Control method and device of automatic driving vehicle and automatic driving vehicle

Abstract

The invention discloses a control method and device of an automatic driving vehicle and the automatic driving vehicle. The method relates to the technical field of automatic driving and comprises the steps that the driving track of the automatic driving vehicle and a plurality of speed limiting scenes of the automatic driving vehicle are obtained, and the speed limiting thresholds for limiting the speed of the automatic driving vehicle in different speed limiting scenes are different; based on precise control probabilities corresponding to the multiple speed limiting scenes, a target speed limiting scene corresponding to each track point in the driving track is determined, and the precise control probabilities are used for representing the probability that the speed limiting precision of the automatic driving vehicle meets the preset precision of the corresponding speed limiting scene; the speed limiting precision is used for representing the precision of speed limiting on the autonomous vehicle according to the corresponding speed limiting scene; and limiting the speed of the autonomous vehicle based on the driving track and the target speed limiting scene corresponding to each track point. The technical problem that when the speed of the automatic driving vehicle is limited, the energy consumption of the vehicle is large is solved.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a control method and device for an autonomous driving vehicle and an autonomous driving vehicle. Background Art

[0002] In autonomous driving environments such as mining areas, vehicles often need to travel in different speed ranges and different speed limit scenarios. With the development of autonomous driving technology, autonomous mining vehicles are facing the challenge of how to achieve energy conservation and emission reduction while ensuring safety while achieving safe and efficient operation. Traditional control strategies often only focus on the accuracy of speed and path control in different speed limit scenarios, resulting in over-reliance on mechanical braking. Mechanical braking consumes vehicle energy. At the same time, there may be multiple speed limit scenarios when a vehicle is traveling on a path. Limiting the speed of the vehicle in different speed limit scenarios will increase energy consumption, which results in a large amount of energy consumption when the speed of the autonomous driving vehicle is limited.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] Embodiments of the present invention provide a control method and device for an autonomous driving vehicle and an autonomous driving vehicle, so as to at least solve the technical problem of high energy consumption of the vehicle when the speed of the autonomous driving vehicle is limited.

[0005] According to one aspect of an embodiment of the present invention, there is provided a control method for an autonomous driving vehicle, comprising: obtaining a driving trajectory of the autonomous driving vehicle and a plurality of speed limit scenarios of the autonomous driving vehicle, wherein different speed limit scenarios have different speed limit thresholds for limiting the speed of the autonomous driving vehicle; determining a target speed limit scenario corresponding to each trajectory point in the driving trajectory based on precise control probabilities corresponding to the plurality of speed limit scenarios, wherein the precise control probability is used to characterize the probability that the speed limit accuracy of the autonomous driving vehicle meets a preset accuracy of the corresponding speed limit scenario, and the speed limit accuracy is used to characterize the accuracy of limiting the speed of the autonomous driving vehicle according to the corresponding speed limit scenario; and limiting the speed of the autonomous driving vehicle based on the driving trajectory and the target speed limit scenario corresponding to each trajectory point.

[0006] According to another aspect of an embodiment of the present invention, a control device for an autonomous driving vehicle is further provided, including: an acquisition module, used to acquire a driving trajectory of the autonomous driving vehicle, and multiple speed limit scenarios of the autonomous driving vehicle, wherein different speed limit scenarios have different speed limit thresholds for limiting the speed of the autonomous driving vehicle; a determination module, used to determine a target speed limit scenario corresponding to each trajectory point in the driving trajectory based on precise control probabilities corresponding to multiple speed limit scenarios, wherein the precise control probability is used to characterize the probability that the speed limit accuracy of the autonomous driving vehicle meets a preset accuracy of the corresponding speed limit scenario, and the speed limit accuracy is used to characterize the accuracy of speed limiting the autonomous driving vehicle according to the corresponding speed limit scenario; a control module, used to limit the speed of the autonomous driving vehicle based on the driving trajectory and the target speed limit scenario corresponding to each trajectory point.

[0007] According to another aspect of an embodiment of the present invention, there is also provided an autonomous driving vehicle, comprising: a memory storing an executable program; and a processor for running the program, wherein the method in each embodiment of the present invention is executed when the program is running.

[0008] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the methods in various embodiments of the present invention.

[0009] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0010] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0011] According to another aspect of the embodiments of the present invention, a computer program is further provided. When the computer program is executed by a processor, the methods in the embodiments of the present invention are implemented.

[0012] In the embodiment of the present invention, the driving trajectory of the autonomous driving vehicle and multiple speed limit scenarios of the autonomous driving vehicle are obtained, wherein different speed limit scenarios have different speed limit thresholds for speed limit of the autonomous driving vehicle; based on the precise control probabilities corresponding to the multiple speed limit scenarios, the target speed limit scenario corresponding to each track point in the driving trajectory is determined, wherein the precise control probability is used to characterize the probability that the speed limit accuracy of the autonomous driving vehicle meets the preset accuracy of the corresponding speed limit scenario, and the speed limit accuracy is used to characterize the accuracy of speed limit of the autonomous driving vehicle according to the corresponding speed limit scenario; based on the driving trajectory and the target speed limit scenario corresponding to each track point, the speed limit of the autonomous driving vehicle is limited. It is easy to notice that firstly, the target speed limit scenario corresponding to each track point in the driving trajectory is determined from multiple speed limit scenarios based on the precise control probability, and secondly, the driving control mode can be dynamically adjusted according to the scenario based on the target speed limit scenario and the driving trajectory, so as to achieve the purpose of selecting a speed limit scenario that is more in line with the current state of the autonomous driving vehicle, and limit control of the autonomous driving vehicle, thereby avoiding the increase of energy consumption caused by considering multiple speed limit scenarios at the same time, and achieving the technical effect of saving the energy consumption of the vehicle, thereby solving the technical problem of large energy consumption of the vehicle when the speed of the autonomous driving vehicle is limited. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0014] Figure 1 is a flow chart of a control method of an autonomous driving vehicle according to an embodiment of the present invention;

[0015] Figure 2 is a schematic diagram of an optional speed limit acquisition scenario according to an embodiment of the present invention;

[0016] Figure 3 is a schematic diagram of an optional control method for an autonomous driving vehicle according to an embodiment of the present invention;

[0017] Figure 4 is a schematic diagram of a control device for an autonomous driving vehicle according to an embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme 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 described embodiments 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 creative work should fall within the scope of protection of the present invention.

[0019] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0020] According to an embodiment of the present invention, an embodiment of a control method for an autonomous driving vehicle is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in an order different from that shown here.

[0021] Figure 1 is a flow chart of a control method for an autonomous driving vehicle according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0022] Step S102, obtaining a driving trajectory of the autonomous driving vehicle and a plurality of speed limit scenarios of the autonomous driving vehicle, wherein different speed limit scenarios have different speed limit thresholds for limiting the speed of the autonomous driving vehicle.

[0023] The above-mentioned autonomous driving vehicle can be any vehicle that can automatically drive based on the generated path. For example, the type of vehicle can include but is not limited to: passenger cars, trucks, and cars. The specific vehicle type can be set by the user according to the actual use needs. In this embodiment, a truck (for example, a mining truck, referred to as a mining truck) is used as an example for explanation, but it is not limited to this. Among them, the application scenarios of trucks can include but are not limited to: commercial transportation scenarios, express logistics scenarios, construction scenarios, agricultural scenarios, energy and mineral scenarios, medical and pharmaceutical scenarios, and public service scenarios. The specific scenario type can be set by the user according to the actual use needs. In this embodiment, the energy and mineral scenarios are used as an example for explanation, but it is not limited to this. The above-mentioned driving trajectory can be automatically generated by the path generation platform after the technician inputs the vehicle attributes, starting point and end point of the autonomous driving vehicle into the path generation platform, or it can be generated by the technician based on the vehicle attributes, starting point, end point and working environment of the autonomous driving vehicle, but it is not limited to this.

[0024] The above-mentioned multiple speed limit scenarios are used to ensure that the autonomous driving vehicle can drive safely in different path segments in the driving path. After being classified according to the speed limit source, they may include but are not limited to: service / platform / dispatching speed limit, closed area speed limit, curvature and curvature change rate speed limit, static obstacle speed limit, dynamic obstacle speed limit, dust speed limit, road boundary speed limit, lateral detour / riding speed limit, speed limit caused by predicted trajectory, risk speed limit, multi-vehicle interaction speed limit, trajectory end speed limit, and speed limit under precise parking. Among them, the speed limit scenario may include but is not limited to: speed limit segment, speed limit interval and speed limit reason. The speed limit segment can be a certain path segment in the driving path of the autonomous driving vehicle where the speed of the autonomous driving vehicle is restricted. The speed limit interval can be the trajectory point interval in the driving path of the autonomous driving vehicle where the speed of the autonomous driving vehicle is restricted by the corresponding speed limit scenario. The speed limit reason can be the reason for the speed limit of the autonomous driving vehicle in the corresponding speed limit scenario. The speed limit reason may include but is not limited to: safety considerations, comfort, energy efficiency, road conditions and vehicle performance. The multiple speed limit scenarios can be set in advance by the technician based on the vehicle information of the autonomous driving vehicle and the environmental information of the work site, and then input into the path generation platform. They can also be automatically generated by the path generation platform based on the vehicle information of the autonomous driving vehicle and the environmental information of the work site, but are not limited to this. Among them, the vehicle information may include at least one of the following: attribute information, perception information, decision information and scheduling information of the autonomous driving vehicle. Among them, the attribute information may include but is not limited to: weight, size, volume and model. Perception information can be information obtained by the sensor on the autonomous driving vehicle to perceive the working environment, for example, it can include but is not limited to: visual perception, radar perception, laser radar perception, ultrasonic perception, vehicle communication system perception, pedestrian detection perception and road condition perception. Decision information can be information that the controller on the autonomous driving vehicle decides how to drive the vehicle based on the perception information, for example, it can include but is not limited to: path planning, speed control, obstacle avoidance, emergency handling, vehicle-to-vehicle communication, environmental adaptability and energy management. Scheduling information can be information generated by the controller on the autonomous driving vehicle based on the decision information, which is used to schedule the autonomous driving vehicle to perform the corresponding operation, and can include but is not limited to: vehicle positioning, vehicle status, task allocation, path planning, scheduling strategy, energy management and safety monitoring. It should be noted that, in each of the multiple speed limit scenarios, the speed limit threshold for limiting the speed of the autonomous driving vehicle is different. The speed limit threshold may be set in advance by a technician, or may be automatically generated by the path generation platform based on the multiple speed limit scenarios, but is not limited thereto.

[0025] In an optional embodiment, in the energy and mineral scenario, the autonomous driving vehicle often needs to operate in the mining area in different speed ranges and different speed limit scenarios. With the development of autonomous driving technology, autonomous driving vehicles are also faced with the challenge of how to achieve energy conservation and emission reduction under the premise of ensuring safety. The current control strategy relies too much on mechanical braking, and mechanical braking consumes the energy of the vehicle, which leads to the technical problem that the energy consumption of the vehicle is large when the vehicle is limited in different speed limit scenarios. In order to solve the above technical problems, in an embodiment of the present invention, the driving trajectory of the autonomous driving vehicle and multiple speed limit scenarios of the autonomous driving vehicle are first obtained, wherein different speed limit scenarios have different speed limit thresholds for the speed limit of the autonomous driving vehicle. For example, the technician can input the starting point and end point of the autonomous driving vehicle into the path generation platform to obtain the driving trajectory of the autonomous driving vehicle. At the same time, the vehicle information of the autonomous driving vehicle and the environmental information of the work site can also be input into the path generation platform, and the path generation platform calculates multiple speed limit scenarios of the autonomous driving vehicle based on the speed limit scenario division algorithm. It should be noted that the multiple speed limit scenarios also include the speed limit reasons, and the speed limit reasons and speed limit thresholds of different speed limit scenarios are different.

[0026] Figure 2 is a schematic diagram of an optional speed limit acquisition scenario according to an embodiment of the present invention, such as Figure 2 As shown, it includes: the driving path of the vehicle, where the black solid triangle in the driving path S is the starting point of the autonomous driving vehicle, the hollow triangle is the end point of the autonomous driving vehicle, and the black dots are the track points in the driving path. Figure 2 As shown, in the case of considering the complete driving path, the speed limit scenario can be the map service speed limit; in the case of considering the curved path of the driving path, the speed limit scenario can be the curvature / curvature change rate speed limit; in the case of considering the obstacles in the driving path (such as Figure 2 In the case of the white square in the figure, the speed limit scenario can be the obstacle speed limit, and considering the closed section in the driving path (such as Figure 2 In the case of the black square with diagonal lines shown in ), the speed limit scenario can be a closed interval speed limit, but is not limited to this. That is, each trajectory point in the driving path S will correspond to at least one speed limit scenario. Figure 2 It can be seen that in the direction of the driving path S, each section of the path has various speed limits, and the speed limit thresholds of different speed limit scenarios are different. In this way, the speed limit scenario and speed limit reason of each point on the driving path can be obtained.

[0027] Step S104, based on the precise control probabilities corresponding to multiple speed limit scenarios, determine the target speed limit scenario corresponding to each trajectory point in the driving trajectory, wherein the precise control probability is used to characterize the probability that the speed limit accuracy of the autonomous driving vehicle meets the preset accuracy of the corresponding speed limit scenario, and the speed limit accuracy is used to characterize the accuracy of speed limiting the autonomous driving vehicle according to the corresponding speed limit scenario.

[0028] The above-mentioned precise control probability can be determined by the technician based on the preset driving demand of the autonomous driving vehicle, corresponding to multiple speed limit scenarios one by one. Among them, the interval range of the precise control probability is [0,1]. The preset driving demand can be set in advance by the technician based on the environmental conditions and operating requirements of the operating site of the autonomous driving vehicle, and can include but is not limited to: safe driving requirements, tracking accuracy requirements, and parking accuracy requirements. Among them, in the preset driving requirements, the specific values ​​of the specific requirements can be set by the technician according to the actual control requirements, and are not limited in this embodiment. The above-mentioned preset accuracy can be determined by the technician based on different speed limit scenarios. The specific accuracy value is not limited in this embodiment and can be set according to the actual speed limit scenario.

[0029] In an optional embodiment, the technician can first set the precise control probabilities corresponding to multiple speed limit scenarios in advance based on the preset driving requirements of the autonomous driving vehicle, and obtain a corresponding table of speed limit scenarios and precise control probabilities. Secondly, based on the speed limit intervals corresponding to the multiple speed limit scenarios, at least one candidate speed limit scenario corresponding to each trajectory point can be determined, and then based on the precise control probability corresponding to at least one candidate speed limit scenario, the target speed limit scenario corresponding to the corresponding trajectory point can be determined from at least one candidate speed limit scenario. For example, the candidate speed limit scenario with the largest numerical value of the precise control probability can be determined as the target speed limit scenario, and the candidate speed limit scenario with the precise control probability closest to the preset precise control probability can also be determined as the target speed limit scenario, but it is not limited to this.

[0030] In another optional embodiment, when multiple speed limit scenarios, precise control probabilities corresponding to multiple speed limit scenarios, and speed limit intervals corresponding to multiple speed limit scenarios are obtained, at least one candidate speed limit scenario corresponding to each trajectory point can be determined based on the speed limit interval through the path generation platform, and then the precision of limiting the driving speed of the autonomous driving vehicle according to the speed limit threshold corresponding to at least one candidate speed limit scenario at different trajectory points can be calculated to obtain the speed limit precision of at least one candidate speed limit scenario, and at least one actual precise control probability of at least one candidate speed limit scenario can be obtained based on the speed limit precision of at least one candidate speed limit scenario and the preset precision, and then the target precise control probability can be obtained based on at least one actual precise control probability of at least one candidate speed limit scenario. For example, the precise control probability with the largest value in at least one actual precise control probability can be determined as the target precise control probability. For another example, the actual precise control probability closest to the preset precise control probability in at least one actual precise control probability can also be determined as the target precise control probability, but it is not limited to this.

[0031] Step S106: Based on the driving trajectory and the target speed limit scenario corresponding to each trajectory point, the speed of the autonomous driving vehicle is limited.

[0032] In an optional embodiment, when the driving trajectory and the target speed limit scenario corresponding to each trajectory point are obtained, the path generation platform can directly limit the driving speed of the autonomous driving vehicle based on the driving trajectory and the target speed limit scenario corresponding to each trajectory point. For example, when the autonomous driving vehicle is driving along the driving trajectory, the path generation platform can directly control the driving speed of the autonomous driving vehicle to maintain the speed limit threshold based on the speed limit threshold corresponding to the target speed limit scenario corresponding to each trajectory point. This avoids the problem of excessive energy consumption of the autonomous driving vehicle caused by excessive reliance on mechanical braking in different speed limit scenarios, and can effectively reduce the energy consumption of the vehicle.

[0033] In another optional embodiment, when the driving trajectory and the target speed limit scenario corresponding to each trajectory point are obtained, the speed limit error of the corresponding trajectory point can also be determined based on the target precise control probability corresponding to the target speed limit scenario, wherein the speed limit error is the error between the speed limit speed of the autonomous driving vehicle and the target speed limit threshold of the target speed limit scenario, and the speed limit speed is used to characterize the speed obtained by limiting the speed of the autonomous driving vehicle according to the target speed limit scenario. Finally, the speed limit of the autonomous driving vehicle can be set based on the driving trajectory and the speed limit error of each trajectory point. For example, when the autonomous driving vehicle is driving according to the driving trajectory, the path generation platform can control the speed of the autonomous driving vehicle based on the speed limit error to reach the speed threshold corresponding to the target speed limit scenario corresponding to each trajectory point, and control the driving speed of the autonomous driving vehicle to maintain the speed limit threshold.

[0034] In the embodiment of the present invention, the driving trajectory of the autonomous driving vehicle and multiple speed limit scenarios of the autonomous driving vehicle are obtained, wherein different speed limit scenarios have different speed limit thresholds for speed limit of the autonomous driving vehicle; based on the precise control probabilities corresponding to the multiple speed limit scenarios, the target speed limit scenario corresponding to each track point in the driving trajectory is determined, wherein the precise control probability is used to characterize the probability that the speed limit accuracy of the autonomous driving vehicle meets the preset accuracy of the corresponding speed limit scenario, and the speed limit accuracy is used to characterize the accuracy of speed limit of the autonomous driving vehicle according to the corresponding speed limit scenario; based on the driving trajectory and the target speed limit scenario corresponding to each track point, the speed limit of the autonomous driving vehicle is limited. It is easy to notice that firstly, the target speed limit scenario corresponding to each track point in the driving trajectory is determined from multiple speed limit scenarios based on the precise control probability, and secondly, the driving control mode can be dynamically adjusted according to the scenario based on the target speed limit scenario and the driving trajectory, so as to achieve the purpose of selecting a speed limit scenario that is more in line with the current state of the autonomous driving vehicle, and limit control of the autonomous driving vehicle, thereby avoiding the increase of energy consumption caused by considering multiple speed limit scenarios at the same time, and achieving the technical effect of saving the energy consumption of the vehicle, thereby solving the technical problem of large energy consumption of the vehicle when the speed of the autonomous driving vehicle is limited.

[0035] Optionally, based on the precise control probabilities corresponding to multiple speed limit scenarios, a target speed limit scenario corresponding to each trajectory point in the driving trajectory is determined, including: based on the speed limit intervals corresponding to the multiple speed limit scenarios, at least one candidate speed limit scenario corresponding to each trajectory point is determined, wherein the speed limit interval is used to characterize the trajectory point interval in which the corresponding speed limit scenario limits the speed of the autonomous driving vehicle; based on the precise control probability corresponding to at least one candidate speed limit scenario, a target speed limit scenario corresponding to the corresponding trajectory point is determined from at least one candidate speed limit scenario, wherein the precise control probability corresponding to the target speed limit scenario is greater than the precise control probability corresponding to other speed limit scenarios, and the other speed limit scenarios are used to characterize speed limit scenarios other than the target speed limit scenario in at least one candidate speed limit scenario.

[0036] The above-mentioned speed limit interval can be a trajectory point interval in the driving path where the speed limit scenario limits the speed of the autonomous driving vehicle. The specific speed limit interval can be set according to the actual control needs of the user and is not specifically limited in this embodiment. The above-mentioned at least one candidate speed limit scenario can be a speed limit scenario in which the speed limit accuracy of the autonomous driving vehicle meets the preset accuracy of the corresponding speed limit scenario.

[0037] In an optional embodiment, the technician may first set the correspondence between different speed limit scenarios and corresponding speed limit intervals, and input the correspondence into the path generation platform. Secondly, the path generation platform may determine the speed limit intervals corresponding to the multiple speed limit scenarios based on the correspondence. Then, the path generation platform may determine at least one candidate speed limit scenario corresponding to each trajectory point based on the speed limit interval. Then, the accuracy of limiting the driving speed of the autonomous driving vehicle at different trajectory points according to the speed limit threshold corresponding to at least one candidate speed limit scenario may be calculated to obtain the speed limit accuracy of at least one candidate speed limit scenario. Based on the speed limit accuracy of at least one candidate speed limit scenario and the preset accuracy, at least one actual precise control probability of at least one candidate speed limit scenario may be obtained. Then, based on at least one actual precise control probability of at least one candidate speed limit scenario, the target speed limit scenario corresponding to the corresponding trajectory point may be determined from at least one candidate speed limit scenario. For example, it may be determined that the precise control probability with the largest value among at least one precise control probability is the target precise control probability. Then, the candidate speed limit scenario corresponding to the target precise control probability is the target speed limit scenario, wherein the precise control probability corresponding to the target speed limit scenario is greater than the precise control probability corresponding to other speed limit scenarios.

[0038] Optionally, the precise control probability is determined based on preset driving requirements of the autonomous driving vehicle, and the preset driving requirements include at least one of the following: safe driving requirements, tracking accuracy requirements, and parking accuracy requirements.

[0039] The above-mentioned preset driving requirements can be set in advance by technicians based on the safety and energy consumption requirements of the autonomous driving vehicle, to ensure that the autonomous driving vehicle can travel according to the driving path safely and with low energy consumption.

[0040] In an optional embodiment, various speed limit scenarios in autonomous driving can be classified and scored according to preset driving requirements such as safe driving requirements, tracking accuracy requirements, and parking accuracy requirements, and the probability of precise control can be given to construct a speed limit scenario and precise control ratio table.

[0041] Optionally, the speed of the autonomous driving vehicle is limited based on the driving trajectory and the target speed limit scenario corresponding to each trajectory point, including: determining the speed limit error of the corresponding trajectory point based on the target precise control probability corresponding to the target speed limit scenario, wherein the speed limit error is used to characterize the error between the speed limit speed of the autonomous driving vehicle and the target speed limit threshold of the target speed limit scenario, and the speed limit speed is used to characterize the speed obtained by limiting the speed of the autonomous driving vehicle according to the target speed limit scenario; the speed of the autonomous driving vehicle is limited based on the driving trajectory and the speed limit error at each trajectory point.

[0042] The above speed limit error is used to control the speed limit of the autonomous driving vehicle to reach the target speed limit threshold of the target speed limit scenario. The speed limit is the speed obtained by limiting the speed of the autonomous driving vehicle according to the target speed limit scenario. The target speed limit threshold can be set by the technician based on different speed limit scenarios, or it can be automatically generated by the path generation platform based on different speed limit scenarios, but is not limited to this. The specific threshold is not limited in this embodiment, and the technician can set it according to actual needs.

[0043] In an optional embodiment, first, the speed limit error of the corresponding trajectory point can be determined based on the target precise control probability corresponding to the target speed limit scenario, wherein the speed limit error is the error between the speed limit speed of the autonomous driving vehicle and the target speed limit threshold of the target speed limit scenario. For example, the speed limit error can be obtained by calculating the large model, and the speed limit error can also be obtained by a preset corresponding relationship, but it is not limited to this. Finally, the speed of the autonomous driving vehicle can be limited based on the driving trajectory and the speed limit error of each trajectory point, so that the autonomous driving vehicle can travel safely, efficiently, and with low energy consumption. For example, the speed of the autonomous driving vehicle can be limited directly based on the driving trajectory and the speed limit error of each trajectory point, and the speed of the autonomous driving vehicle can be limited based on the filtered driving trajectory and the speed limit error of each trajectory point after filtering the driving trajectory, but it is not limited to this.

[0044] Optionally, based on the target precise control probability corresponding to the target speed limit scenario, the speed limit error of the corresponding trajectory point is determined, including: obtaining a target probability error model of the target speed limit scenario, wherein the target probability error model is used to characterize the mapping relationship between the target precise control probability and the speed limit error of the corresponding trajectory point; inputting the target precise control probability into the target probability error model to obtain the speed limit error of the corresponding trajectory point.

[0045] The above target probability error model is obtained by testing the autonomous driving vehicle under different precision control probabilities in the coasting deceleration scenario.

[0046] In an optional embodiment, firstly, based on the vehicle type of the autonomous driving vehicle, in a coasting deceleration scenario, the autonomous driving vehicle is tested for different precise control probabilities to obtain a target probability error model, wherein the target probability error model can reflect the mapping relationship between the target precise control probability and the speed limit error of the corresponding trajectory point. Secondly, the speed limit error y of the corresponding trajectory point can be obtained by the following formula:

[0047]

[0048] in, is the target probability error model, a and b are the coefficients of the target probability error model, which are obtained through the vehicle type test of the vehicle, indicating the speed value at which the vehicle can slow down during the sliding process, and x is the precise control probability value.

[0049] It can be seen from the above formula that when the coefficients a and b are obtained through testing, the precise control probability value x is input into the target probability error model to obtain the speed limit error y of the corresponding trajectory point.

[0050] Optionally, obtaining a target probability error model for a target speed limit scenario includes: determining the vehicle type of the autonomous driving vehicle; obtaining multiple probability error models that match the vehicle type, wherein different probability error models correspond to different speed limit scenarios; obtaining a probability error model that matches the target speed limit scenario from the multiple probability error models to obtain a target probability error model.

[0051] In an optional embodiment, a technician may first construct a correspondence between different vehicle types and different probability error models. Secondly, the vehicle type of the autonomous driving vehicle may be determined. Then, based on the correspondence, multiple probability error models matching the vehicle type of the autonomous driving vehicle may be obtained, wherein different probability error models correspond to different speed limit scenarios. Finally, based on the target speed limit scenario, a probability error model matching the target speed limit scenario may be obtained from multiple probability error models to obtain a target probability error model.

[0052] Optionally, the target probability error model is obtained by testing the autonomous driving vehicle for different precise control probabilities in a coasting deceleration scenario.

[0053] In an optional embodiment, the coefficients a and b in the target probability error model are obtained by testing the autonomous driving vehicle for different precision control probabilities in a coasting deceleration scenario. For example, taking a certain type of vehicle as an example, the vehicle decelerates at 2km / h and the deceleration is -0.3m / s 2 The following situations can be achieved through sliding resistance, so it can be calculated that a and b are approximately 0.55, and x is the probability value of precise control. The larger the x, the more precise control the vehicle needs, and there can be no error loss. On the contrary, very precise control is not required. Therefore, the larger the error, y is the output error that allows precise control.

[0054] Optionally, the speed of the autonomous driving vehicle is limited based on the driving trajectory and the speed limit error at each trajectory point, including: filtering the speed limit error at each trajectory point to obtain a filtered speed limit error for the trajectory point; and limiting the speed of the autonomous driving vehicle based on the driving trajectory and the filtered speed limit error at each trajectory point.

[0055] In an optional embodiment, in order to avoid the impact of excessive error jumps on vehicle control, the speed limit error of each trajectory point can be filtered first, for example, it can be smoothed to obtain the filtered speed limit error of the trajectory point, and finally the speed of the autonomous driving vehicle can be limited based on the driving trajectory and the filtered speed limit error of each trajectory point.

[0056] Optionally, obtaining multiple speed limit scenarios of the autonomous driving vehicle includes: obtaining vehicle information of the autonomous driving vehicle, wherein the vehicle information includes at least one of the following: perception information, decision information and scheduling information, wherein the perception information is information obtained by the autonomous driving vehicle perceiving the surrounding environment, the decision information is information obtained by making decisions on the driving behavior of the autonomous driving vehicle based on the perception information, and the scheduling information is information for scheduling the autonomous driving vehicle to perform work tasks; based on the vehicle information, determining multiple speed limit scenarios and the speed limit range corresponding to each speed limit scenario.

[0057] In an optional embodiment, first, the vehicle information of the autonomous driving vehicle can be obtained, and then based on the vehicle information, multiple speed limit scenarios and speed limit intervals corresponding to each speed limit scenario can be automatically generated in the path generation platform. Based on the vehicle information, multiple speed limit scenarios and speed limit intervals corresponding to each speed limit scenario can also be generated in the path generation platform by technicians. The vehicle information includes at least one of the following: perception information, decision information and scheduling information, wherein the perception information is information obtained by the autonomous driving vehicle sensing the surrounding environment, the decision information is information obtained by making decisions on the driving behavior of the autonomous driving vehicle based on the perception information, and the scheduling information is information for scheduling the autonomous driving vehicle to perform work tasks.

[0058] Figure 3 is a schematic diagram of an optional control method for an autonomous driving vehicle according to an embodiment of the present invention, such as Figure 3 As shown, the method comprises the following steps:

[0059] Step S301, input path information, environmental information, service / scheduling information, and decision information;

[0060] Step S302, calculating each speed limit scenario, obtaining the type of the speed limit scenario and the speed limit path interval;

[0061] Among them, according to the trajectory, map, perceived surrounding environment information, and decision information, the speed limit information acting on the trajectory of each scenario is calculated, and the corresponding speed limit section and speed limit interval on the trajectory are given.

[0062] Step S303, combining the speed limit type and the speed limit interval, and selecting the speed limit type and speed limit interval with the highest probability at each path point according to the percentage of the speed limit type and the speed limit interval;

[0063] First, a matrix table of reasons and precise control ratios is constructed: various speed limit scenarios in autonomous driving are classified and scored according to standards such as safety, efficiency, and parking accuracy, and the probability of precise control is given. The energy consumption cost of precise control of each speed limit scenario is calculated based on safety, tracking accuracy, and parking accuracy, and the probability value of precise control is given, and the probability value is between [0,1]. Secondly, all speed limit reasons on each section of the trajectory point are compared, and the one with the highest precise control ratio is given as the highest speed limit reason for the current section: traverse each trajectory point on the driving path, compare the probability values ​​corresponding to the speed limit reasons of each trajectory point, and take the largest probability value as the speed limit reason for this point.

[0064] Step S304, selecting a speed limit error according to the speed limit type, and adding the speed limit error to the speed limit interval according to the speed limit path length interval (i.e., the speed limit interval);

[0065] Among them, the speed limit error of each trajectory point is calculated, and according to the precise control probability corresponding to the speed limit reason of each trajectory point, the speed limit error value on each trajectory point is calculated by combining the precise control probability with the error model formula and assigned to the corresponding trajectory point.

[0066] Step S305, filtering the error interval of the entire path;

[0067] The speed limit error is filtered to avoid excessive error jumps, and in this embodiment, a sliding average filter is used for processing.

[0068] Step S306, outputting the speed error value and the precise control probability ratio on the path to control the vehicle;

[0069] Step S307, end.

[0070] The method provided in this embodiment can optimize the energy consumption of autonomous driving vehicles and achieve an environmentally friendly driving mode by accurately controlling the speed limit and braking strategies in different scenarios while ensuring safety. In addition, high-risk scenarios are automatically identified and the response strategy is automatically adjusted to improve the overall driving safety and comfort. On the trajectory given to the control, the error values ​​given for different scenarios such as straight roads and curves are different as follows. Under actual vehicle model testing, the fuel saving rate for a specific vehicle model currently exceeds 10%.

[0071] The present invention provides a method for dynamically adjusting the driving mode according to the scene, which not only improves the driving efficiency of the autonomous driving vehicle, but also significantly reduces energy consumption, and is particularly suitable for autonomous driving vehicles under special conditions such as mining areas. The present invention mainly solves the braking efficiency in non-precise control scenes, improves fuel saving, and reduces vehicle loss.

[0072] According to an embodiment of the present invention, an embodiment of a control device for an autonomous driving vehicle is provided. It should be noted that the device can be used to execute the control method for the autonomous driving vehicle described above. Figure 4 is a schematic diagram of a control device for an autonomous driving vehicle according to an embodiment of the present invention. Figure 4 As shown, the device includes: an acquisition module 42, which is used to acquire the driving trajectory of the autonomous driving vehicle and multiple speed limit scenarios of the autonomous driving vehicle, wherein different speed limit scenarios have different speed limit thresholds for limiting the speed of the autonomous driving vehicle; a determination module 44, which is used to determine the target speed limit scenario corresponding to each trajectory point in the driving trajectory based on the precise control probabilities corresponding to the multiple speed limit scenarios, wherein the precise control probability is used to characterize the probability that the speed limit accuracy of the autonomous driving vehicle meets the preset accuracy of the corresponding speed limit scenario, and the speed limit accuracy is used to characterize the accuracy of speed limiting the autonomous driving vehicle according to the corresponding speed limit scenario; a control module 46, which is used to limit the speed of the autonomous driving vehicle based on the driving trajectory and the target speed limit scenario corresponding to each trajectory point.

[0073] Optionally, the determination module includes: a first determination unit, used to determine at least one candidate speed limit scenario corresponding to each trajectory point based on the speed limit intervals corresponding to multiple speed limit scenarios, wherein the speed limit interval is used to characterize the trajectory point interval in which the corresponding speed limit scenario limits the speed of the autonomous driving vehicle; a second determination unit, used to determine the target speed limit scenario corresponding to the corresponding trajectory point from at least one candidate speed limit scenario based on the precise control probability corresponding to at least one candidate speed limit scenario, wherein the precise control probability corresponding to the target speed limit scenario is greater than the precise control probability corresponding to other speed limit scenarios, and the other speed limit scenarios are used to characterize the speed limit scenarios other than the target speed limit scenario in at least one candidate speed limit scenario.

[0074] Optionally, the precise control probability is determined based on preset driving requirements of the autonomous driving vehicle, and the preset driving requirements include at least one of the following: safe driving requirements, tracking accuracy requirements, and parking accuracy requirements.

[0075] Optionally, the control module includes: a third determination unit, used to determine the speed limit error of the corresponding trajectory point based on the target precise control probability corresponding to the target speed limit scenario, wherein the speed limit error is used to characterize the error between the speed limit speed of the autonomous driving vehicle and the target speed limit threshold of the target speed limit scenario, and the speed limit speed is used to characterize the speed obtained by limiting the speed of the autonomous driving vehicle according to the target speed limit scenario; a control unit, used to limit the speed of the autonomous driving vehicle based on the driving trajectory and the speed limit error of each trajectory point.

[0076] Optionally, the third determination unit includes: an acquisition subunit, used to acquire a target probability error model of a target speed limit scenario, wherein the target probability error model is used to characterize the mapping relationship between the target precise control probability and the speed limit error of the corresponding trajectory point; an input subunit, used to input the target precise control probability into the target probability error model to obtain the speed limit error of the corresponding trajectory point.

[0077] Optionally, the acquisition subunit is also used to: determine the vehicle type of the autonomous driving vehicle; obtain multiple probability error models that match the vehicle type, wherein different probability error models correspond to different speed limit scenarios; obtain a probability error model that matches the target speed limit scenario from the multiple probability error models to obtain a target probability error model.

[0078] Optionally, the target probability error model is obtained by testing the autonomous driving vehicle for different precise control probabilities in a coasting deceleration scenario.

[0079] Optionally, the control unit includes: a filtering subunit, used to filter the speed limit error of each trajectory point to obtain the filtered speed limit error of the trajectory point; and a control subunit, used to limit the speed of the autonomous driving vehicle based on the driving trajectory and the filtered speed limit error of each trajectory point.

[0080] Optionally, the acquisition module includes: an acquisition unit, used to acquire vehicle information of the autonomous driving vehicle, wherein the vehicle information includes at least one of the following: perception information, decision information and scheduling information, wherein the perception information is information obtained by the autonomous driving vehicle perceiving the surrounding environment, the decision information is information obtained by making decisions on the driving behavior of the autonomous driving vehicle based on the perception information, and the scheduling information is information for scheduling the autonomous driving vehicle to perform a work task; a fourth determination unit, used to determine multiple speed limit scenarios and the speed limit range corresponding to each speed limit scenario based on the vehicle information.

[0081] An embodiment of the present application also provides an autonomous driving vehicle, comprising: a memory storing an executable program; and a processor for running the program, wherein the methods in various embodiments of the present invention are executed when the program is running.

[0082] An embodiment of the present application further provides a computer-readable storage medium, which includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the methods in various embodiments of the present invention.

[0083] An embodiment of the present application further provides a computer program product, including a computer program, which implements the methods in various embodiments of the present invention when executed by a processor.

[0084] An embodiment of the present application further provides a computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium is used to store a computer program, and when the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0085] The embodiments of the present application further provide a computer program, which implements the methods in the above-mentioned embodiments of the present invention when executed by a processor.

[0086] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0087] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0088] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0089] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0090] If the integrated unit is implemented in the form of 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, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0091] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A control method for an autonomous driving vehicle, characterized in that: include: Acquire a driving trajectory of the autonomous driving vehicle and a plurality of speed limit scenarios of the autonomous driving vehicle, wherein different speed limit scenarios have different speed limit thresholds for limiting the speed of the autonomous driving vehicle; Based on the precise control probabilities corresponding to the multiple speed limit scenarios, determine the target speed limit scenario corresponding to each trajectory point in the driving trajectory, wherein the precise control probability is used to characterize the probability that the speed limit accuracy of the autonomous driving vehicle meets the preset accuracy of the corresponding speed limit scenario, and the speed limit accuracy is used to characterize the accuracy of speed limiting the autonomous driving vehicle according to the corresponding speed limit scenario; Based on the driving trajectory and the target speed limit scenario corresponding to each trajectory point, the speed of the autonomous driving vehicle is limited.

2. The method according to claim 1, characterized in that: The determining, based on the precise control probabilities corresponding to the multiple speed limit scenarios, a target speed limit scenario corresponding to each trajectory point in the driving trajectory includes: Determine, based on the speed limit intervals corresponding to the multiple speed limit scenarios, at least one candidate speed limit scenario corresponding to each trajectory point, wherein the speed limit interval is used to represent the trajectory point interval in which the speed of the autonomous driving vehicle is restricted by the corresponding speed limit scenario; Based on the precise control probability corresponding to the at least one candidate speed limit scenario, a target speed limit scenario corresponding to the corresponding trajectory point is determined from the at least one candidate speed limit scenario, wherein the precise control probability corresponding to the target speed limit scenario is greater than the precise control probability corresponding to other speed limit scenarios, and the other speed limit scenarios are used to characterize the speed limit scenarios other than the target speed limit scenario in the at least one candidate speed limit scenario.

3. The method according to claim 1 or 2, characterized in that: The precise control probability is determined based on a preset driving requirement of the autonomous driving vehicle, and the preset driving requirement includes at least one of the following: a safe driving requirement, a tracking accuracy requirement, and a parking accuracy requirement.

4. The method according to any one of claims 1 to 3, characterized in that The limiting the speed of the autonomous driving vehicle based on the driving trajectory and the target speed limit scenario corresponding to each trajectory point includes: Based on the target precise control probability corresponding to the target speed limit scenario, determine the speed limit error of the corresponding trajectory point, wherein the speed limit error is used to characterize the error between the speed limit speed of the autonomous driving vehicle and the target speed limit threshold of the target speed limit scenario, and the speed limit speed is used to characterize the speed obtained by limiting the speed of the autonomous driving vehicle according to the target speed limit scenario; The speed of the autonomous driving vehicle is limited based on the driving trajectory and the speed limit error of each trajectory point.

5. The method according to claim 4, characterized in that The determining the speed limit error of the corresponding trajectory point based on the target precise control probability corresponding to the target speed limit scenario includes: Acquire a target probability error model of the target speed limit scenario, wherein the target probability error model is used to characterize a mapping relationship between the target precise control probability and the speed limit error of the corresponding trajectory point; The target precise control probability is input into the target probability error model to obtain the speed limit error of the corresponding trajectory point.

6. The method according to claim 5, characterized in that The step of obtaining a target probability error model for the target speed limit scenario includes: determining a vehicle type of the autonomous vehicle; Acquire multiple probability error models matching the vehicle type, wherein different probability error models correspond to different speed limit scenarios; A probability error model matching the target speed limit scenario is acquired from the multiple probability error models to obtain the target probability error model.

7. The method according to claim 5 or 6, characterized in that The target probability error model is obtained by testing the autonomous driving vehicle for different precise control probabilities in a coasting deceleration scenario.

8. The method according to any one of claims 4 to 7, characterized in that The step of limiting the speed of the autonomous driving vehicle based on the driving trajectory and the speed limit error at each trajectory point includes: Filtering the speed limit error of each trajectory point to obtain a filtered speed limit error of the trajectory point; The speed of the autonomous driving vehicle is limited based on the driving trajectory and the filtered speed limit error of each trajectory point.

9. The method according to any one of claims 1 to 8, characterized in that The obtaining of multiple speed limit scenarios of the autonomous driving vehicle includes: Acquiring vehicle information of the autonomous driving vehicle, wherein the vehicle information includes at least one of the following: perception information, decision information, and scheduling information, wherein the perception information is information obtained by the autonomous driving vehicle perceiving the surrounding environment, the decision information is information obtained by making a decision on the driving behavior of the autonomous driving vehicle based on the perception information, and the scheduling information is information for scheduling the autonomous driving vehicle to perform a task; Based on the vehicle information, the multiple speed limit scenarios and the speed limit interval corresponding to each speed limit scenario are determined.

10. A control device for an autonomous driving vehicle, characterized in that: include: An acquisition module, used to acquire a driving trajectory of the autonomous driving vehicle and a plurality of speed limit scenarios of the autonomous driving vehicle, wherein different speed limit scenarios have different speed limit thresholds for limiting the speed of the autonomous driving vehicle; a determination module, configured to determine a target speed limit scenario corresponding to each trajectory point in the driving trajectory based on the precise control probabilities corresponding to the multiple speed limit scenarios, wherein the precise control probability is used to characterize the probability that the speed limit accuracy of the autonomous driving vehicle meets the preset accuracy of the corresponding speed limit scenario, and the speed limit accuracy is used to characterize the accuracy of speed limiting the autonomous driving vehicle according to the corresponding speed limit scenario; A control module is used to limit the speed of the autonomous driving vehicle based on the driving trajectory and the target speed limit scenario corresponding to each trajectory point.

11. An autonomous driving vehicle, characterized in that: include: A memory storing an executable program; A processor, configured to run the program, wherein the program executes the method according to any one of claims 1 to 9 when running.

Images