Safety corridor generation method, device and equipment, moving tool and medium

Abstract

The invention relates to a safety corridor generation method and device, equipment, a moving tool and a medium, and the method comprises the steps: obtaining target data, and determining a target path point according to an initial path point in the target data, the target data comprising the initial path point, decision information, obstacle data and a three-dimensional map; determining the expansion range of each target path point in each dimension according to the decision information, the vehicle kinematics and the obstacle data; and expanding each target path point according to the expansion range to obtain a plurality of three-dimensional rectangles, and generating a safety corridor on a three-dimensional map by using each three-dimensional rectangle. The safety corridor meeting the decision intention is generated by combining the decision information corresponding to the scene, and the problem that the decision information is not considered when the safety corridor is generated in the prior art is solved.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a method, device, equipment, mobile tool and medium for generating a safe corridor. Background Art

[0002] In the face of complex traffic flows in urban areas, especially on roads with mixed traffic of motor vehicles and non-motor vehicles, trajectory planning needs to be comprehensively considered from the two dimensions of path and speed in order to approximate a safe and intelligent autonomous driving trajectory. In the Frenet coordinate system, this is a three-dimensional trajectory planning problem. The model needs to convert real-world scenarios such as road boundaries and obstacle-occupied spaces into safe corridors as hard constraints of the model in order to obtain a safe trajectory.

[0003] In the prior art, decision information is not taken into account in the process of generating safety corridors.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The present application provides a method, device, equipment, mobile tool and medium for generating a safety corridor to solve the technical problem that decision information is not taken into account when generating the safety corridor.

[0006] According to one aspect of an embodiment of the present application, the present application provides a method for generating a safe corridor, including: acquiring target data, and determining target path points based on initial path points in the target data, wherein the target data includes initial path points, decision information, obstacle data, and a three-dimensional map; determining an expansion range of each target path point in each dimension based on the decision information, vehicle kinematics, and obstacle data; expanding each target path point according to the expansion range to obtain multiple three-dimensional rectangles, so as to generate a safe corridor on the three-dimensional map using each three-dimensional rectangle.

[0007] Optionally, determining the target path points based on the initial path points in the target data includes: obtaining time parameters of each initial path point; determining distribution information of each initial path on the T-axis based on the time parameters, wherein the three-dimensional map includes the T-axis; generating interpolation points on the T-axis at preset intervals based on the distribution information, and determining the interpolation points and the initial path points as target path points.

[0008] Optionally, determining the expansion range of each target path point in each dimension based on the decision information, vehicle kinematics and obstacle data includes: determining multiple time ranges of the three-dimensional rectangle in the time dimension based on preset intervals, wherein the time range includes an upper limit and a lower limit of time; determining the width expansion range of the target path point in the width dimension based on the decision information; determining the length expansion range of the target path point in the length dimension based on the decision information, vehicle kinematics and obstacle data.

[0009] Optionally, determining the width expansion range of the target path point in the width dimension according to the decision information includes: obtaining the lane width, and determining whether to change lanes according to the decision information; if the decision information indicates to change lanes, then based on the width of the two lanes, the width range after expanding to both sides by a preset width is used as the width expansion range; and if the decision information indicates not to change lanes, then based on a single lane, the width range after expanding to both sides by a preset width is used as the width expansion range.

[0010] Optionally, determining the length extension range of the target path point in the length dimension based on the decision information, vehicle kinematics and obstacle data includes: taking 0 as the lower limit of the length extension range, and taking the farthest driving distance based on the vehicle kinematics as the upper limit of the length extension range, wherein the farthest driving distance is the total driving distance of the vehicle from the lower limit to the upper limit under the constraints of the road speed limit and vehicle kinematics; and adjusting the upper limit or the lower limit of the length based on the decision information and the obstacle data.

[0011] Optionally, adjusting the upper or lower length limit according to the decision information and the obstacle data includes: if the decision information indicates to follow or give way, and the obstacle data indicates that the predicted trajectory of an obstacle occupies the current lane, then subtracting the first length from the lower limit of the trajectory corresponding to the predicted trajectory to obtain a new upper length limit; if the decision information indicates to overtake, and the obstacle data indicates that the predicted trajectory of an obstacle occupies the current lane, then adding the second length to the upper limit of the trajectory corresponding to the predicted trajectory to obtain a new lower length limit.

[0012] Optionally, each target path point is expanded according to the expansion range to obtain multiple three-dimensional rectangles, including: within the expansion range, the target path point is expanded in the positive and negative directions of the L axis until it overlaps with the previous three-dimensional rectangle in the L axis direction, and then the target path point is continued to be expanded in the positive and negative directions of the L axis to the vehicle width; the target path point is expanded in the negative direction of the S axis until a collision occurs or the lower limit of the length in the expansion range is reached, and the target path point is expanded in the positive direction of the S axis until a collision occurs or the upper limit of the length of the expansion range corresponding to the current time is reached to obtain the rectangle length; based on the vehicle width, the target path point is continued to be expanded in the positive and negative directions of the L axis until a collision occurs or the road boundary is reached, then the expansion on the L axis is stopped, and the width after expansion is subtracted from the vehicle frame width to obtain the rectangle width; the three-dimensional rectangle is obtained according to the rectangle length and rectangle width of each time range.

[0013] According to another aspect of an embodiment of the present application, the present application provides a device for generating a safe corridor, including: an acquisition module, used to acquire target data, and determine the target path points based on the initial path points in the target data, wherein the target data includes the initial path points, decision information, obstacle data and a three-dimensional map; a determination module, used to determine the expansion range of each target path point in each dimension based on the decision information, vehicle kinematics and obstacle data; an expansion module, used to expand each target path point according to the expansion range to obtain multiple three-dimensional rectangles, so as to generate a safe corridor on the three-dimensional map using each three-dimensional rectangle.

[0014] According to another aspect of an embodiment of the present application, the present application provides an electronic device, including a memory, a processor, a communication interface and a communication bus, wherein the memory stores a computer program that can be run on the processor, the memory and the processor communicate through the communication bus and the communication interface, and the steps of the above method are implemented when the processor executes the computer program.

[0015] According to another aspect of an embodiment of the present application, the present application provides a mobile tool, including the above-mentioned electronic device.

[0016] According to another aspect of an embodiment of the present application, the present application also provides a computer-readable medium having a non-volatile program code executable by a processor, and the program code enables the processor to execute the above method.

[0017] The above technical solution provided by the embodiment of the present application has the following advantages compared with the related art:

[0018] The present application provides a method for generating a safety corridor, including: obtaining target data, and determining target path points according to initial path points in the target data, wherein the target data includes initial path points, decision information, obstacle data, and a three-dimensional map; determining the expansion range of each target path point in each dimension according to the decision information, vehicle kinematics, and obstacle data; expanding each target path point according to the expansion range to obtain multiple three-dimensional rectangles, so as to generate a safety corridor on a three-dimensional map using each three-dimensional rectangle. By combining the decision information corresponding to the scene to generate a safety corridor that meets the decision intent, the problem of not considering the decision information when generating a safety corridor in the prior art is solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0021] Figure 1 A flowchart of an optional method for generating a safety corridor according to an embodiment of the present application;

[0022] Figure 2 An optional three-dimensional rectangular schematic diagram provided according to an embodiment of the present application;

[0023] Figure 3 A schematic diagram of an optional straight road vehicle model provided according to an embodiment of the present application;

[0024] Figure 4 A schematic diagram of an optional curved vehicle model provided according to an embodiment of the present application;

[0025] Figure 5 A schematic diagram of an optional upper limit length adjustment provided according to an embodiment of the present application;

[0026] Figure 6 A schematic diagram of an optional lower limit length adjustment provided according to an embodiment of the present application;

[0027] Figure 7 A schematic diagram of an optional safety corridor provided according to an embodiment of the present application;

[0028] Figure 8 A schematic diagram of the length direction expansion provided for this application;

[0029] Fig. 9 A block diagram for generating an optional safety corridor according to an embodiment of the present application;

[0030] Fig.10 A schematic diagram of an optional electronic device structure provided in an embodiment of the present application. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0032] In the subsequent description, the suffixes such as "module", "component" or "unit" used to represent elements are only used to facilitate the description of the present application and have no specific meaning. Therefore, "module" and "component" can be used interchangeably.

[0033] In the face of complex traffic flows in urban areas, especially on roads with mixed traffic of motor vehicles and non-motor vehicles, trajectory planning needs to be comprehensively considered from the two dimensions of path and speed in order to approximate a safe and intelligent autonomous driving vehicle trajectory. In the Frenet coordinate system, this is the SLT three-dimensional trajectory planning problem. The model needs to convert real-world scenarios such as road boundaries and obstacle-occupied spaces into SLT safety corridors as model hard constraints to obtain a safe trajectory.

[0034] The existing technology uses a particle model without considering the vehicle model; it does not consider decision information, and the expansion space is easily limited. If the expansion is too wide in the L direction (width direction), the expansion length in the S direction (length direction) will be insufficient.

[0035] In order to solve the problems mentioned in the background technology, according to one aspect of the embodiments of the present application, an embodiment of a method for generating a safety corridor is provided, such as Figure 1 As shown, including:

[0036] Step 101, acquiring target data, and determining target path points according to initial path points in the target data, wherein the target data includes initial path points, decision information, obstacle data, and a three-dimensional map;

[0037] Step 103, determining the expansion range of each target path point in each dimension based on the decision information, vehicle kinematics and obstacle data;

[0038] Step 105, expand each target path point according to the expansion range to obtain multiple three-dimensional rectangles, and use each three-dimensional rectangle to generate a safety corridor on the three-dimensional map.

[0039] This application can be applied to the field of trajectory planning in autonomous driving technology, specifically for generating safe corridors.

[0040] Trajectory planning generally includes two parts: decision-making and planning. The planning in this application adopts numerical optimization methods. The optimization model includes cost functions, equality constraints, and inequality constraints. The safe corridor is the inequality constraint in the mathematical model that converts the real traversable space.

[0041] This application is a module of SLT three-dimensional trajectory planning, which converts decision information such as overtaking / yielding / following and road access information into inequality constraints in SLT three-dimensional trajectory planning (expressed in the form of safe corridors). And by adjusting the generation method of corridors, the constraint range is expanded to improve the success rate of solving planning problems.

[0042] The safety corridor provided by this application is composed of multiple three-dimensional rectangles. Figure 2 The schematic diagram of the three-dimensional rectangle provided in this application is shown in the figure. The three-dimensional rectangle is composed of S upper and lower limits (s l ,s u )、L upper and lower limits (L l ,L u ) and T upper and lower limits (T l ,T u )composition.

[0043] This application needs to pre-acquire the safe SLT path (composed of discrete SLT points) searched and generated by the decision module, obstacle decision information (follow, overtake, give way), and SLT map, where the SLT map includes obstacle information of each frame, specifically including the predicted trajectory of dynamic obstacles and static obstacle information.

[0044] Figure 3 Schematic diagram of a straight road vehicle model provided for this application, Figure 4 Schematic diagram of the curved vehicle model provided in this application. Among them, c1 is the length from the front of the vehicle to the rear axle, c2 is the length from the rear of the vehicle to the rear axle, c3 is the width from the left side of the vehicle frame to the rear axle, and c4 is the width from the right side of the vehicle frame to the rear axle.

[0045] This application uses a vehicle model instead of a particle model when generating corridors, which has a higher safety factor.

[0046] As an optional embodiment, determining the target path points based on the initial path points in the target data includes: obtaining time parameters of each initial path point; determining distribution information of each initial path on the T-axis based on the time parameters, wherein the three-dimensional map includes the T-axis; generating interpolation points on the T-axis at preset intervals based on the distribution information, and determining the interpolation points and the initial path points as target path points.

[0047] For example, the initial path point is the initialization seed, and the seed is the SLT path point provided by the decision module and is non-uniformly distributed on the T axis. Each seed has three-dimensional information, that is, each seed has a corresponding time parameter.

[0048] Specifically, the preset interval can be set according to actual conditions. In the preferred embodiment provided in the present application, the preset interval is 0.2s.

[0049] For example, through linear interpolation, an interpolation point is generated every 0.2 seconds on the T axis as the initial value of the three-dimensional rectangle.

[0050] As an optional embodiment, determining the expansion range of each target path point in each dimension based on decision information, vehicle kinematics and obstacle data includes: determining multiple time ranges of the three-dimensional rectangle in the time dimension based on preset intervals, wherein the time range includes an upper time limit and a lower time limit; determining the width expansion range of the target path point in the width dimension based on the decision information; determining the length expansion range of the target path point in the length dimension based on the decision information, vehicle kinematics and obstacle data.

[0051] The dimensions refer to the length dimension, time dimension and width dimension, corresponding to the S axis, T axis and L axis respectively.

[0052] The time range of each three-dimensional rectangle is different, and the time interval between the lower limit of each three-dimensional rectangle is a preset interval.

[0053] For example, taking the seed as an example, the start time of the time range of the three-dimensional rectangle is the seed time (ie, the time parameter), and 0.2 seconds later is the end time.

[0054] It should be noted that the three-dimensional rectangle starts from 0s and there is a three-dimensional rectangle every 0.2s. The lower limit of the time of the first rectangle is 0, plus the preset interval 0.2s to get the upper limit of the time of the first rectangle.

[0055] This application combines the decision results and obstacle information to determine the expansion range of the length dimension and the width dimension. Next, it will explain how to combine the decision results, vehicle kinematics and obstacle information to determine the expansion range of the length dimension and the width dimension.

[0056] As an optional embodiment, determining the width expansion range of the target path point in the width dimension according to the decision information includes: obtaining the lane width, and determining whether to change lanes according to the decision information; if the decision information indicates to change lanes, then based on the widths of the two lanes, the width range after expanding to both sides by a preset width is used as the width expansion range; and if the decision information indicates not to change lanes, then based on a single lane, the width range after expanding to both sides by a preset width is used as the width expansion range.

[0057] Optionally, the preset width in the preferred embodiment provided in the present application is 0.5 meters, but the preset width can be adjusted according to actual conditions.

[0058] For example, if there is no need to change lanes, the lane width is expanded by 0.5 meters on each side. If there is no need to change lanes, the lane width is expanded by 0.5 meters on each side.

[0059] The preset width is the lane width. In the lane avoidance scenario, the vehicle will exceed the lane.

[0060] As an optional embodiment, determining the length extension range of the target path point in the length dimension based on decision information, vehicle kinematics and obstacle data includes: taking 0 as the lower limit of the length extension range, and taking the farthest driving distance based on vehicle kinematics as the upper limit of the length extension range, wherein the farthest driving distance is the total driving distance of the vehicle from the lower limit of time to the upper limit of time under the constraints of road speed limit and vehicle kinematics; adjusting the upper limit or the lower limit of length based on decision information and obstacle data.

[0061] On the S axis, the default lower length limit is 0, and the upper length limit is the maximum driving distance. The maximum driving distance is the maximum distance that can be reached at the upper limit of the rectangle considering the road speed limit and the kinematic limitations of the vehicle.

[0062] As an optional embodiment, adjusting the upper or lower length limit according to the decision information and the obstacle data includes: if the decision information indicates to follow or give way, and the obstacle data indicates that the predicted trajectory of an obstacle occupies the current lane, then subtracting the first length from the lower limit of the trajectory corresponding to the predicted trajectory to obtain a new upper length limit; if the decision information indicates to overtake, and the obstacle data indicates that the predicted trajectory of an obstacle occupies the current lane, then adding the second length to the upper limit of the trajectory corresponding to the predicted trajectory to obtain a new lower length limit.

[0063] The first length is the c1 mentioned above (the length from the front of the vehicle to the rear axle), and the second length is the c2 mentioned above (the length from the rear of the vehicle to the rear axle).

[0064] If the decision result is to follow or yield, when the obstacle prediction trajectory occupies the current driving lane, adjust the upper limit of the length of the three-dimensional rectangle. Figure 5 The schematic diagram of the upper limit length adjustment provided for this application is shown in the figure. At the seed time t, the lower limit S of the space range occupied by the obstacle corresponding to the predicted position minus the length c1 from the front of the vehicle to the rear axle.

[0065] The decision result is to overtake. When the obstacle prediction trajectory occupies the current driving lane, the lower limit of the three-dimensional rectangle length is adjusted. Figure 6 The schematic diagram of the lower limit adjustment of the length provided for this application is shown in the figure. At the seed time t, the upper limit S of the space range occupied by the obstacle corresponding to the predicted position is added to the length c2 from the rear of the vehicle to the rear axle.

[0066] As an optional embodiment, each target path point is expanded according to the expansion range to obtain multiple three-dimensional rectangles, including: within the expansion range, the target path point is expanded in the positive and negative directions of the L axis until it overlaps with the previous three-dimensional rectangle in the L axis direction, and then the target path point is continued to be expanded in the positive and negative directions of the L axis to the vehicle width; the target path point is expanded in the negative direction of the S axis until a collision occurs or the lower limit of the length in the expansion range is reached, and the target path point is expanded in the positive direction of the S axis until a collision occurs or the upper limit of the length of the expansion range corresponding to the current time is reached to obtain the rectangle length; based on the vehicle width, the target path point is continued to be expanded in the positive and negative directions of the L axis until a collision occurs or the road boundary is reached, then the expansion on the L axis is stopped, and the width after expansion is subtracted from the vehicle frame width to obtain the rectangle width; the three-dimensional rectangle is obtained according to the rectangle length and rectangle width of each time range.

[0067] The expansion idea provided by this application is to first expand the space in the L direction to be enough for vehicles to pass, then expand the S direction as long as possible, and then widen the L direction after the expansion in the S direction is completed. If the S direction is not long enough, it will limit the feasible space for vehicles, resulting in solution failure or vehicle speed not being able to increase. This expansion method of making the corridor expansion space as large as possible expands the solution space, increases the possibility of obstacle avoidance, and reduces the probability of solution failure

[0068] In addition, in order to ensure a safe distance between the vehicle and obstacles, after the three-dimensional rectangle is initially obtained, it is necessary to detect whether there are obstacles on the left or right side of the expanded safety corridor. If so, the range of the rectangle on that side is reduced by a certain distance (such as 0.4 meters).

[0069] Specifically, the expansion order is as follows:

[0070] 1. Expand the positive and negative directions of L in sequence, and overlap with the L direction of the previous three-dimensional rectangle;

[0071] 2. Expand L in the positive and negative directions in sequence to reach the vehicle width c3+c4;

[0072] 3. Expand the positive direction of S to the upper limit of S or detect a collision;

[0073] 4. Expand the negative direction of S to the lower limit of S or detect a collision;

[0074] 5. Expand both sides of L. Stop expansion when the L range boundary is detected, or the road boundary is detected as a solid line, or a collision is detected. After the expansion in the L direction is completed, the left side is subtracted from the left side width of the car frame c3, and the right side is subtracted from the right side width of the car frame c4;

[0075] 6. Check whether there are obstacles on the left or right side of the expanded corridor. If so, reduce the corridor on that side by 0.4 (to the safety margin of the obstacle).

[0076] Figure 7 Schematic diagram of the safety corridor provided for this application.

[0077] Specifically, the specific expansion method of the S / L direction provided in this application includes: generating an obstacle space in the SLT map using obstacle prediction information and road semantic information, such as red lights and the latest lane change point. When expanding the three-dimensional rectangle, the S and L directions are expanded at a certain step length to detect whether there is a collision. If there is no collision, the expansion is successful. Figure 8 Schematic diagram of S-direction expansion provided for this application.

[0078] This application considers the vehicle model and provides reliable and safe hard constraints for SLT three-dimensional trajectory optimization. It also expands the feasible space as much as possible and reduces the probability of solution failure. In addition, since the obstacle decision information is taken into account, the generated trajectory can better meet the decision intention.

[0079] The present application provides a method for generating a safety corridor, including: obtaining target data, and determining target path points according to initial path points in the target data, wherein the target data includes initial path points, decision information, obstacle data, and a three-dimensional map; determining the expansion range of each target path point in each dimension according to the decision information, vehicle kinematics, and obstacle data; expanding each target path point according to the expansion range to obtain multiple three-dimensional rectangles, so as to generate a safety corridor on a three-dimensional map using each three-dimensional rectangle. By combining the decision information corresponding to the scene to generate a safety corridor that meets the decision intent, the problem that the decision information is not taken into account when generating a safety corridor in the prior art is solved.

[0080] According to another aspect of the embodiment of the present application, the present application provides a device for generating a safe corridor, such as Fig. 9 As shown, including:

[0081] An acquisition module 902 is used to acquire target data and determine target path points according to initial path points in the target data, wherein the target data includes initial path points, decision information, obstacle data and a three-dimensional map;

[0082] A determination module 904 is used to determine the extension range of each target path point in each dimension based on the decision information, vehicle kinematics and obstacle data;

[0083] The expansion module 906 is used to expand each target path point according to the expansion range to obtain multiple three-dimensional rectangles, so as to generate a safety corridor on the three-dimensional map using each three-dimensional rectangle.

[0084] It should be noted that the acquisition module 902 in this embodiment can be used to execute step 101 in the embodiment of the present application, the determination module 904 in this embodiment can be used to execute step 103 in the embodiment of the present application, and the expansion module 906 in this embodiment can be used to execute step 105 in the embodiment of the present application.

[0085] Optionally, the acquisition module 902 is also used to obtain the time parameters of each initial path point; determine the distribution information of each initial path on the T-axis based on the time parameters, wherein the three-dimensional map includes the T-axis; generate interpolation points on the T-axis at preset intervals based on the distribution information, and determine the interpolation points and the initial path points as target path points.

[0086] Optionally, the determining module 904 includes:

[0087] A time determination submodule, used to determine multiple time ranges of the three-dimensional rectangle in the time dimension according to a preset interval, wherein the time range includes an upper time limit and a lower time limit;

[0088] A width determination submodule is used to determine the width expansion range of the target path point in the width dimension according to the decision information;

[0089] The length determination submodule is used to determine the length extension range of the target path point in the length dimension based on the decision information, vehicle kinematics and obstacle data.

[0090] Optionally, the width determination submodule is also used to obtain the lane width and determine whether to change lanes based on the decision information; if the decision information indicates to change lanes, the width range after expanding the preset width to both sides is used as the width expansion range based on the width of the two lanes; and if the decision information indicates not to change lanes, the width range after expanding the preset width to both sides is used as the width expansion range based on the single lane.

[0091] Optionally, the length determination submodule is further used to use 0 as the lower limit of the length extension range, and use the longest driving distance based on vehicle kinematics as the upper limit of the length extension range, wherein the longest driving distance is the total driving distance of the vehicle from the lower limit to the upper limit under the constraints of road speed limit and vehicle kinematics; the upper limit or the lower limit of the length is adjusted according to the decision information and obstacle data.

[0092] Optionally, the length determination submodule is also used to, if the decision information indicates to follow or give way, and the obstacle data indicates that the predicted trajectory of an obstacle occupies the current lane, subtract the first length from the lower limit of the trajectory corresponding to the predicted trajectory to obtain a new upper limit of length; if the decision information indicates to overtake, and the obstacle data indicates that the predicted trajectory of an obstacle occupies the current lane, then add the second length to the upper limit of the trajectory corresponding to the predicted trajectory to obtain a new lower limit of length.

[0093] Optionally, the expansion module 906 is specifically used to expand the target path points in the positive and negative directions of the L axis within the expansion range until they overlap with the previous three-dimensional rectangle in the L axis direction, and then continue to expand the target path points in the positive and negative directions of the L axis to the vehicle width; expand the target path points in the negative direction of the S axis until a collision occurs or the lower limit of the length in the expansion range is reached, and expand the target path points in the positive direction of the S axis until a collision occurs or the upper limit of the length of the expansion range corresponding to the current time is reached, to obtain the rectangle length; continue to expand the target path points in the positive and negative directions of the L axis based on the vehicle width until a collision occurs or the road boundary is reached, then stop the expansion on the L axis, and subtract the vehicle frame width from the expanded width to obtain the rectangle width; obtain the three-dimensional rectangle according to the rectangle length and rectangle width of each time range.

[0094] It should be noted here that the examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the contents disclosed in the above embodiments.

[0095] According to another aspect of the embodiments of the present application, the present application provides an electronic device, such as Fig.10 As shown, it includes a memory 1001, a processor 1003, a communication interface 1005 and a communication bus 1007. The memory 1001 stores a computer program that can be run on the processor 1003. The memory 1001 and the processor 1003 communicate through the communication interface 1005 and the communication bus 1007. When the processor 1003 executes the computer program, the steps of the above method are implemented.

[0096] The memory and processor in the above electronic device communicate via a communication bus and a communication interface. The communication bus may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus may be divided into an address bus, a data bus, a control bus, etc.

[0097] The memory may include a random access memory (RAM) or a non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0098] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0099] According to another aspect of the embodiments of the present application, a mobile tool is provided, including the above-mentioned electronic device.

[0100] The mobile tool of the present application can be a vehicle or robot with an autonomous driving function, such as a vacuum truck, a floor scrubber, a sprinkler truck, a sewage treatment truck, a sanitation truck, a lawn mower, a golf cart, an entertainment vehicle, an amusement park autonomous driving device, a balance car, a sweeping robot, a food delivery robot, a shopping guide robot, etc.

[0101] In some possible implementations, the electronic device provided in the present application is an autonomous driving domain controller, and the mobile tool provided in the present application is equipped with an autonomous driving domain controller and various sensors for sensing environmental information and the mobile tool's own information (including but not limited to lidar, camera, millimeter wave radar, ultrasonic radar, inertial measurement unit, wheel speed meter, etc.). When the mobile tool is in working state, the autonomous driving domain controller is communicated with the various sensors loaded on the mobile tool, and path planning is performed for the mobile tool based on the environmental information collected by these sensors and the mobile tool's own information, so as to achieve the purpose of controlling the mobile tool to drive automatically.

[0102] According to another aspect of the embodiments of the present application, a computer-readable medium having a non-volatile program code executable by a processor is provided.

[0103] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment will not be described in detail here.

[0104] When the embodiments of the present application are specifically implemented, reference may be made to the above-mentioned embodiments, which have corresponding technical effects.

[0105] It is understood that the embodiments described herein may be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit may be implemented in one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), general purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the functions described in the present application, or a combination thereof.

[0106] For software implementation, the technology described herein can be implemented by a unit that performs the functions described herein. The software code can be stored in a memory and executed by a processor. The memory can be implemented in the processor or outside the processor.

[0107] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0108] Those skilled in the art can 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.

[0109] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules 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 an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0110] 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 network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0111] In addition, each functional unit in each embodiment of the present application 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.

[0112] If the function 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 such an understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium, including several instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a ROM, a RAM, a magnetic disk or an optical disk. It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. Moreover, the term "include", "include" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements that are not explicitly listed, or also includes elements inherent to such a process, method, article or device. Without more constraints, an element defined by the phrase "comprising a..." does not exclude the existence of other identical elements in the process, method, article or apparatus comprising the element.

[0113] The above description is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest range consistent with the principles and novel features applied for herein.

Claims

1. A method for generating a safety corridor, characterized in that: include: Acquiring target data, and determining target path points according to initial path points in the target data, wherein the target data includes the initial path points, decision information, obstacle data, and a three-dimensional map; Determining the extension range of each of the target path points in each dimension according to the decision information, vehicle kinematics and the obstacle data; Each of the target path points is expanded according to the expansion range to obtain a plurality of three-dimensional rectangles, so as to generate a safety corridor on the three-dimensional map using each of the three-dimensional rectangles.

2. The method according to claim 1, characterized in that Determining the target path point according to the initial path point in the target data comprises: Obtaining time parameters of each of the initial path points; Determining distribution information of each of the initial paths on a T-axis according to the time parameter, wherein the three-dimensional map includes the T-axis; Based on the distribution information, interpolation points are generated on the T axis at preset intervals, and the interpolation points and the initial path points are determined as the target path points.

3. The method according to claim 1, characterized in that The step of determining the expansion range of each target path point in each dimension according to the decision information, vehicle kinematics, and obstacle data includes: Determine multiple time ranges of the three-dimensional rectangle in the time dimension according to a preset interval, wherein the time range includes an upper time limit and a lower time limit; Determine a width expansion range of the target path point in a width dimension according to the decision information; The length extension range of the target path point in the length dimension is determined based on the decision information, the vehicle kinematics and the obstacle data.

4. The method according to claim 3, characterized in that Determining the width expansion range of the target path point in the width dimension according to the decision information includes: Obtaining lane width, and determining whether to change lanes based on the decision information; If the decision information indicates to change lanes, based on the widths of the two lanes, a width range after the preset widths are expanded to both sides is used as the width expansion range; and If the decision information indicates not to change lanes, based on a single lane, the width range after expanding the preset width to both sides is used as the width expansion range.

5. The method according to claim 3, characterized in that: The determining of the length extension range of the target path point in the length dimension according to the decision information, the vehicle kinematics and the obstacle data comprises: 0 is used as the lower limit of the length of the length extension range, and the farthest driving distance based on the vehicle kinematics is used as the upper limit of the length of the length extension range, wherein the farthest driving distance is the total driving distance of the vehicle from the lower limit to the upper limit under the constraints of the road speed limit and the vehicle kinematics; The upper limit of the length or the lower limit of the length is adjusted according to the decision information and the obstacle data.

6. The method according to claim 5, characterized in that The adjusting the upper limit or the lower limit of the length according to the decision information and the obstacle data includes: If the decision information indicates to follow or yield, and the obstacle data indicates that the predicted trajectory of an obstacle occupies the current lane, subtract the first length from the lower limit of the trajectory corresponding to the predicted trajectory to obtain a new upper limit of the length; If the decision information indicates overtaking, and the obstacle data indicates that the predicted trajectory of the obstacle occupies the current lane, the second length is added to the trajectory upper limit corresponding to the predicted trajectory to obtain a new length lower limit.

7. The method according to claim 1, characterized in that The target path points are expanded according to the expansion range to obtain a plurality of three-dimensional rectangles, including: Within the expansion range, the target path point is expanded in the positive and negative directions of the L axis until it overlaps with the previous three-dimensional rectangle in the direction of the L axis, and then the target path point is continued to be expanded in the positive and negative directions of the L axis to the width of the vehicle; The target path point is extended in the negative direction of the S axis until a collision occurs or the lower limit of the length in the extended range is reached, and the target path point is extended in the positive direction of the S axis until a collision occurs or the upper limit of the length of the extended range corresponding to the current time is reached, to obtain the length of the rectangle; On the basis of the vehicle width, the target path point is continuously extended in the positive and negative directions of the L axis until a collision occurs or the road boundary is reached, then the extension on the L axis is stopped, and the width after the extension is subtracted from the vehicle frame width to obtain the rectangle width; The three-dimensional rectangle is obtained according to the rectangle length and the rectangle width of each time range.

8. A device for generating a safety corridor, characterized in that: include: An acquisition module, used to acquire target data and determine the target path point according to the initial path point in the target data, wherein the target data includes the initial path point, decision information, obstacle data and a three-dimensional map; A determination module, configured to determine the extension range of each of the target path points in each dimension according to the decision information, vehicle kinematics and obstacle data; The expansion module is used to expand each of the target path points according to the expansion range to obtain multiple three-dimensional rectangles, so as to use each of the three-dimensional rectangles to generate a safety corridor on the three-dimensional map.

9. An electronic device, comprising a memory, a processor, a communication interface and a communication bus, wherein the memory stores a computer program that can be run on the processor, and the memory and the processor communicate through the communication bus and the communication interface, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A mobile tool, characterized in that: Comprising the electronic device as claimed in claim 9.

11. A computer readable medium having a non-volatile program code executable by a processor, characterized in that: The program code enables the processor to execute the method according to any one of claims 1 to 7.

Images