle; Obtaining preset global speed limit information based on the current operating route, and obtaining preset scenario speed limit information based on the current driving scenario; Determining the autonomous driving state of the autonomous driving vehicle and determining abnormal state speed limit information based on the determination result; Calculating curvature speed limit information of the planned vehicle path; According to the planned vehicle path, discrete sampling point analysis is performed in combination with the static obstacle information and the dynamic obstacle information to obtain narrow path speed limit information, static obstacle speed limit information, dynamic obstacle speed limit information, and courtesy speed limit information; The vehicle speed limit information, the global speed limit information, the scene speed limit information, the abnormal state speed limit information, the curvature speed limit information, the narrow path speed limit information, the static obstacle speed limit information, the dynamic obstacle speed limit information and the courtesy speed limit information are comprehensively smoothed, and the speed limit information obtained after the smoothing process is used as the risk speed limit information.

3. The active speed limiting system according to claim 2, characterized in that: The planner is specifically used to: Determining the autonomous driving state of the autonomous driving vehicle according to the abnormal status code; When the driving state of the automatic driving vehicle is normal, determining that the abnormal state speed limit information is empty; When the driving state of the autonomous driving vehicle is abnormal, the preset speed limit information under the abnormal state is obtained as the abnormal state speed limit information of the autonomous driving vehicle in the current driving scenario.

4. The active speed limiting system according to claim 2, characterized in that: The high-precision map is in communication with the sensor; the sensor is further used to locate the position of the autonomous driving vehicle in the high-precision map; the planner is specifically used to: discretely sampling the planned vehicle path to obtain a plurality of path sampling points; For each sampling point on the path: Calculating the boundary width of the path at the path sampling point, and obtaining preset narrow path speed limit information according to the boundary width; Extracting at least one static obstacle located at and around the path sampling point from the static obstacle information, and obtaining static obstacle speed limit information by traversing each of the static obstacles; Extracting at least one dynamic obstacle located at and around the path sampling point, and a predicted obstacle trajectory of the at least one dynamic obstacle from the dynamic obstacle information, and obtaining dynamic obstacle speed limit information by traversing each of the dynamic obstacles based on the predicted obstacle trajectory; A map element of the path sampling point is obtained, a courtesy judgment is performed based on the map element and in combination with the at least one dynamic obstacle, and courtesy speed limit information is obtained according to the courtesy judgment result.

5. The active speed limiting system according to any one of claims 2 to 4, characterized in that: The map information includes lane speed limit information; the planner is specifically used to: Combining the risk speed limit information and the lane speed limit information, a final driving trajectory of the autonomous driving vehicle is generated through planning and solving.

6. The active speed limiting system according to claim 5, characterized in that: The controller is communicatively connected to the vehicle chassis of the autonomous driving vehicle; the controller is specifically configured to: The control instruction sent by the planner is received, and the control instruction is converted into an actual control action for the vehicle chassis, so that the vehicle chassis performs corresponding active speed limit based on the actual control action.

7. The active speed limiting system according to claim 6, characterized in that: The actual control actions at least include acceleration, braking, left turn lever, and right turn lever.

8. A method for active speed limiting of an autonomous vehicle, characterized in that: An active speed limiting system for an autonomous vehicle includes a planner, a controller connected to the planner, a sensor, and a high-precision map. The method includes: sensing the road condition of the autonomous driving vehicle through the sensor, generating surrounding obstacle information, and transmitting the surrounding obstacle information to the planner; The planner obtains map information of the autonomous driving vehicle from the high-precision map, calculates risk speed limit information based on the surrounding obstacle information, generates a driving trajectory by combining the risk speed limit information and the map information, and converts the driving trajectory into a control instruction and sends it to the controller, so that the controller can perform active speed limit actions based on the control instruction.

9. An electronic device, characterized in that: The device includes a processor and a memory: The memory is used to store program code and transmit the program code to the processor; The processor is used to execute the active speed limiting method for an autonomous driving vehicle according to claim 8 according to the instructions in the program code.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium is used to store program code, and the program code is used to execute the active speed limiting method for an autonomous driving vehicle as described in claim 8.

Images