WO2022121207A1 - 轨迹规划方法、装置、设备、存储介质和程序产品 - Google Patents
轨迹规划方法、装置、设备、存储介质和程序产品 Download PDFInfo
- Publication number
- WO2022121207A1 WO2022121207A1 PCT/CN2021/088385 CN2021088385W WO2022121207A1 WO 2022121207 A1 WO2022121207 A1 WO 2022121207A1 CN 2021088385 W CN2021088385 W CN 2021088385W WO 2022121207 A1 WO2022121207 A1 WO 2022121207A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- segment
- robot
- acceleration
- trajectory
- time
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 62
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 16
- 230000001133 acceleration Effects 0.000 claims description 69
- 238000004590 computer program Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 abstract description 4
- 239000004576 sand Substances 0.000 description 26
- 238000010586 diagram Methods 0.000 description 9
- 238000012545 processing Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 3
- 241000283070 Equus zebra Species 0.000 description 2
- 244000035744 Hura crepitans Species 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000011217 control strategy Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000010845 search algorithm Methods 0.000 description 2
- 238000012356 Product development Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1656—Programme controls characterised by programming, planning systems for manipulators
- B25J9/1664—Programme controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1679—Programme controls characterised by the tasks executed
- B25J9/1684—Tracking a line or surface by means of sensors
Definitions
- the present application relates to the technical field of robot trajectory planning, and in particular, to a trajectory planning method, apparatus, device, storage medium and program product.
- the embodiments of the present application provide a trajectory planning method, apparatus, device, storage medium, and program product.
- an embodiment of the present application provides a trajectory planning method, the trajectory planning method includes: acquiring trajectory information and traffic information from the modeling, wherein the trajectory information includes a current position and a destination position of a robot ; Set a plurality of key points on the modeling based on the traffic information; form a connected segment between two key points based on the traffic information; use a preset algorithm to search for the relationship between the current position and the destination position All connected segments between the connected segments are connected as the target trajectory path of the robot according to the search result.
- the traffic information includes traffic road distribution; the step of setting a plurality of key points on the modeling based on the traffic information includes: acquiring each intersection based on the traffic road distribution The key coordinates in the modeling at the entrance and exit of each curve, the edge and middle position of each road, and the key coordinates in the modeling; set the key coordinates at the corresponding position of the modeling as the key point.
- the step of setting a plurality of key points on the modeling based on the traffic information further includes: obtaining the coordinates of the parking permitted positions in the modeling based on the traffic information; The position coordinates of the robot that needs to be parked in the modeling are obtained from the position coordinates that allow parking; the position coordinates are set as the key points at the positions corresponding to the modeling.
- the traffic information includes traffic rules; the step of forming a connected segment between two key points based on the traffic information includes: connecting a key point between the current position of the robot and the destination position A trajectory segment is formed between two points; a trajectory segment that conforms to the traffic rules is set as the connected segment.
- the trajectory planning method further includes: acquiring a dynamic model of the robot, wherein the The dynamic model includes the acceleration and the maximum speed of the robot in each connected segment; obtains the motion time and motion vector of each connected segment of the robot in the target trajectory path; based on the size of the motion time, The motion vector of each connected segment is updated by the acceleration and the maximum speed of the robot in each connected segment.
- the dynamic model of the robot is introduced to optimize the target trajectory path.
- the trajectory planning method further includes: based on the motion vector of the connected segment and The ratio of the acceleration segment to the connected segment is to obtain the speed coefficient of the connected segment; to obtain the start time and the end time of the connected segment; to determine the first standard time based on the start time and speed coefficient of the connected segment; The ratio of the first standard time, the motion vector, the velocity coefficient and the acceleration segment of the connected segment to the connected segment determines the second standard time; the second standard time is determined by the robot based on the size of the motion time
- the step of updating the motion vector of each segment of the connected segment by the acceleration and the maximum speed of the connected segment includes: based on the motion time, the size of the first standard time and the second standard time, through the robot in each segment of the connected segment The acceleration and maximum velocity of the segment update the motion vector of the connected segment for each segment.
- the acceleration and the maximum speed of the robot in each of the connected segments are updated for each segment of the connected segment.
- the step of moving the vector includes: when the moving time is between the starting time and the first standard time, based on the starting time and the acceleration and the maximum acceleration of the robot in each of the connected segments speed to update the motion vector; when the motion time is between the first standard time and the second standard time, based on the first standard time and the robot in each connected segment
- the motion vector is updated according to the acceleration and the maximum speed of The acceleration and maximum velocity of the connected segments update the motion vector.
- the target trajectory path is optimized in different ways according to the comparison result between the movement time of the robot in the target trajectory path and the judgment condition.
- the step of acquiring the velocity coefficient of the connected segment based on the motion vector of the connected segment and the ratio of the acceleration segment to the connected segment includes: based on the motion vector of the connected segment, the The acceleration and the maximum speed of the robot determine the ratio of the acceleration segment to the connected segment; the connection is determined based on the maximum speed of the robot, the motion vector of the connected segment, and the ratio of the acceleration segment to the connected segment The speed factor of the segment.
- an embodiment of the present application further provides a trajectory planning device, the device includes: a first acquisition module configured to acquire trajectory information and traffic information from modeling, wherein the trajectory information includes the current position of the robot and destination location; a setting module, configured to set a plurality of key points on the modeling based on the traffic information; a forming module, configured to form a connected segment between two key points based on the traffic information; a connection module is configured to search all connected segments between the current position and the destination location by using a preset algorithm, and connect the connected segments as the target trajectory path of the robot according to the search result.
- an embodiment of the present application further provides a trajectory planning device, where the trajectory planning device includes a memory and a processor, wherein the memory is coupled to the processor;
- the memory is used for storing program data
- the processor is used for executing the program data to implement the above trajectory planning method.
- an embodiment of the present application further provides a computer storage medium, where the computer storage medium is used for storing program data, and when the program data is executed by the processor, the program data is used to implement the above trajectory planning method.
- an embodiment of the present application further provides a computer program product, where the computer program product includes one or more instructions, and the one or more instructions are suitable for being loaded by a processor and executing the above trajectory planning method.
- the trajectory planning device obtains trajectory information and traffic information from modeling, wherein the trajectory information includes the current position and destination position of the robot; Set multiple key points; form a connected segment between two key points based on traffic information; use a preset algorithm to search for all connected segments between the current location and the destination location, and connect the connected segments as the robot's target trajectory according to the search results path.
- the trajectory planning method of the embodiment of the present application sets a plurality of key points between the current position and the destination position, and forms the target trajectory path of the robot by combining the plurality of key points.
- the trajectory planning device is set based on the traffic information
- the key point that is, the position of the key point is set at a reasonable position in the modeling, which improves the flexibility and practicability of the target trajectory path, so as to realize the point-to-point path planning of the robot in the modeling.
- FIG. 1 is a schematic flowchart of a trajectory planning method provided by an embodiment of the present application.
- FIG. 2 is a schematic structural diagram of a sand table modeling provided by an embodiment of the present application.
- FIG. 3 is a schematic diagram of sand table modeling of multiple trajectory paths provided by an embodiment of the present application.
- FIG. 4 is a schematic diagram of a target trajectory path modeling on a sand table provided by an embodiment of the present application
- FIG. 5 is a schematic flowchart of a trajectory planning method provided by an embodiment of the present application.
- 6A is a schematic flowchart of a trajectory planning method provided by an embodiment of the present application.
- 6B is a schematic flowchart of a method for setting key points provided by an embodiment of the present application.
- FIG. 7 is a schematic diagram of sand table modeling of an optimized target trajectory path provided by an embodiment of the present application.
- FIG. 8 is a schematic structural diagram of a trajectory planning apparatus provided by an embodiment of the present application.
- FIG. 9 is a schematic structural diagram of a trajectory planning device provided by an embodiment of the present application.
- FIG. 10 is a schematic structural diagram of a computer storage medium provided by an embodiment of the present application.
- FIG. 1 is a schematic flowchart of a trajectory planning method provided by an embodiment of the present application.
- the trajectory planning method of the embodiment of the present application is applied to a trajectory planning device, where the trajectory planning device of the embodiment of the present application may be a server, a terminal device, or a system in which a server and a terminal device cooperate with each other.
- the various parts included in the electronic device such as each unit, subunit, module, and submodule, may all be provided in the server, in the terminal device, or in the server and the terminal device respectively.
- the method steps can also be performed by a processor running computer executable code.
- the above server may be hardware or software.
- the server When the server is hardware, it can be implemented as a distributed server cluster composed of multiple servers, or can be implemented as a single server.
- the server When the server is software, it can be implemented as multiple software or software modules, such as software or software modules for providing distributed servers, or can be implemented as a single software or software module, which is not specifically limited here.
- the trajectory planning method of this embodiment specifically includes the following steps:
- S101 Acquire trajectory information and traffic information from modeling, where the trajectory information includes a current position and a destination position of the robot.
- the modeling in this embodiment of the present application may be a sand table for simulating advanced urban road traffic, for example, a sand table designed based on 212 Chinese urban road traffic scenarios.
- the sandbox may include elements such as lanes, traffic signs, traffic lights, and road gates, wherein lanes, traffic signs, traffic lights, and road gates are in a 1:10 scale.
- the sand table visualizes road traffic events by controlling the state of the elements in it, improving the display effect of the sand table.
- the trajectory planning equipment is connected to the sand table modeling, and the access method can be connected through a universal serial bus (Universal Serial Bus, USB) interface, or a wireless communication connection.
- the trajectory planning equipment obtains trajectory information and traffic information through the positioning system of sand table modeling.
- the positioning system for sand table modeling includes several camera devices above the sand table, and the camera devices are configured to capture real-time traffic images on the sand table.
- the positioning system for sand table modeling uses the real-time traffic images collected by the camera devices to obtain trajectory information and traffic information .
- the trajectory information includes the robot's current position and destination position in the sand table modeling, and the traffic information includes traffic rules and traffic road distribution.
- the operating rules of the robot are determined by the traffic rules modeled on the sand table, and the traffic rules are consistent with the traffic rules in real life.
- the trajectory planning equipment sets a number of key points on the sand table modeling based on the distribution of traffic roads. These key points are distributed on the road according to the direction of the traffic roads.
- the positions of the key points are the positions that the robot can reach during normal operation. , such as road edges, road bends, and road junctions.
- the purpose of preset key points by the trajectory planning device is to provide a reasonable search space for trajectory planning, and the generated trajectory path must pass through several key points and then reach the destination position.
- a connected segment is formed between two key points based on the traffic information.
- the trajectory planning device determines the destination position of the trajectory planning target based on the trajectory information, and obtains the current position of the robot through the positioning system modeled by the sand table.
- the trajectory planning device needs to design a directed adjacency matrix between two key points between the current position and the destination position for traffic rule design in some embodiments. If the two key points can be connected under the traffic rules, the line is set to 1 in the adjacency matrix, that is, the line between the two key points is set as a connected segment.
- the trajectory planning device is connected to multiple connected segments between the current position and the destination location of the robot through multiple key points. Feasible connected segment of the trace.
- the trajectory planning device also needs to select the nearest and reasonable connected segments from a plurality of feasible connected segments and connect them into the final target trajectory path.
- S104 Use a preset algorithm to search for all connected segments between the current position and the destination location, and connect the connected segments as the target trajectory path of the robot according to the search result.
- the trajectory planning device may use a preset search algorithm to search for the best trajectory path from multiple trajectory paths as the target trajectory path.
- the preset search algorithms include but are not limited to: Dijkstra algorithm, A* (A-Star) algorithm, RRT algorithm, artificial potential field method, and the like.
- the A-Star algorithm is the most effective method for solving the shortest path in a static road network.
- the actual cost to node n, h(n) is the estimated cost of the best path from node n to the destination location.
- the trajectory planning path uses the A-Star algorithm to calculate the evaluation function of all connected segments between the current position and the destination location, and connects the multi-connected segments with the smallest combined estimated function value into the target trajectory path of the robot.
- the trajectory planning device accesses the modeling, and obtains trajectory information and traffic information from the modeling, wherein the trajectory information includes the current position and destination position of the robot; based on the traffic information, a number of key points are set in the modeling Based on traffic information, a connected segment is formed between two key points; a preset algorithm is used to search for all connected segments between the current position and the destination location, and the connected segments are connected as the target trajectory path of the robot according to the search results.
- the trajectory planning method of the embodiment of the present application sets a plurality of key points between the current position and the destination position, and forms the target trajectory path of the robot by combining the plurality of key points.
- the trajectory planning device is set based on the traffic information
- the key point that is, the position of the key point is set at a reasonable position in the modeling, which improves the flexibility and practicability of the target trajectory path, so as to realize the point-to-point path planning of the robot in the modeling.
- FIG. 5 is a schematic flowchart of a trajectory planning method provided by an embodiment of the present application.
- the trajectory planning method of this embodiment specifically includes the following steps:
- S201 Acquire trajectory information and traffic information from modeling, where the trajectory information includes a current position and a destination position of the robot.
- S202 Based on the distribution of traffic roads, obtain the key coordinates of the entrance and exit of each intersection, the entrance and exit of each curve, and the edge and middle positions of each road in modeling.
- the trajectory planning device obtains the key coordinates of the entrance and exit of each intersection, the entrance and exit of each curve, and the edge and middle position of each road in the sand table modeling based on the distribution of traffic roads modeled by the sand table.
- the trajectory planning equipment sets multiple key points on the sand table modeling based on the key coordinates to generate the sand table modeling as shown in Figure 2.
- the trajectory planning device may also rank the generated keypoints based on traffic rules. For example, on a road, the trajectory planning device ranks the key points on the road according to the drivable direction of the road. Therefore, the arrangement order of key points also directly reflects the traffic rules of sand table modeling to a certain extent.
- a trajectory segment is formed between the key points between the current position of the robot and the destination position.
- the trajectory planning equipment consists of two key points, and the line whose adjacency matrix value is 1 is set as a trajectory segment, and the trajectory segment is a directed trajectory segment.
- the trajectory planning device also needs to combine the running time and the distribution of traffic roads to determine whether the trajectory segment complies with the traffic rules in some embodiments, wherein the traffic rules include rules such as odd and even traffic restrictions, and traffic restrictions according to time. .
- the trajectory planning device sets the trajectory segments that conform to the traffic rules as connected segments.
- FIG. 6A is a schematic flowchart of a trajectory planning method provided by the embodiment of the present application.
- the trajectory planning method of this embodiment specifically includes the following steps:
- S301 Acquire trajectory information and traffic information from modeling, where the trajectory information includes the current position and destination position of the robot.
- the step of setting multiple key points on the modeling based on the traffic information further includes:
- the traffic information includes traffic rules and traffic road distribution, wherein the traffic rules include rules such as odd and even numbers, and time limits; the traffic rules here can be consistent with the traffic rules in real life.
- Traffic road distribution includes the distribution of traversable roads.
- the trajectory planning device can determine the coordinates of the position where the robot is allowed to park based on the traffic rules and the traffic road distribution on the modeling. For example, the location that does not affect the passage of other robots in the modeling can be determined as the location where parking is allowed, or the robot is allowed to park in front of the zebra crossing when encountering a red light.
- the trajectory planning device may determine the position coordinates where the robot needs to park in the modeling according to the actual operation requirements of the robot from the position coordinates that allow parking. For example, determine the coordinates of the location where the robot is allowed to park in front of a zebra crossing when encountering a red light.
- the trajectory planning device may set the coordinates of the position to be parked as a key point at the position corresponding to the modeling.
- S303 A connected segment is formed between two key points based on the traffic information.
- S304 Use a preset algorithm to search for all connected segments between the current position and the destination location, and connect the connected segments as the target trajectory path of the robot according to the search result.
- the target trajectory path obtained through the above steps is logically reasonable and feasible, but in actual operation, the dynamic model of the robot needs to be considered in some embodiments.
- the trajectory planning equipment needs to optimize the target trajectory path according to the dynamic model of the robot.
- the dynamic model constraints of the robot mainly include the acceleration of the vertical axis and the turning radius.
- the turning radius can be equivalent to the acceleration of the horizontal axis.
- the trajectory planning equipment needs to ensure that the acceleration of any segment of the target planning path must meet the maximum acceleration constraint. Please continue to the following steps:
- S305 Obtain a dynamic model of the robot, wherein the dynamic model includes the acceleration and the maximum speed of the robot in each connected segment.
- the trajectory planning device obtains the proportion of the acceleration segment in the connected segment based on the motion vector of the connected segment, the acceleration and the maximum speed of the robot.
- the calculation formula (1) is as follows:
- ⁇ is the ratio of the acceleration segment to the entire connected segment
- P is the motion vector of the connected segment
- a is the acceleration
- v is the maximum velocity
- the motion vector of the connected segment includes the direction of the connected segment and the length of the connected segment, and the direction of the connected segment represents the movable direction of the robot in the connected segment.
- the trajectory planning device obtains the velocity coefficient of the connected segment based on the motion vector of the connected segment and the ratio of the acceleration segment to the connected segment, for example, the calculation formula (2) is as follows:
- ⁇ is the velocity coefficient of the connected segment.
- the trajectory planning device obtains the expected start time and expected end time of each connected segment, and obtains the first standard time of the connected segment according to the expected start time of the connected segment and the velocity coefficient, for example, the calculation formula ( 3) as follows:
- t 0 is the expected start time of the trajectory segment
- t 1 is the first standard time of the trajectory segment.
- the trajectory planning device determines the second standard time based on the first standard time of the connected segment, the motion vector, the velocity coefficient, and the ratio of the acceleration segment to the connected segment.
- the calculation formula (4) is as follows:
- t 2 is the second standard time of the connected segment.
- the trajectory planning device may update the motion vector of each connected segment through the acceleration and maximum speed of the robot in each connected segment based on the size of the motion time.
- the trajectory planning device may perform the following steps to update the motion vector of the connected segment.
- S307 Based on the motion time, the first standard time and the second standard time, update the motion vector of each connected segment through the acceleration and the maximum speed of the robot in each connected segment.
- the trajectory planning device optimizes the motion vector of each connected segment according to the motion time of the robot, the size of the first standard time and the second standard time.
- the optimization formula (5) is as follows:
- Ti(P, t) is the motion path of the connected segment.
- the robot When the movement time is between the start time and the first standard time, the robot is in an accelerated state, and the trajectory planning device updates the movement vector based on the start time.
- the robot When the movement time is between the first standard time and the second standard time, the robot is in a constant speed state, and the trajectory planning device updates the movement vector based on the first standard time.
- the robot When the motion time is between the second standard time and the termination time, the robot is in a deceleration state, and the trajectory planning device updates the motion vector based on the termination time.
- the trajectory planning device merges the updated trajectory segments to obtain a complete trajectory path as shown in Figure 7. So far, the trajectory planning equipment has completed the trajectory planning between the starting point and the destination point, and the generated trajectory takes into account the current position, speed, and attitude of the robot, and generates a smooth path that satisfies the curvature continuity, which can be directly solved according to this path.
- the speed and control configuration of the robot at any time allows the robot to move according to the specified control strategy to perfectly follow the specified trajectory.
- the embodiments of the present application provide a trajectory planning apparatus, which includes each module included and each submodule included in each module, which can be implemented by a processor in a computer device; of course, it can also be It is implemented by a specific logic circuit; in the process of implementation, the processor may be a central processing unit (CPU), a microprocessor (MPU), a digital signal processor (DSP) or a field programmable gate array (FPGA) or the like.
- the processor may be a central processing unit (CPU), a microprocessor (MPU), a digital signal processor (DSP) or a field programmable gate array (FPGA) or the like.
- FIG. 8 is a schematic structural diagram of a trajectory planning device provided by an embodiment of the present application. As shown in FIG. 8 , the device 800 includes:
- a first obtaining module 810 configured to obtain trajectory information and traffic information from modeling, wherein the trajectory information includes the current position and destination position of the robot;
- a setting module 820 configured to set a plurality of key points on the modeling based on the traffic information
- forming module 830 configured to form a connected segment between two key points based on the traffic information
- the connection module 840 is configured to use a preset algorithm to search for all connected segments between the current position and the destination location, and connect the connected segments as the target trajectory path of the robot according to the search result.
- the traffic information includes traffic road distribution
- the setting module includes: a first acquisition sub-module configured to acquire the entrance and exit of each intersection, each curve based on the traffic road distribution The key coordinates of the entrance and exit of each road and the edge and middle position of each road in the modeling; the first setting sub-module is configured to set the key coordinates at the position corresponding to the modeling as the key point .
- the setting module further includes: a second obtaining sub-module, configured to obtain, based on the traffic information, the location coordinates of the allowed parking in the modeling; a third obtaining sub-module, configured to obtain from the allowed parking The position coordinates of the robot that needs to be parked in the modeling are obtained from the parking position coordinates; the second setting sub-module is configured to set the position coordinates at the position corresponding to the modeling as the key point.
- the traffic information includes traffic rules;
- the forming module includes: a forming sub-module configured to form trajectory segments between key points between the robot's current position and the destination position;
- the third setting sub-module is configured to set the track segment conforming to the traffic rule as the connected segment.
- the apparatus further includes: a second acquisition module configured to acquire a dynamic model of the robot, wherein the dynamic model includes the acceleration and the maximum acceleration of the robot in each of the connected segments speed; a third acquisition module, configured to acquire the motion time and motion vector of each connected segment of the robot in the target trajectory path; an update module, configured to be based on the size of the motion time, through the robot in each The acceleration and maximum velocity of the connected segment of the segment update the motion vector of each segment of the connected segment.
- a second acquisition module configured to acquire a dynamic model of the robot, wherein the dynamic model includes the acceleration and the maximum acceleration of the robot in each of the connected segments speed
- a third acquisition module configured to acquire the motion time and motion vector of each connected segment of the robot in the target trajectory path
- an update module configured to be based on the size of the motion time, through the robot in each The acceleration and maximum velocity of the connected segment of the segment update the motion vector of each segment of the connected segment.
- the apparatus further includes: a fourth obtaining module configured to obtain the velocity coefficient of the connected segment based on the motion vector of the connected segment and the ratio of the acceleration segment to the connected segment; a fifth obtaining module , configured to obtain the start time and the end time of the connected segment; the first determination module, configured to determine the first standard time based on the start time and velocity coefficient of the connected segment; the second determination module, configured to be based on the The ratio of the first standard time, motion vector, velocity coefficient and acceleration segment of the connected segment to the connected segment determines the second standard time; the update module is also configured to be based on the motion time, the first standard time and the first standard time.
- the size of the standard time is to update the motion vector of each connected segment by the acceleration and the maximum speed of the robot in each connected segment.
- the update module includes: a first update sub-module configured to, when the movement time is between the start time and the first standard time, based on the start time and the The robot updates the motion vector at the acceleration and the maximum speed of each connected segment;
- the second update sub-module is configured to when the motion time is between the first standard time and the second standard time time, the motion vector is updated based on the first standard time and the acceleration and the maximum speed of the robot in each of the connected segments;
- the third update sub-module is configured to be configured when the motion time is in the Between the second standard time and the termination time, the motion vector is updated based on the second standard time and the acceleration and the maximum speed of the robot in each of the connected segments.
- the fourth acquisition module includes: a first determination sub-module configured to determine the ratio of the acceleration segment to the connected segment based on the motion vector of the connected segment, the acceleration and the maximum speed of the robot ; a second determination sub-module, configured to determine the velocity coefficient of the connected segment based on the maximum speed of the robot, the motion vector of the connected segment, and the ratio of the acceleration segment to the connected segment.
- an embodiment of the present application also proposes a trajectory planning device.
- FIG. 9 is a schematic structural diagram of a trajectory planning device provided by an embodiment of the present application.
- the trajectory planning device 400 in this embodiment includes a processor 41 , a memory 42 , an input and output device 43 and a bus 44 .
- the processor 41, the memory 42, and the input/output device 43 are respectively connected to the bus 44, the memory 42 stores program data, and the processor 41 is used for executing the program data to implement the trajectory planning method described in the above embodiments.
- the processor 41 may also be referred to as a central processing unit (Central Processing Unit, CPU).
- the processor 41 may be an integrated circuit chip with signal processing capability.
- the processor 41 can also be a general-purpose processor, a digital signal processor (Digital Signal Processing, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field programmable gate array (Field Programmable Gate Array, FPGA) or other possible Programming logic devices, discrete gate or transistor logic devices, discrete hardware components.
- a general purpose processor may be a microprocessor or the processor 41 may be any conventional processor or the like.
- An embodiment of the present application further provides a computer storage medium.
- the computer storage medium 500 is used to store program data 51 , and when the program data 51 is executed by the processor, it is used to realize the trajectory described in the above embodiment. planning method.
- the trajectory planning methods described in the above embodiments of the present application when implemented, exist in the form of software functional units and are sold or used as independent products, and can be stored in a device, such as a computer-readable storage medium.
- a device such as a computer-readable storage medium.
- the medium includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the methods described in the various embodiments of the present invention.
- the aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk and other media that can store program codes .
- the trajectory planning method provided by the embodiment of the present application sets a plurality of key points between the current position and the destination position, and forms the target trajectory path of the robot by combining the plurality of key points. Since the trajectory planning device sets the key points based on the traffic information, That is, the position of the key point is set at a reasonable position in the modeling, which improves the flexibility and practicability of the target trajectory path, so as to realize the point-to-point path planning of the robot in the modeling.
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Manipulator (AREA)
- Navigation (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
Abstract
一种轨迹规划方法,包括:从建模获取轨迹信息和交通信息,其中,轨迹信息包括机器人的当前位置和目的地位置;基于交通信息在建模上设置多个关键点;基于交通信息在两两关键点之间形成连通段;采用预设算法搜索当前位置和目的地位置之间的所有连通段,按照搜索结果将连通段连接为机器人的目标轨迹路径。通过该轨迹规划方法,能够实现机器人在建模上点对点之间的路径规划。还提供一种轨迹规划装置、设备、存储介质和程序产品。
Description
相关申请的交叉引用
本公开基于申请号为202011455167.9、申请日为2020年12月10日、申请名称为“一种轨迹规划方法、装置以及计算机存储介质”的中国专利申请提出,并要求该中国专利申请的优先权,该中国专利申请的全部内容在此以引入方式并入本公开。
本申请涉及机器人轨迹规划技术领域,特别是涉及一种轨迹规划方法、装置、设备、存储介质和程序产品。
近年来,人工智能(Artificial Intelligence,AI)教育与自动驾驶逐渐变得火热,将二者结合在一起的智能机器人成为了大部分公司产品开发的重点。这种智能机器人通常在封闭沙盘运行,可供学生学习机器人控制策略以及路径规划等方面的知识。除此之外,这种具有自动驾驶功能的机器人作为展品的展示效果也是非常好的。
发明内容
本申请实施例提供了一种轨迹规划方法、装置、设备、存储介质和程序产品。
第一方面,本申请实施例提供了一种轨迹规划方法,所述轨迹规划方法包括:从所述建模获取轨迹信息和交通信息,其中,所述轨迹信息包括机器人的当前位置和目的地位置;基于所述交通信息在所述建模上设置多个关键点;基于所述交通信息在两两关键点之间形成连通段;采用预设算法搜索所述当前位置和所述目的地位置之间的所有连通段,按照搜索结果将所述连通段连接为所述机器人的目标轨迹路径。
在一些实施例中,所述交通信息包括交通道路分布情况;所述基于所述交通信息在所述建模上设置多个关键点的步骤,包括:基于所述交通道路分布情况获取每个路口的进出口处、每个弯道的进出口处以及每条道路的边缘和中间位置在所述建模中的关键坐标;将所述关键坐标在所述建模对应的位置设置为所述关键点。
通过上述方式,提出了一种基于道路分布情况设置关键点的方法。
在一些实施例中,所述基于所述交通信息在所述建模上设置多个关键点的步骤,还包括:基于所述交通信息获取所述建模中允许停泊的位置坐标;从所述允许停泊的位置坐标中获取所述机器人在所述建模中需要停泊的位置坐标;将所述位置坐标在所述建模 对应的位置设置为所述关键点。
通过上述方式,提出了一种基于机器人情况设置关键点的方法。
在一些实施例中,所述交通信息包括交通规则;所述基于所述交通信息在两两关键点之间形成连通段的步骤包括:将所述机器人的当前位置和目的地位置之间的关键点两两之间组成轨迹段;将符合所述交通规则的轨迹段设置为所述连通段。
通过上述方式,引入交通规则判断两两关键点连成的轨迹段是否合理。
在一些实施例中,所述按照搜索结果将所述连通段连接为所述机器人的目标轨迹路径的步骤之后,所述轨迹规划方法还包括:获取所述机器人的动力学模型,其中,所述动力学模型包括所述机器人在每段所述连通段的加速度和最大速度;获取所述机器人在所述目标轨迹路径中每段连通段的运动时间以及运动向量;基于所述运动时间的大小,通过所述机器人在每段所述连通段的加速度和最大速度更新每段所述连通段的运动向量。
通过上述方式,引入机器人的动力学模型优化目标轨迹路径。
在一些实施例中,所述获取所述机器人在所述目标轨迹路径中每段连通段的运动时间以及运动向量的步骤之后,所述轨迹规划方法还包括:基于所述连通段的运动向量以及加速度段占所述连通段的比例获取所述连通段的速度系数;获取所述连通段的起始时间和终止时间;基于所述连通段的起始时间和速度系数确定第一标准时间;基于所述连通段的第一标准时间、运动向量、速度系数和加速度段占所述连通段的比例确定第二标准时间;所述基于所述运动时间的大小,通过所述机器人在每段所述连通段的加速度和最大速度更新每段所述连通段的运动向量的步骤,包括:基于所述运动时间、第一标准时间和第二标准时间的大小,通过所述机器人在每段所述连通段的加速度和最大速度更新每段所述连通段的运动向量。
通过上述方式,计算目标轨迹路径优化的判断条件。
在一些实施例中,所述基于所述运动时间、第一标准时间和第二标准时间的大小,通过所述机器人在每段所述连通段的加速度和最大速度更新每段所述连通段的运动向量的步骤,包括:当所述运动时间在所述起始时间和所述第一标准时间之间时,基于所述起始时间以及所述机器人在每段所述连通段的加速度和最大速度将所述运动向量进行更新;当所述运动时间在所述第一标准时间和所述第二标准时间之间时,基于所述第一标准时间以及所述机器人在每段所述连通段的加速度和最大速度将所述运动向量进行更新;当所述运动时间在所述第二标准时间和所述终止时间之间时,基于所述第二标准时间以及所述机器人在每段所述连通段的加速度和最大速度将所述运动向量进行更新。
通过上述方式,根据机器人在目标轨迹路径中的运动时间与判断条件的比较结果对目标轨迹路径进行不同方式的优化。
在一些实施例中,所述基于所述连通段的运动向量以及加速度段占所述连通段的比 例获取所述连通段的速度系数的步骤,包括:基于所述连通段的运动向量、所述机器人的加速度和最大速度确定所述加速度段占所述连通段的比例;基于所述机器人的最大速度、所述连通段的运动向量以及所述加速度段占所述连通段的比例确定所述连通段的速度系数。
通过上述方式,提出一种计算每个轨迹段中加速度段的长度比例。
第二方面,本申请实施例还提供了一种轨迹规划装置,所述装置包括:第一获取模块,配置为从建模获取轨迹信息和交通信息,其中,所述轨迹信息包括机器人的当前位置和目的地位置;设置模块,配置为基于所述交通信息在所述建模上设置多个关键点;形成模块,配置为基于所述交通信息在两两关键点之间形成连通段;连接模块,配置为采用预设算法搜索所述当前位置和所述目的地位置之间的所有连通段,按照搜索结果将所述连通段连接为所述机器人的目标轨迹路径。
第三方面,本申请实施例还提供了一种轨迹规划设备,所述轨迹规划设备包括存储器和处理器,其中,所述存储器与所述处理器耦接;
其中,所述存储器用于存储程序数据,所述处理器用于执行所述程序数据以实现如上述的轨迹规划方法。
第四方面,本申请实施例还提供了一种计算机存储介质,所述计算机存储介质用于存储程序数据,所述程序数据在被处理器执行时,用以实现如上述的轨迹规划方法。
第五方面,本申请实施例还提供了一种计算机程序产品,所述计算机程序产品包括一条或多条指令,所述一条或多条指令适于由处理器加载并执行上述的轨迹规划方法。
与现有技术相比,本申请实施例的有益效果是:轨迹规划设备从建模获取轨迹信息和交通信息,其中,轨迹信息包括机器人的当前位置和目的地位置;基于交通信息在建模上设置多个关键点;基于交通信息在两两关键点之间形成连通段;采用预设算法搜索当前位置和目的地位置之间的所有连通段,按照搜索结果将连通段连接为机器人的目标轨迹路径。通过上述方式,本申请实施例的轨迹规划方法通过在当前位置和目的地位置之间设置多个关键点,并通过多个关键点组合形成机器人的目标轨迹路径,由于轨迹规划设备基于交通信息设置关键点,即关键点的位置设置于建模中的合理位置,提高目标轨迹路径的灵活性和实用性,从而实现机器人在建模上点对点之间的路径规划。
为了更清楚地说明本发明实施例中的技术方案,下面将对实施例描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他的附图。其中:
图1是本申请实施例提供的一种轨迹规划方法的流程示意图;
图2是本申请实施例提供的一种沙盘建模的结构示意图;
图3是本申请实施例提供的多条轨迹路径在沙盘建模的示意图;
图4是本申请实施例提供的目标轨迹路径在沙盘建模的示意图;
图5是本申请实施例提供的一种轨迹规划方法的流程示意图;
图6A是本申请实施例提供的一种轨迹规划方法的流程示意图;
图6B是本申请实施例提供的一种设置关键点方法的流程示意图;
图7是本申请实施例提供的优化后目标轨迹路径在沙盘建模的示意图;
图8是本申请实施例提供的一种轨迹规划装置的结构示意图;
图9是本申请实施例提供的一种轨迹规划设备的结构示意图;
图10是本申请实施例提供的一种计算机存储介质的结构示意图。
实施方式
下面将结合本申请实施例中的附图,对本申请实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例仅是本申请的一部分实施例,而不是全部的实施例。基于本申请中的实施例,本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例,都属于本申请保护的范围。
为了机器人在建模上点对点之间的路径规划,本申请实施例提出了一种轨迹规划方法,请参阅图1,图1是本申请实施例提供的一种轨迹规划方法的流程示意图。
本申请实施例的轨迹规划方法应用于一种轨迹规划设备,其中,本申请实施例的轨迹规划设备可以为服务器,也可以为终端设备,还可以为由服务器和终端设备相互配合的系统。相应地,电子设备包括的各个部分,例如各个单元、子单元、模块、子模块可以全部设置于服务器中,也可以全部设置于终端设备中,还可以分别设置于服务器和终端设备中。此外,该方法步骤也可以通过处理器运行计算机可执行代码的方式执行。
在一些实施例中,上述服务器可以是硬件,也可以是软件。当服务器为硬件时,可以实现成多个服务器组成的分布式服务器集群,也可以实现成单个服务器。当服务器为软件时,可以实现成多个软件或软件模块,例如用来提供分布式服务器的软件或软件模块,也可以实现成单个软件或软件模块,在此不做具体限定。
如图1所示,本实施例的轨迹规划方法具体包括以下步骤:
S101:从建模获取轨迹信息和交通信息,其中,轨迹信息包括机器人的当前位置和目的地位置。
其中,本申请实施例的建模可以为一种用于模拟城市先进道路交通的沙盘,例如是基于212种中国城市道路交通场景设计的沙盘。例如请参阅图2,沙盘中可以包括车道、交通标志、交通信号灯以及道路闸机等元素,其中,车道、交通标志、交通信号灯以及道路闸机按1比10的微缩比例。沙盘通过控制其中元素的状态将道路交通事件可视化, 提升沙盘的展示效果。
其中,轨迹规划设备接入沙盘建模,接入方式可以为通过通用串行总线(Universal Serial Bus,USB)接口连接,或无线通信连接。轨迹规划设备通过沙盘建模的定位系统定位获取轨迹信息和交通信息。例如,沙盘建模的定位系统包括沙盘上方的若干摄像设备,摄像设备配置为拍摄所述沙盘上的实时交通图像,沙盘建模的定位系统利用摄像设备采集的实时交通图像获取轨迹信息和交通信息。轨迹信息包括机器人在沙盘建模中的当前位置和目的地位置,交通信息包括交通规则和交通道路分布情况。轨迹规划设备接入沙盘建模后,可获悉沙盘建模的三维模型以及机器人在沙盘建模中可运行的区域以及运行规则。机器人的运行规则由沙盘建模的交通规则决定,交通规则与现实生活中的交通规则一致。
S102:基于交通信息在建模上设置多个关键点。
其中,轨迹规划设备基于交通道路分布情况在沙盘建模上设置多个关键点,这些关键点根据交通道路的走向分布在道路上,关键点的位置均为机器人在正常运行过程中可以到达的位置,例如道路边缘、道路拐弯处以及道路交汇处等。
其中,轨迹规划设备预设关键点的目的是为轨迹规划提供合理的搜索空间,生成的轨迹路径一定是穿过若干关键点然后到达目的地位置。
S103:基于交通信息在两两关键点之间形成连通段。
其中,轨迹规划设备基于轨迹信息确定此次轨迹规划目标的目的地位置,以及通过沙盘建模的定位系统获取机器人的当前位置。
由于最终的目标轨迹路径是有向路径,轨迹规划设备需要在一些实施例中设计当前位置和目的地位置之间两两关键点之间的有向邻接矩阵以进行交通规则设计。两个关键点之间若在交通规则下能够进行连接,则在邻接矩阵中将该线路设置为1,即将两个关键点之间的线路设置为连通段。
由此,轨迹规划设备通过多个关键点在机器人的当前位置和目的地位置之间连接成多条连通段,组成每条连通段的临界矩阵均为1,即连接成的连通段为可循迹的可行连通段。
如图3所示,一般而言,由于关键点的数量较多,连接成的连通段数量也很多。因此,轨迹规划设备还需要从多条可行连通段中筛选中最近且合理的连通段连接成最终的目标轨迹路径。
S104:采用预设算法搜索当前位置和目的地位置之间的所有连通段,按照搜索结果将连通段连接为机器人的目标轨迹路径。
其中,轨迹规划设备可以采用预设的搜索算法,从多条轨迹路径中搜索出最佳的轨迹路径作为目标轨迹路径。其中,预设的搜索算法包括但不限于:Dijkstra算法、A*(A-Star)算法、RRT算法、人工势场法等。
以A-Star算法为例,A-Star算法是一种静态路网中求解最短路最有效的方法。公式 表示为:f(n)=g(n)+h(n),其中f(n)是节点n从当前位置到目的地位置的估价函数,g(n)是在状态空间中从当前位置到节点n的实际代价,h(n)是从节点n到目的地位置最佳路径的估计代价。例如,轨迹规划路径采用A-Star算法计算当前位置到目的地位置之间的所有连通段的估价函数,将组合估计函数值最小的多段连通段连接成机器人的目标轨迹路径。
在本实施例中,轨迹规划设备接入建模,并从建模获取轨迹信息和交通信息,其中,轨迹信息包括机器人的当前位置和目的地位置;基于交通信息在建模上设置多个关键点;基于交通信息在两两关键点之间形成连通段;采用预设算法搜索当前位置和目的地位置之间的所有连通段,按照搜索结果将连通段连接为机器人的目标轨迹路径。通过上述方式,本申请实施例的轨迹规划方法通过在当前位置和目的地位置之间设置多个关键点,并通过多个关键点组合形成机器人的目标轨迹路径,由于轨迹规划设备基于交通信息设置关键点,即关键点的位置设置于建模中的合理位置,提高目标轨迹路径的灵活性和实用性,从而实现机器人在建模上点对点之间的路径规划。
为了机器人在建模上点对点之间的路径规划,本申请提出了另一种轨迹规划方法,请参阅图5,图5是本申请实施例提供的一种轨迹规划方法的流程示意图。
如图5所示,本实施例的轨迹规划方法具体包括以下步骤:
S201:从建模获取轨迹信息和交通信息,其中,轨迹信息包括机器人的当前位置和目的地位置。
S202:基于交通道路分布情况获取每个路口的进出口处、每个弯道的进出口处以及每条道路的边缘和中间位置在建模中的关键坐标。
其中,对于一般的交通道路来说,在道路上正常运行的车辆只能在路口、弯道、道路交汇处改变运动方向,因此,轨迹规划设备需要在路口、弯道、道路交汇处设置关键点。除此之外,对于一些较长的道路,在道路的中间设置关键点有利于适应车辆加速、减速的情况。
例如,轨迹规划设备基于沙盘建模的交通道路分布情况获取每个路口的进出口处、每个弯道的进出口处以及每条道路的边缘和中间位置在沙盘建模中的关键坐标。
S203:将关键坐标在建模对应的位置设置为关键点。
其中,轨迹规划设备基于关键坐标在沙盘建模上设置多个关键点,生成如图2所示的沙盘建模。
在一些实施例中,轨迹规划设备还可以基于交通规则对生成的关键点进行排序。例如,在一条道路上,轨迹规划设备根据该道路的可行驶方向对道路上的关键点进行排序。因此,关键点的排列顺序在一定程度也直接反映了沙盘建模的交通规则。
S204:将机器人的当前位置和目的地位置之间的关键点两两之间组成轨迹段。
S205:将符合交通规则的轨迹段设置为连通段。
其中,轨迹规划设备将关键点两两之间组成,且邻接矩阵数值为1的线路设置为轨 迹段,轨迹段为有向轨迹段。在连接多条轨迹段之间,轨迹规划设备还需要结合运行时间、交通道路分布情况在一些实施例中判断轨迹段是否符合交通规则,其中,交通规则包括单双号限行、按照时间限行等规则。当轨迹点符合交通规则时,轨迹规划设备将符合交通规则的轨迹段设置为连通段。
为了机器人在建模上点对点之间的路径规划,本申请实施例提出了又一种轨迹规划方法,请参阅图6A,图6A是本申请实施例提供的一种轨迹规划方法的流程示意图。
如图6A所示,本实施例的轨迹规划方法具体包括以下步骤:
S301:从建模获取轨迹信息和交通信息,其中,轨迹信息包括机器人的当前位置和目的地位置。
S302:基于交通信息在建模上设置多个关键点。
在一些实施例中,基于交通信息在建模上设置多个关键点的步骤,如图6B所示,还包括:
S3021:基于交通信息获取建模中允许停泊的位置坐标;
在实施过程中,交通信息包括交通规则和交通道路分布情况,其中,交通规则包括单双号限行、按照时间限行等规则;这里的交通规则可以与现实生活中的交通规则一致。交通道路分布情况包括可以通行的道路的分布。
轨迹规划设备基于交通规则和建模上的交通道路分布情况可以确定允许机器人停泊的位置坐标。例如,可以确定建模中不影响其他机器人通行的位置为允许停泊的位置,或者遇到红灯时斑马线前允许机器人停泊。
S3022:从允许停泊的位置坐标中获取机器人在建模中需要停泊的位置坐标;
在一些实施例中,轨迹规划设备可以从允许停泊的位置坐标中,根据机器人的实际运行需求确定机器人在建模中需要停泊的位置坐标。例如,确定遇到红灯时斑马线前允许机器人停泊的位置坐标。
S3023:将位置坐标在所述建模对应的位置设置为所述关键点。
在一些实施例中,轨迹规划设备可以将需要停泊的位置坐标在建模对应的位置设置为关键点。
S303:基于交通信息在两两关键点之间形成连通段。
S304:采用预设算法搜索当前位置和目的地位置之间的所有连通段,按照搜索结果将连通段连接为机器人的目标轨迹路径。
通过上述步骤得到的目标轨迹路径在逻辑上合理可行,但是在实际运行中,还需要在一些实施例中考虑机器人的动力学模型。如图4生成的目标轨迹路径中,轨迹段之间有一定的夹角;当夹角较小时,由于机器人的动力学模型约束,在实际运行中,机器人很难完成按照目标轨迹路径运行,可能会偏离目标轨迹路径,影响后续的运行情况。因此,轨迹规划设备需要针对机器人的动力学模型对目标轨迹路径进行优化。机器人的动力学模型约束主要包含纵轴加速度和转弯半径,转弯半径可以等价为横轴加速度,轨迹 规划设备需要保证目标规划路径的任意一段加速度都要符合最大加速度约束。请继续参阅以下步骤:
S305:获取机器人的动力学模型,其中,动力学模型包括机器人在每段连通段的加速度和最大速度。
S306:获取机器人在目标轨迹路径中每段连通段的运动时间以及运动向量。
其中,轨迹规划设备基于连通段的运动向量、机器人的加速度和最大速度获取该连通段中加速度段所占的比例,例如计算公式(1)如下:
其中,ω为加速度段占整个连通段的比例,P为连通段的运动向量,a为加速度,v为最大速度。
其中,连通段的运动向量包括连通段的方向以及连通段的长度,连通段的方向表示机器人在该连通段的可运动方向。
轨迹规划设备在一些实施例中基于连通段的运动向量以及加速度段占连通段的比例获取连通段的速度系数,例如计算公式(2)如下:
其中,λ为连通段的速度系数。
在一些实施例中,轨迹规划设备获取每一连通段的其预期起始时间和预期终止时间,并根据连通段的预期起始时间和速度系数获取连通段的第一标准时间,例如计算公式(3)如下:
其中,t
0为轨迹段的预期起始时间,t
1为轨迹段的第一标准时间。
轨迹规划设备基于连通段的第一标准时间、运动向量、速度系数和加速度段占连通段的比例确定第二标准时间,例如计算公式(4)如下:
其中,t
2为连通段的第二标准时间。
轨迹规划设备可基于所述运动时间的大小,通过所述机器人在每段所述连通段的加速度和最大速度更新每段所述连通段的运动向量。
在一些实施例中,轨迹规划设备可执行如下步骤实现更新连通段的运动向量。
S307:基于运动时间、第一标准时间和第二标准时间的大小,通过机器人在每段连通段的加速度和最大速度更新每段连通段的运动向量。
其中,轨迹规划设备根据机器人的运动时间、第一标准时间和第二标准时间的大小,对每段连通段的运动向量进行优化,例如优化公式(5)如下:
其中,Ti(P,t)为连通段的运动路径。
当运动时间在起始时间和第一标准时间之间时,机器人处于加速状态,轨迹规划设备基于起始时间更新运动向量。
当运动时间在第一标准时间和第二标准时间之间时,机器人处于匀速状态,轨迹规划设备基于第一标准时间更新运动向量。
当运动时间在第二标准时间和终止时间之间时,机器人处于减速状态,轨迹规划设备基于终止时间更新运动向量。
最后,轨迹规划设备将更新后的轨迹段进行合并,得到如图7所示的完整轨迹路径。至此,轨迹规划设备完成了起始点和目的地点之间的轨迹规划,且生成的轨迹考虑到当前机器人的位置、速度、姿态,生成一条满足曲率连续性的光滑路径,可以根据此路径直接解算机器人在任意时刻的速度及控制配置,让机器人按照指定的控制策略运动即可完美地按照规定轨迹运行。
基于前述的实施例,本申请实施例提供一种轨迹规划装置,该装置包括所包括的各模块、以及各模块所包括的各子模块,可以通过计算机设备中的处理器来实现;当然也可通过具体的逻辑电路实现;在实施的过程中,处理器可以为中央处理器(CPU)、微处理器(MPU)、数字信号处理器(DSP)或现场可编程门阵列(FPGA)等。
本申请实施例提供一种轨迹规划装置,图8为本申请实施例提供的一种轨迹规划装置结构组成示意图,如图8所示,所述装置800包括:
第一获取模块810,配置为从建模获取轨迹信息和交通信息,其中,所述轨迹信息包括机器人的当前位置和目的地位置;
设置模块820,配置为基于所述交通信息在所述建模上设置多个关键点;
形成模块830,配置为基于所述交通信息在两两关键点之间形成连通段;
连接模块840,配置为采用预设算法搜索所述当前位置和所述目的地位置之间的所有连通段,按照搜索结果将所述连通段连接为所述机器人的目标轨迹路径。
在一些实施例中,所述交通信息包括交通道路分布情况;所述设置模块包括:第一获取子模块,配置为基于所述交通道路分布情况获取每个路口的进出口处、每个弯道的进出口处以及每条道路的边缘和中间位置在所述建模中的关键坐标;第一设置子模块,配置为将所述关键坐标在所述建模对应的位置设置为所述关键点。
在一些实施例中,所述设置模块还包括:第二获取子模块,配置为基于所述交通信息获取所述建模中允许停泊的位置坐标;第三获取子模块,配置为从所述允许停泊的位置坐标中获取所述机器人在所述建模中需要停泊的位置坐标;第二设置子模块,配置为将所述位置坐标在所述建模对应的位置设置为所述关键点。
在一些实施例中,所述交通信息包括交通规则;所述形成模块包括:组成子模块,配置为将所述机器人的当前位置和目的地位置之间的关键点两两之间组成轨迹段;第三设置子模块,配置为将符合所述交通规则的轨迹段设置为所述连通段。
在一些实施例中,所述装置还包括:第二获取模块,配置为获取所述机器人的动力学模型,其中,所述动力学模型包括所述机器人在每段所述连通段的加速度和最大速度;第三获取模块,配置为获取所述机器人在所述目标轨迹路径中每段连通段的运动时间以及运动向量;更新模块,配置为基于所述运动时间的大小,通过所述机器人在每段所述连通段的加速度和最大速度更新每段所述连通段的运动向量。
在一些实施例中,所述装置还包括:第四获取模块,配置为基于所述连通段的运动向量以及加速度段占所述连通段的比例获取所述连通段的速度系数;第五获取模块,配置为获取所述连通段的起始时间和终止时间;第一确定模块,配置为基于所述连通段的起始时间和速度系数确定第一标准时间;第二确定模块,配置为基于所述连通段的第一标准时间、运动向量、速度系数和加速度段占所述连通段的比例确定第二标准时间;所述更新模块,还配置为基于所述运动时间、第一标准时间和第二标准时间的大小,通过所述机器人在每段所述连通段的加速度和最大速度更新每段所述连通段的运动向量。
在一些实施例中,所述更新模块包括:第一更新子模块,配置为当所述运动时间在所述起始时间和所述第一标准时间之间时,基于所述起始时间以及所述机器人在每段所述连通段的加速度和最大速度将所述运动向量进行更新;第二更新子模块,配置为当所述运动时间在所述第一标准时间和所述第二标准时间之间时,基于所述第一标准时间以及所述机器人在每段所述连通段的加速度和最大速度将所述运动向量进行更新;第三更新子模块,配置为当所述运动时间在所述第二标准时间和所述终止时间之间时,基于所述第二标准时间以及所述机器人在每段所述连通段的加速度和最大速度将所述运动向量进行更新。
在一些实施例中,第四获取模块,包括:第一确定子模块,配置为基于所述连通段的运动向量、所述机器人的加速度和最大速度确定所述加速度段占所述连通段的比例;第二确定子模块,配置为基于所述机器人的最大速度、所述连通段的运动向量以及所述加速度段占所述连通段的比例确定所述连通段的速度系数。
为实现上述实施例的轨迹规划方法,本申请实施例还提出了一种轨迹规划设备,请参阅图9,图9是本申请实施例提供的一种轨迹规划设备的结构示意图。
本实施例的轨迹规划设备400包括处理器41、存储器42、输入输出设备43以及总线44。
该处理器41、存储器42、输入输出设备43分别与总线44相连,该存储器42中存储有程序数据,处理器41用于执行程序数据以实现上述实施例所述的轨迹规划方法。
在本实施例中,处理器41还可以称为中央处理单元(Central Processing Unit,CPU)。处理器41可能是一种集成电路芯片,具有信号的处理能力。处理器41还可以是通用处 理器、数字信号处理器(Digital Signal Processing,DSP)、专用集成电路(Application Specific Integrated Circuit,ASIC)、现场可编程门阵列(Field Programmable Gate Array,FPGA)或者其它可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。通用处理器可以是微处理器或者该处理器41也可以是任何常规的处理器等。
本申请实施例还提供一种计算机存储介质,如图10所示,计算机存储介质500用于存储程序数据51,程序数据51在被处理器执行时,用以实现如上述实施例所述的轨迹规划方法。
本申请上述实施例所述的轨迹规划方法,在实现时以软件功能单元的形式存在并作为独立的产品销售或使用时,可以存储在装置中,例如一个计算机可读取存储介质中。基于这样的理解,本申请实施例的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来,该计算机软件产品存储在一个存储介质中,包括若干指令用以使得一台计算机设备(可以是个人计算机,服务器,或者网络设备等)或处理器(processor)执行本发明各个实施方式所述方法的全部或部分步骤。而前述的存储介质包括:U盘、移动硬盘、只读存储器(Read-Only Memory,ROM)、随机存取存储器(Random Access Memory,RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述仅为本申请的实施方式,并非因此限制本申请的专利范围,凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换,或直接或间接运用在其他相关的技术领域,均同理包括在本申请的专利保护范围内。
本申请实施例提供的轨迹规划方法通过在当前位置和目的地位置之间设置多个关键点,并通过多个关键点组合形成机器人的目标轨迹路径,由于轨迹规划设备基于交通信息设置关键点,即关键点的位置设置于建模中的合理位置,提高目标轨迹路径的灵活性和实用性,从而实现机器人在建模上点对点之间的路径规划。
Claims (19)
- 一种轨迹规划方法,所述方法由轨迹规划设备执行,所述轨迹规划方法包括:从建模获取轨迹信息和交通信息,其中,所述轨迹信息包括机器人的当前位置和目的地位置;基于所述交通信息在所述建模上设置多个关键点;基于所述交通信息在两两关键点之间形成连通段;采用预设算法搜索所述当前位置和所述目的地位置之间的所有连通段,按照搜索结果将所述连通段连接为所述机器人的目标轨迹路径。
- 根据权利要求1所述的轨迹规划方法,其中,所述交通信息包括交通道路分布情况;所述基于所述交通信息在所述建模上设置多个关键点的步骤,包括:基于所述交通道路分布情况获取每个路口的进出口处、每个弯道的进出口处以及每条道路的边缘和中间位置在所述建模中的关键坐标;将所述关键坐标在所述建模对应的位置设置为所述关键点。
- 根据权利要求2所述的轨迹规划方法,其中,所述基于所述交通信息在所述建模上设置多个关键点的步骤,还包括:基于所述交通信息获取所述建模中允许停泊的位置坐标;从所述允许停泊的位置坐标中获取所述机器人在所述建模中需要停泊的位置坐标;将所述位置坐标在所述建模对应的位置设置为所述关键点。
- 根据权利要求2或3所述的轨迹规划方法,其中,所述交通信息包括交通规则;所述基于所述交通信息在两两关键点之间形成连通段的步骤包括:将所述机器人的当前位置和目的地位置之间的关键点两两之间组成轨迹段;将符合所述交通规则的轨迹段设置为所述连通段。
- 根据权利要求1至4任一项所述的轨迹规划方法,其中,所述按照搜索结果将所述连通段连接为所述机器人的目标轨迹路径的步骤之后,所述轨迹规划方法还包括:获取所述机器人的动力学模型,其中,所述动力学模型包括所述机器人在每段所述连通段的加速度和最大速度;获取所述机器人在所述目标轨迹路径中每段连通段的运动时间以及运动向量;基于所述运动时间的大小,通过所述机器人在每段所述连通段的加速度和最大速度更新每段所述连通段的运动向量。
- 根据权利要求5所述的轨迹规划方法,其中,所述获取所述机器人在所述目标轨迹路径中每段连通段的运动时间以及运动向量的步骤之后,所述轨迹规划方法还包括:基于所述连通段的运动向量以及加速度段占所述连通段的比例获取所述连通段的速度系数;获取所述连通段的起始时间和终止时间;基于所述连通段的起始时间和速度系数确定第一标准时间;基于所述连通段的第一标准时间、运动向量、速度系数和加速度段占所述连通段的比例确定第二标准时间;所述基于所述运动时间的大小,通过所述机器人在每段所述连通段的加速度和最大速度更新每段所述连通段的运动向量的步骤,包括:基于所述运动时间、第一标准时间和第二标准时间的大小,通过所述机器人在每段所述连通段的加速度和最大速度更新每段所述连通段的运动向量。
- 根据权利要求6所述的轨迹规划方法,其中,所述基于所述运动时间、第一标准时间和第二标准时间的大小,通过所述机器人在每段所述连通段的加速度和最大速度更新每段所述连通段的运动向量的步骤,包括:当所述运动时间在所述起始时间和所述第一标准时间之间时,基于所述起始时间以及所述机器人在每段所述连通段的加速度和最大速度将所述运动向量进行更新;当所述运动时间在所述第一标准时间和所述第二标准时间之间时,基于所述第一标准时间以及所述机器人在每段所述连通段的加速度和最大速度将所述运动向量进行更新;当所述运动时间在所述第二标准时间和所述终止时间之间时,基于所述第二标准时间以及所述机器人在每段所述连通段的加速度和最大速度将所述运动向量进行更新。
- 根据权利要求6或7所述的轨迹规划方法,其中,所述基于所述连通段的运动向量以及加速度段占所述连通段的比例获取所述连通段的速度系数的步骤,包括:基于所述连通段的运动向量、所述机器人的加速度和最大速度确定所述加速度段占所述连通段的比例;基于所述机器人的最大速度、所述连通段的运动向量以及所述加速度段占所述连通段的比例确定所述连通段的速度系数。
- 一种轨迹规划装置,所述装置包括:第一获取模块,配置为从建模获取轨迹信息和交通信息,其中,所述轨迹信息包括机器人的当前位置和目的地位置;设置模块,配置为基于所述交通信息在所述建模上设置多个关键点;形成模块,配置为基于所述交通信息在两两关键点之间形成连通段;连接模块,配置为采用预设算法搜索所述当前位置和所述目的地位置之间的所有连通段,按照搜索结果将所述连通段连接为所述机器人的目标轨迹路径。
- 根据权利要求9所述的装置,其中,所述交通信息包括交通道路分布情况;所述设置模块包括:第一获取子模块,配置为基于所述交通道路分布情况获取每个路口的进出口处、每个弯道的进出口处以及每条道路的边缘和中间位置在所述建模中的关键坐标;第一设置子模块,配置为将所述关键坐标在所述建模对应的位置设置为所述关键点。
- 根据权利要求10所述的装置,其中,所述设置模块还包括:第二获取子模块,配置为基于所述交通信息获取所述建模中允许停泊的位置坐标;第三获取子模块,配置为从所述允许停泊的位置坐标中获取所述机器人在所述建模中需要停泊的位置坐标;第二设置子模块,配置为将所述位置坐标在所述建模对应的位置设置为所述关键点。
- 根据权利要求10或11所述的装置,其中,所述交通信息包括交通规则;所述形成模块包括:组成子模块,配置为将所述机器人的当前位置和目的地位置之间的关键点两两之间组成轨迹段;第三设置子模块,配置为将符合所述交通规则的轨迹段设置为所述连通段。
- 根据权利要求9至12任一项所述的装置,其中,所述装置还包括:第二获取模块,配置为获取所述机器人的动力学模型,其中,所述动力学模型包括所述机器人在每段所述连通段的加速度和最大速度;第三获取模块,配置为获取所述机器人在所述目标轨迹路径中每段连通段的运动时间以及运动向量;更新模块,配置为基于所述运动时间的大小,通过所述机器人在每段所述连通段的加速度和最大速度更新每段所述连通段的运动向量。
- 根据权利要求13所述的装置,其中,所述装置还包括:第四获取模块,配置为基于所述连通段的运动向量以及加速度段占所述连通段的比例获取所述连通段的速度系数;第五获取模块,配置为获取所述连通段的起始时间和终止时间;第一确定模块,配置为基于所述连通段的起始时间和速度系数确定第一标准时间;第二确定模块,配置为基于所述连通段的第一标准时间、运动向量、速度系数和加速度段占所述连通段的比例确定第二标准时间;所述更新模块,还配置为基于所述运动时间、第一标准时间和第二标准时间的大小,通过所述机器人在每段所述连通段的加速度和最大速度更新每段所述连通段的运动向量。
- 根据权利要求14所述的装置,其中,所述更新模块包括:第一更新子模块,配置为当所述运动时间在所述起始时间和所述第一标准时间之间时,基于所述起始时间以及所述机器人在每段所述连通段的加速度和最大速度将所述运 动向量进行更新;第二更新子模块,配置为当所述运动时间在所述第一标准时间和所述第二标准时间之间时,基于所述第一标准时间以及所述机器人在每段所述连通段的加速度和最大速度将所述运动向量进行更新;第三更新子模块,配置为当所述运动时间在所述第二标准时间和所述终止时间之间时,基于所述第二标准时间以及所述机器人在每段所述连通段的加速度和最大速度将所述运动向量进行更新。
- 根据权利要求14或15所述的装置,其中,第四获取模块,包括:第一确定子模块,配置为基于所述连通段的运动向量、所述机器人的加速度和最大速度确定所述加速度段占所述连通段的比例;第二确定子模块,配置为基于所述机器人的最大速度、所述连通段的运动向量以及所述加速度段占所述连通段的比例确定所述连通段的速度系数。
- 一种轨迹规划设备,所述轨迹规划设备包括存储器和处理器,其中,所述存储器与所述处理器耦接;其中,所述存储器用于存储程序数据,所述处理器用于执行所述程序数据以实现如权利要求1至8任一项所述的轨迹规划方法。
- 一种计算机存储介质,所述计算机存储介质用于存储程序数据,所述程序数据在被处理器执行时,用以实现如权利要求1至8中任一项所述的轨迹规划方法。
- 一种计算机程序产品,所述计算机程序产品包括一条或多条指令,所述一条或多条指令适于由处理器加载并执行如权利要求1至8任一项所述的轨迹规划方法。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020217035939A KR20220083975A (ko) | 2020-12-10 | 2021-04-20 | 궤적 계획 방법, 장치, 기기, 저장 매체 및 프로그램 제품 |
JP2021562392A JP2023508794A (ja) | 2020-12-10 | 2021-04-20 | 軌跡計画方法及び装置、機器、記憶媒体並びにプログラム製品 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011455167.9 | 2020-12-10 | ||
CN202011455167.9A CN112454367B (zh) | 2020-12-10 | 2020-12-10 | 一种轨迹规划方法、装置以及计算机存储介质 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022121207A1 true WO2022121207A1 (zh) | 2022-06-16 |
Family
ID=74801500
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2021/088385 WO2022121207A1 (zh) | 2020-12-10 | 2021-04-20 | 轨迹规划方法、装置、设备、存储介质和程序产品 |
Country Status (4)
Country | Link |
---|---|
JP (1) | JP2023508794A (zh) |
KR (1) | KR20220083975A (zh) |
CN (1) | CN112454367B (zh) |
WO (1) | WO2022121207A1 (zh) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115309171A (zh) * | 2022-10-12 | 2022-11-08 | 维飒科技(西安)有限公司 | 轨道机器人的行为轨迹控制方法及装置 |
CN116372927A (zh) * | 2023-04-06 | 2023-07-04 | 深圳市康士达科技有限公司 | 一种机器人示教的轨迹生成方法、装置、设备和介质 |
CN117476172A (zh) * | 2023-12-28 | 2024-01-30 | 深圳市亿莱顿科技有限公司 | 家庭健康管理方法、系统以及计算机设备 |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112454367B (zh) * | 2020-12-10 | 2022-04-26 | 北京市商汤科技开发有限公司 | 一种轨迹规划方法、装置以及计算机存储介质 |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150046089A1 (en) * | 2013-03-15 | 2015-02-12 | Applied Minds, Llc | Method and apparatus for two-stage planning |
US20150269622A1 (en) * | 2014-03-20 | 2015-09-24 | Yahoo Japan Corporation | Movement controller, movement control method, and movement control system |
CN107702723A (zh) * | 2017-11-27 | 2018-02-16 | 安徽工程大学 | 一种机器人路径规划方法、存储介质及设备 |
CN108475059A (zh) * | 2015-12-15 | 2018-08-31 | 高通股份有限公司 | 自主视觉导航 |
CN109916422A (zh) * | 2019-03-29 | 2019-06-21 | 北京经纬恒润科技有限公司 | 一种全局路径规划方法及装置 |
CN112454367A (zh) * | 2020-12-10 | 2021-03-09 | 北京市商汤科技开发有限公司 | 一种轨迹规划方法、装置以及计算机存储介质 |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP5902890B2 (ja) * | 2011-05-06 | 2016-04-13 | 株式会社ゼンリン | 携帯型ナビゲーション装置 |
ES2646267T3 (es) * | 2013-07-15 | 2017-12-13 | Bae Systems Plc | Planificación de rutas |
CN104819724B (zh) * | 2015-03-02 | 2018-04-03 | 北京理工大学 | 一种基于gis的无人地面车辆自主行驶辅助系统 |
CN108597315A (zh) * | 2018-04-11 | 2018-09-28 | 广州维脉电子科技有限公司 | 一种沙盘智能模型车辆控制装置和方法 |
CN110501007B (zh) * | 2019-09-06 | 2021-07-16 | 腾讯科技(深圳)有限公司 | 一种路径规划方法、装置及终端 |
CN110646007B (zh) * | 2019-09-20 | 2021-10-01 | 中国科学技术大学 | 一种基于形式化表示的车辆驾驶方法 |
-
2020
- 2020-12-10 CN CN202011455167.9A patent/CN112454367B/zh active Active
-
2021
- 2021-04-20 JP JP2021562392A patent/JP2023508794A/ja not_active Withdrawn
- 2021-04-20 WO PCT/CN2021/088385 patent/WO2022121207A1/zh active Application Filing
- 2021-04-20 KR KR1020217035939A patent/KR20220083975A/ko unknown
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150046089A1 (en) * | 2013-03-15 | 2015-02-12 | Applied Minds, Llc | Method and apparatus for two-stage planning |
US20150269622A1 (en) * | 2014-03-20 | 2015-09-24 | Yahoo Japan Corporation | Movement controller, movement control method, and movement control system |
CN108475059A (zh) * | 2015-12-15 | 2018-08-31 | 高通股份有限公司 | 自主视觉导航 |
CN107702723A (zh) * | 2017-11-27 | 2018-02-16 | 安徽工程大学 | 一种机器人路径规划方法、存储介质及设备 |
CN109916422A (zh) * | 2019-03-29 | 2019-06-21 | 北京经纬恒润科技有限公司 | 一种全局路径规划方法及装置 |
CN112454367A (zh) * | 2020-12-10 | 2021-03-09 | 北京市商汤科技开发有限公司 | 一种轨迹规划方法、装置以及计算机存储介质 |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115309171A (zh) * | 2022-10-12 | 2022-11-08 | 维飒科技(西安)有限公司 | 轨道机器人的行为轨迹控制方法及装置 |
CN115309171B (zh) * | 2022-10-12 | 2022-12-20 | 维飒科技(西安)有限公司 | 轨道机器人的行为轨迹控制方法及装置 |
CN116372927A (zh) * | 2023-04-06 | 2023-07-04 | 深圳市康士达科技有限公司 | 一种机器人示教的轨迹生成方法、装置、设备和介质 |
CN116372927B (zh) * | 2023-04-06 | 2024-03-22 | 深圳市康士达科技有限公司 | 一种机器人示教的轨迹生成方法、装置、设备和介质 |
CN117476172A (zh) * | 2023-12-28 | 2024-01-30 | 深圳市亿莱顿科技有限公司 | 家庭健康管理方法、系统以及计算机设备 |
CN117476172B (zh) * | 2023-12-28 | 2024-05-28 | 深圳市亿莱顿科技有限公司 | 家庭健康管理方法、系统以及计算机设备 |
Also Published As
Publication number | Publication date |
---|---|
CN112454367B (zh) | 2022-04-26 |
CN112454367A (zh) | 2021-03-09 |
JP2023508794A (ja) | 2023-03-06 |
KR20220083975A (ko) | 2022-06-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2022121207A1 (zh) | 轨迹规划方法、装置、设备、存储介质和程序产品 | |
CN113032285B (zh) | 一种高精地图测试方法、装置、电子设备及存储介质 | |
WO2020224434A1 (zh) | 一种驾驶仿真方法、装置、电子设备及计算机存储介质 | |
CN109213153B (zh) | 一种车辆自动驾驶方法及电子设备 | |
WO2020108207A1 (zh) | 一种高精度地图的构建方法及装置 | |
CN108645411B (zh) | 基于粒子群算法的机器人路径规划方法、装置及终端设备 | |
WO2020216315A1 (zh) | 一种参考行驶线快速生成方法、系统、终端和存储介质 | |
WO2022056770A1 (zh) | 一种路径规划方法和路径规划装置 | |
CN109697875B (zh) | 规划行驶轨迹的方法及装置 | |
CN109947090A (zh) | 用于自动驾驶车辆规划的非阻塞边界 | |
CN110389581A (zh) | 用于为自动驾驶车辆生成障碍物的预测轨迹的方法 | |
JP2020001678A (ja) | 重み付け幾何学的コストを有する区分的螺旋曲線を使用した基準線平滑化方法 | |
CN111422204B (zh) | 自动驾驶车辆通行判定方法及相关设备 | |
CN109955853A (zh) | 用于操作自动驾驶车辆的方法、系统和存储介质 | |
CN108602509A (zh) | 基于运动规划来操作自动驾驶车辆的方法和系统 | |
WO2021097845A1 (zh) | 一种仿真场景的图像生成方法、电子设备和存储介质 | |
CN111142525A (zh) | 高精度地图车道拓扑构建方法及系统、服务器及介质 | |
CN113682318B (zh) | 车辆行驶控制方法及装置 | |
CN113569378B (zh) | 仿真场景的生成方法、装置、电子设备以及存储介质 | |
CN113139696B (zh) | 一种轨迹预测模型构建方法及轨迹预测方法、装置 | |
Gómez-Huélamo et al. | Train here, drive there: ROS based end-to-end autonomous-driving pipeline validation in CARLA simulator using the NHTSA typology | |
CN116424336A (zh) | 一种轨迹预测方法、装置及车联网设备 | |
Khanum et al. | Involvement of deep learning for vision sensor-based autonomous driving control: a review | |
CN110553662B (zh) | 一种基于道路口编码体系的导航方法及系统 | |
CN117734715A (zh) | 基于强化学习的自动驾驶控制方法、系统、设备及存储介质 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
ENP | Entry into the national phase |
Ref document number: 2021562392 Country of ref document: JP Kind code of ref document: A |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21901922 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 21901922 Country of ref document: EP Kind code of ref document: A1 |