WO2023010877A1 - 无人驾驶设备的路径规划 - Google Patents
无人驾驶设备的路径规划 Download PDFInfo
- Publication number
- WO2023010877A1 WO2023010877A1 PCT/CN2022/085562 CN2022085562W WO2023010877A1 WO 2023010877 A1 WO2023010877 A1 WO 2023010877A1 CN 2022085562 W CN2022085562 W CN 2022085562W WO 2023010877 A1 WO2023010877 A1 WO 2023010877A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- calibration
- path
- planned
- planning
- reference position
- Prior art date
Links
- 238000000034 method Methods 0.000 claims abstract description 87
- 238000004590 computer program Methods 0.000 claims description 26
- 238000003860 storage Methods 0.000 claims description 19
- 230000008569 process Effects 0.000 abstract description 12
- 238000010586 diagram Methods 0.000 description 31
- 238000005516 engineering process Methods 0.000 description 14
- 230000006870 function Effects 0.000 description 11
- 230000033001 locomotion Effects 0.000 description 11
- 230000006872 improvement Effects 0.000 description 9
- 230000008859 change Effects 0.000 description 7
- 238000012545 processing Methods 0.000 description 6
- 239000000047 product Substances 0.000 description 6
- 230000007613 environmental effect Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- PCTMTFRHKVHKIS-BMFZQQSSSA-N (1s,3r,4e,6e,8e,10e,12e,14e,16e,18s,19r,20r,21s,25r,27r,30r,31r,33s,35r,37s,38r)-3-[(2r,3s,4s,5s,6r)-4-amino-3,5-dihydroxy-6-methyloxan-2-yl]oxy-19,25,27,30,31,33,35,37-octahydroxy-18,20,21-trimethyl-23-oxo-22,39-dioxabicyclo[33.3.1]nonatriaconta-4,6,8,10 Chemical compound C1C=C2C[C@@H](OS(O)(=O)=O)CC[C@]2(C)[C@@H]2[C@@H]1[C@@H]1CC[C@H]([C@H](C)CCCC(C)C)[C@@]1(C)CC2.O[C@H]1[C@@H](N)[C@H](O)[C@@H](C)O[C@H]1O[C@H]1/C=C/C=C/C=C/C=C/C=C/C=C/C=C/[C@H](C)[C@@H](O)[C@@H](C)[C@H](C)OC(=O)C[C@H](O)C[C@H](O)CC[C@@H](O)[C@H](O)C[C@H](O)C[C@](O)(C[C@H](O)[C@H]2C(O)=O)O[C@H]2C1 PCTMTFRHKVHKIS-BMFZQQSSSA-N 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000006227 byproduct Substances 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 229920001296 polysiloxane Polymers 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 239000010979 ruby Substances 0.000 description 1
- 229910001750 ruby Inorganic materials 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
Definitions
- the present disclosure relates to the technical field of unmanned driving, and in particular to path planning of unmanned equipment.
- the present disclosure provides a path planning method for unmanned equipment, including:
- the attribute information of each reference position in the reference route, and the attribute information of each planned position in the planned route of the unmanned device at least including: time, the speed direction and speed of the unmanned device;
- the direction of the planned path it is sequentially judged whether the speed direction of each planned position is opposite to the speed direction of the same reference position at the same time, if so, the planned position with the opposite speed direction is used as the calibration planned position;
- the planned route is re-determined, and the unmanned device is controlled to travel along the planned route.
- the present disclosure provides a path planning method for unmanned equipment, including:
- the attribute information of each reference position in the reference route, and the attribute information of each planned position in the planned route of the unmanned device at least including: time, the speed direction and speed of the unmanned device;
- the direction of the planned path it is sequentially judged whether the speed direction of each planned position is opposite to the speed direction of the same reference position at the same time, if so, the planned position with the opposite speed direction is used as the calibration planned position;
- the planned route is re-determined, and the unmanned device is controlled to travel along the planned route.
- the present disclosure provides a path planning device for unmanned equipment, including:
- An acquisition module configured to acquire the attribute information of each reference position in the reference route, and the attribute information of each planned position in the planned route of the unmanned device, the attribute information at least includes: time, the speed direction of the unmanned device and speed;
- the determination module is used to sequentially judge whether the speed direction of each planned position is opposite to the speed direction of the reference position at the same time according to the direction of the planned path, and if so, use the planned position with the opposite speed direction as the calibration planned position;
- a calibration module configured to determine a calibration reference position in the reference path according to the point closest to the calibration planning position in the reference path, and plan according to a reference path after the calibration reference position in the reference path A calibration path starting from the calibration planning location;
- a planning module configured to re-determine a planned route according to the planned route before the calibration planned position in the planned route and the calibration route, and control the unmanned device to drive along the planned route.
- the present disclosure provides a path planning device for unmanned equipment, including:
- An acquisition module configured to acquire the attribute information of each reference position in the reference route, and the attribute information of each planned position in the planned route of the unmanned device, the attribute information at least includes: time, the speed direction of the unmanned device and speed;
- the determination module is used to sequentially judge whether the speed direction of each planned position is opposite to the speed direction of the reference position at the same time according to the direction of the planned path, and if so, use the planned position with the opposite speed direction as the calibration planned position;
- a calibration module configured to determine a calibration reference position in the reference path, and plan a calibration path starting from the calibration planning position according to a reference path after the calibration reference position in the reference path;
- a planning module configured to re-determine a planned route according to the planned route before the calibration planned position in the planned route and the calibration route, and control the unmanned device to drive along the planned route.
- the present disclosure provides a computer-readable storage medium, the storage medium stores a computer program, and when the computer program is executed by a processor, the above path planning method for an unmanned driving device is realized.
- the present disclosure provides an electronic device, including a memory, a processor, and a computer program stored on the memory and operable on the processor.
- the processor implements the path planning method for the above-mentioned unmanned device when executing the program.
- the present disclosure provides a computer program product, the computer program product includes a computer program or an instruction, and the computer program or instruction is executed by a processor, so that the computer implements the above path planning method for an unmanned driving device.
- FIG. 1 is a schematic diagram of path planning and determining a planned path by related technologies
- FIG. 2 is a schematic flowchart of a path planning method for an unmanned device provided by the present disclosure
- FIG. 3 is a schematic diagram of determining a calibration reference position provided by the present disclosure
- Fig. 4a is a schematic diagram of determining the first calibration path provided by the present disclosure
- Fig. 4b is a schematic diagram of determining the calibration path provided by the present disclosure.
- FIG. 5 is a schematic diagram of determining a planned path provided by the present disclosure
- Fig. 6a is a schematic diagram of determining the calibration planning position provided by the present disclosure
- Fig. 6b is a schematic diagram of determining the planned path of the unmanned device provided by the present disclosure
- FIG. 7 is a schematic diagram of determining a reference path for unmanned equipment provided by the present disclosure.
- FIG. 8 is a schematic diagram of determining a reference route and a planned route of an unmanned device provided by the present disclosure
- FIG. 9 is a schematic flowchart of a path planning method for an unmanned device provided by the present disclosure.
- FIG. 10 is a schematic diagram of a path planning device for unmanned equipment provided by the present disclosure.
- FIG. 11 is a schematic diagram of a path planning device for unmanned equipment provided by the present disclosure.
- FIG. 12 is a schematic diagram of an unmanned driving device corresponding to FIG. 2 and FIG. 9 provided by the present disclosure.
- a commonly used path planning method for unmanned equipment is implemented based on the reference path of the unmanned equipment.
- the unmanned device can obtain the reference path fitted by the reference position corresponding to each moment, and "perceive" the surrounding environment of the unmanned device, and determine the position of obstacles around the unmanned device, Then, according to the reference path and the determined position of the obstacle, the planned path of the unmanned device is determined, and the unmanned device is controlled to drive along the planned path.
- each reference position may represent a position and a velocity corresponding to each moment in the reference route.
- the unmanned driving device may cause the unmanned driving device to stop suddenly or fail to drive normally.
- the planned position corresponding to the reference position may exceed the reference position at the next moment (that is, the planned route takes a shortcut), resulting in the planned position at the next moment determined based on the reference position at the next moment is behind the unmanned device, then the unmanned device needs to drive in the opposite direction to reach the next moment
- the planned location of the unmanned driving equipment has great potential safety hazards.
- the present disclosure provides a method for adjusting the planned route based on the curvature and speed of each point in the planned route, and re-determining the planned route, so as to ensure the driving safety of the driverless device.
- the reference position in the reference path has a large curvature
- path planning when path planning is performed based on the reference position, if the unmanned driving device senses an obstacle, the planned path may have a "short cut" situation in the planned path ,As shown in Figure 1.
- FIG. 1 is a schematic diagram of determining a planned path by performing path planning in related technologies.
- the curve where ABCD is located is the reference path of the unmanned equipment
- the dotted line is the obstacle determined by the unmanned equipment through target recognition
- the curve where AEFG is located is the planned path determined by related technologies
- the direction of the arrow is the path direction , and in order to achieve precise control, usually the determined reference path includes the corresponding reference position at each time, and the speed of each reference position, and the planning path determined based on the reference path also includes the corresponding planning position at each time, And the speed corresponding to each planning position.
- point A corresponds to the reference position and planned position at the same time
- reference position point B and planned position point E are at the same time
- reference position point C and planned position point F are at the same time
- reference position point D and planned position point
- the position point G is at the same moment
- the reference position point B is the reference position at the next moment of the reference position point A
- the reference position point C is the reference position of the next moment at the reference position point B
- the reference position point D is the reference position The reference position of point C at the next moment
- the planned position point E is the reference position of the planned position point A at the next moment
- the planned position point F is the reference position of the planned position point E at the next moment
- the planned position point G is the next moment of the planned position point F. Reference location.
- the unmanned driving device can first determine the curvature of the reference position at each time between the reference position point A and the reference position B, and the position of the obstacle, as shown in the figure from the planned position point A to the planned position point E. curve. Obviously, if the planned location point E exceeds the reference location point C, then when the planned path is determined based on the curvature of each reference location between the reference location point B and the reference location point C, since the planned location point E reaches its reference point at the same time The location point B is far away, resulting in the planned location point F being planned at the same time as the reference location point C.
- the driverless device needs to drive in the opposite direction to reach the planned location point F, that is, That is, according to the curvature of the reference position at each moment between the reference position point B and the reference position C, and the position of the obstacle, determine the curve shown in the figure from the planned position point E to the planned position point F. Then, after determining the planned position point F, the unmanned driving device can first determine the planned position point F as shown in the figure according to the curvature of the reference position at each time between the reference position point C and the reference position D, and the position of the obstacle. to the curve shown at the planned location point G.
- the unmanned driving device can perform path planning with G as the starting point according to the curvature corresponding to each reference location in the reference path after the reference location D, the location of obstacles, etc., after determining the G point , and splicing the determined curves from point A to point E, the curve from point E to point F, the curve from point F to point G, and the curve after point G, as the planned path of the unmanned driving device .
- the present disclosure provides a new path planning method for the unmanned driving device, so that the path planning for the unmanned driving device can be re-planned based on the path planned according to the reference path and the obstacle position.
- FIG. 2 is a schematic flow diagram of a path planning method for an unmanned device provided by the present disclosure, including the following steps:
- S100 Obtain the attribute information of each reference position in the reference route, and the attribute information of each planned position in the planned route of the unmanned device, the attribute information at least includes: time, the speed direction and speed of the unmanned device .
- the unmanned equipment mentioned here can refer to unmanned vehicles, robots, automatic distribution equipment and other equipment that can realize automatic driving.
- the path planning method for unmanned equipment provided in the present disclosure can be applied to the field of delivery using unmanned equipment, such as the business scenario of using unmanned equipment for express delivery, logistics, and takeaway delivery. In order to ensure that unmanned equipment can run smoothly in these business scenarios, it is necessary to ensure the accuracy and safety of unmanned equipment path planning.
- the entity performing path planning for the unmanned driving device may be the unmanned driving device itself, or the server of the service provider, that is, the server of the service provider may pass
- the data uploaded by the unmanned equipment is used for path planning of the unmanned equipment.
- the following will only use the unmanned equipment as the execution subject to describe the method for path planning of the unmanned equipment provided by the present disclosure.
- a high-definition map may be pre-stored in the unmanned device, so the unmanned device may determine the lane centerline of the lane where the unmanned device is located according to the pre-stored high-definition map, and use the lane line as If the reference path of the unmanned device is used, the unmanned device can determine the attribute information of each reference position based on its own current velocity and direction, as well as the curvature of the reference path. Wherein, for each reference position, the attribute information of the reference position includes: the time corresponding to the reference position, the curvature of the reference path at the reference position, the speed and direction of the unmanned driving device at the reference position.
- the lane centerline is a curve formed by the center positions of the lane.
- the unmanned device can obtain image data or point cloud data collected by the acquisition device as environmental data, and recognize the environmental data to determine the position of obstacles around the unmanned device.
- the unmanned driving device can determine the attribute information of the planned position corresponding to each time according to the determined position of the obstacle and the determined attribute information of each reference position in the reference path, and each planned position can determine The planned path of the human-driven device.
- the attribute information of the planned location includes: the time corresponding to the planned location, the speed and direction of the speed of the unmanned device at the planned location.
- S102 According to the direction of the planned path, sequentially determine whether the speed direction of each planned position is opposite to that of the reference position at the same time, and if so, use the planned position with the opposite speed direction as the calibration planned position.
- the unmanned driving device can determine the planned location in the planned path whose path direction is opposite to the reference path from the planned path, and adjust the sub-path to determine the planned path whose path direction is the same as the reference path direction.
- the moving direction of the object generally depends on the speed direction of the object, that is to say, the path direction of the planned path and the path direction of the reference path depend on the speed direction of the unmanned device in the path. Therefore, the calibration planning position can be determined based on the velocity direction of the unmanned driving device in the initial planning path and the velocity direction in the reference path at a corresponding moment.
- the unmanned driving device can sequentially determine the speed of each planned position and its reference position at the same time in the Cartesian coordinate system according to the direction of the planned route, and determine the speed of each planned position and its reference position at the same time The product of the speed of the position, and based on the product, etc., it is judged whether the speed of the planned position is the same as the speed of the reference position. And when it is determined that the speed direction of the planning position is opposite to the speed direction of the same reference position at the same moment, the planning position is determined as the calibration planning position.
- the unmanned driving device can determine the speed of the next planning position and the speed of the next reference position according to the ranking, and then judge the next planning Whether the velocity direction of the position is opposite to that of the reference position at the same moment.
- the unmanned driving device when the unmanned driving device performs path planning, it often constructs a Fresnel (Frenet) coordinate system according to the reference path and the distance from the reference path, and then performs path planning in the Fresnel coordinate system.
- the expressions of the reference path and the planning path in the Cartesian coordinate system are often not easy to determine. Therefore, the curvature of the planning location and the distance between the planning location and the reference location at the same time as the planning location can be used to determine Whether the speed of the planning position is the same as that of the reference position at the same time.
- the reference path is L(x,y)(s), and the reference path is continuous, then the reference path satisfies Among them, s represents the length of the reference path, and x and y are both functions of s.
- the Cartesian coordinates of the corresponding reference position in the reference path at this moment are (x 0 , y 0 )
- V 0 is the speed corresponding to the reference position
- x' 0 and y' 0 are the x-axis of the speed of the reference position in the Cartesian coordinate system
- the product of the speed corresponding to the position can determine whether the speed corresponding to the planned position is in the same direction as the speed corresponding to the reference position.
- the unmanned device can first determine the curvature k of the reference position at the planning position at the same time as the reference curvature, and the distance l between the planning position and the reference position at the same time as the reference distance .
- each planned position determines whether the product of the reference curvature of the planned position and the reference distance of the planned position is greater than 1, that is, determine whether kl>1 corresponding to the planned position is established .
- the unmanned driving device can determine that the speed direction of the planned position is opposite to the speed direction of the reference position at the same time. If not, the unmanned driving device can determine that the speed direction of the planned position is the same as the speed direction of the reference position at the same time, and then the unmanned device can continue to judge that the speed direction of the subsequent planning position of the planned path is the same as the reference position at the same time. Whether the speed direction of the position is the same, until all planning positions are judged.
- the attribute information of the planned position also includes the distance between the planned position and its corresponding reference position, and the curvature of the reference position.
- the calibration planning position is not determined above, that is, there is no planning position in the planning path that is opposite to the speed direction of the reference position at the same time, then the planning path can be considered accurate, and the unmanned device can control itself along the Drive along the planned route.
- the unmanned device can sequentially determine the reference curvature and reference distance of each planned position along the direction of the planned path, and after determining the planned position whose velocity direction is opposite to that of the reference position at the same moment, it will not Then determine the reference curvature and reference distance of the subsequent planning position.
- the above-mentioned speed reversal means that the angle between the two speeds is greater than 90 degrees, that is, for any speed, the speed is decomposed along the other speed direction and the direction perpendicular to the other speed direction, and the determined along If the component of the other velocity direction is negative, it can be determined that the two velocity directions are opposite.
- the same direction of speed means that the angle between the two speeds is less than 90 degrees. If the component of the velocity direction is a positive value, it can be determined that the two velocity directions are in the same direction.
- S104 According to the point in the reference path closest to the calibration planning position, determine the calibration reference position in the reference path, and according to the reference path after the calibration reference position in the reference path, plan to use the Calibration planning position as the starting point of the calibration path.
- the unmanned driving device can adjust the planning route after the calibration planning position in the planning route, and adjust the calibration planning position in the planning route
- the easiest way is to re-determine the reference position corresponding to the calibration planning position as the calibration reference position, and plan according to the reference path after the re-determined calibration reference position with the calibration planning position as the starting point .
- the unmanned device may first determine the distance between the calibration planning position and each point in the reference route. Then, according to the determined distances, the point closest to the calibration planning position is determined from the reference positions. Finally, according to the determined point closest to the calibration planning position, a certain point is randomly determined from the path after the point in the reference path as the calibration reference position corresponding to the calibration planning position.
- the calibration reference position is a position in the reference path that is not behind the point closest to the calibration planning position. "Behind" means that along the direction of the reference path, the calibration reference position is ahead of the point closest to the calibration planning position.
- the unmanned equipment since the unmanned equipment often controls the driving of the unmanned equipment in the Fresnel coordinate system during driving, the unmanned equipment can also determine the calibration in the Fresnel coordinate system. Reference position.
- the unmanned device can construct a Fresnel coordinate system according to the reference path and the distance from the reference path, and then project the calibration planning position to determine that the calibration planning position is in the Fresnel coordinate system
- the reference position in , using the reference position as the calibration reference position, and determining the distance between the calibration planning position and the calibration reference position. As shown in Figure 3.
- FIG 3 is a schematic diagram of determining the calibration reference position provided by the present disclosure.
- the solid line a represents the reference path
- the dotted line b represents obstacles
- the solid line c represents the planned path.
- Dot A is the calibration planning position
- dot B is the same as dot A.
- the reference position at the same time, project the calibration planning position, and determine the point C as the reference position of the calibration planning position in the Fresnel coordinate system, then the unmanned device can use the point C as the The calibration reference position corresponding to the calibration planning position, where the direction of the arrow is the path direction.
- the unmanned device can carry out path planning based on the calibration path after the calibration reference position in the reference path, with the calibration planning position as the starting point, and determine the calibration planning position as the starting point. Calibration path.
- the unmanned device may re-determine the attribute information of each planned position according to the attribute information corresponding to each reference position in the reference route after the calibration reference position in the reference route, and take the calibration planned position as a starting point,
- the re-determined planning positions are connected to obtain a calibration path starting from the calibration planning position.
- the unmanned equipment since the unmanned equipment usually controls its own driving in the Fresnel coordinate system, the unmanned equipment can be in the Fresnel coordinate system, according to the curvature of each reference position, the calibration planning position and Calibrate the distance of the reference position, re-determine the curvature of each planning position, and the distance between each planning position and its corresponding reference position, and connect the re-determined planning positions to obtain a calibration path starting from the calibration planning position .
- each reference position in the reference route after the calibration reference position in the reference route can also be re-determined along the reference route with the calibration reference position as a starting point.
- the unmanned driving device can use the calibration reference position as a starting point to re-determine the reference position corresponding to each time, and for the reference position at each time, according to the attribute information of the reference position at that time, determine the corresponding The attribute information of the planning location, and then according to the planning location corresponding to each moment, determine the calibration path starting from the calibration planning location.
- the unmanned device when the unmanned device is planning the path, it can also plan the path according to the position of obstacles in the surrounding environment sensed by the unmanned device.
- the reference path calibration reference position, calibration planning position and The location of obstacles, etc. are used for path planning.
- This disclosure does not limit the way how to perform path planning.
- This disclosure does not repeat the process of how to determine the calibration path.
- the algorithm used There is no limitation on the algorithm used, which can be set according to needs.
- the calibration path is determined only based on the calibration reference position corresponding to the calibration planning position, and the determined planning path may have a sudden change in the speed of the unmanned device.
- the unmanned equipment can use the smooth transition characteristics of the arc for path planning.
- the unmanned device can determine the center of the circle from the normal direction of the velocity direction of the calibration planning position, and the distance between the center of the circle and the calibration planning position is the minimum turning radius of the unmanned device, then after the center of the circle is determined , the unmanned device can use the minimum turning radius as the radius to determine the calibration circle corresponding to the calibration planning position, and take the calibration planning position as the starting point, and take the calibration circle, the calibration planning position and the calibration reference position as the connecting line The other intersection point is the end point, and the calibration arc corresponding to the calibration planning position is determined as the first calibration path.
- the unmanned driving device may use the end point of the first calibration path as a starting point, and perform path planning according to the path after the reference position is calibrated in the reference path, to determine the second calibration path. As shown in Figure 4a and Figure 4b.
- Fig. 4a is a schematic diagram of determining the first calibration path provided by the present disclosure.
- the solid line a is the reference path of the unmanned equipment, and the solid line b and the solid line c are combined to form the planned path of the unmanned equipment, wherein, The solid line b is the planned route before the calibration of the planned position in the planned route, the solid line c is the planned route after the calibration of the planned position in the planned route, point D is the planned position for calibration, point Q is the reference position for calibration, and V1 is the speed, then the direction of V 1 is the speed direction of point D, and the direction of V 2 is the normal direction of the speed direction of point D.
- the unmanned equipment determines the position whose distance from point D is the minimum turning radius of the preset unmanned equipment, as the center of circle O, and then determines the calibration circle, and determines the calibration circle and the calibration circle Another point of intersection E on the connecting line between the planning position and the calibration reference position can be determined as the end point of the first calibration path, and according to the characteristics of the circle, the unmanned device can be planned to obtain the speed direction along the Q point
- the velocity component of point D is equal to the velocity component of point D along the velocity direction of point Q and opposite to point E, and the determined first calibration path is continuous.
- the arrow direction is the path direction.
- the unmanned driving device can determine a calibration path, as shown in Fig. 4b.
- Figure 4b is a schematic diagram of determining the calibration path provided by the present disclosure, similar to Figure 4a, the solid line a is the reference path of the unmanned device, the solid line b is the planned path before the calibration planning position in the planned path, and point D is the calibration plan position, point Q is the calibration reference position, point E is the end point of the first calibration path, and the solid line d is the first calibration path, so the unmanned device can use the end point E of the first calibration path as the starting point, according to the With reference to the path following the path point Q, the second calibration path e is determined. Therefore, the unmanned driving device can determine that the calibration path is composed of the first calibration path d and the second calibration path e. That is to say, the solid line d and the solid line e constitute the calibration path of the unmanned device. Among them, the arrow direction is the path direction.
- the velocity component of its velocity along the velocity direction of point Q may be opposite to the velocity component of the velocity of point D along the velocity direction of point Q.
- S106 Determine a planned route according to the planned route before the calibration planned position in the planned route and the calibration route, and control the unmanned device to drive along the planned route.
- the unmanned driving device can splice the path before the calibration planning position in the planned path and the determined calibration path to obtain the unmanned
- the planned path of the human-driven device is shown in Figure 5.
- FIG. 5 is a schematic diagram of determining the planned path provided by the present disclosure.
- the solid line a is the reference path
- the dotted line b is the obstacle
- the solid line c and the solid line d form the planned path
- the solid line e is the calibration path.
- Line c is the path before the planned position is calibrated in the planned path
- the solid line d is the path after the planned position is calibrated in the planned path
- dot A is the planned position for calibration
- dot B is the reference position at the same time as dot A
- the unmanned device can determine that the path formed by the solid line c and the solid line e is the planned path of the unmanned device, and the direction of the arrow is the path direction.
- the unmanned device can also determine the calibration arc and the correction path, then the unmanned device can also use the path before the calibration planning position in the planned path to determine the first calibration
- the path and the second calibration path are spliced to obtain the planned path of the unmanned device.
- the planned path is a path composed of solid line b, solid line d, and solid line e.
- the unmanned device can control itself to drive along the planned route.
- the control method can be determined based on a motion strategy model, and the unmanned device can use the planned path as an input into the motion strategy model to obtain a corresponding motion strategy, then the unmanned device can be based on the determined motion strategy , to control the driving of the unmanned equipment.
- the unmanned driving device can also determine its own motion strategy according to its current speed, the curvature and speed of each planned position in the planned path, and control its own driving according to the motion strategy.
- the unmanned driving device since the speed direction of the calibration planning position in the original planning path is opposite to the speed direction of the reference position at the same time, the speed direction of each planning position before the calibration planning position in the planning path is opposite to the speed direction of the reference position at the same time same direction.
- the unmanned driving device has experienced a deceleration process in the process of reaching the calibration planning position from the starting point, while the unmanned driving device does not need to decelerate as in the original planning path when driving along the re-planned planning path operate.
- the unmanned driving device can first determine the reference position at the same time as the calibration planning position as the update point, and then according to the attribute information of each reference position in the reference route before the update point, the reference route before the calibration planning position And the attribute information of at least part of the planned positions in the calibration path (for example, the planned positions corresponding to the first five moments in the calibration path), the attribute information of each planned position in the planned path before the calibration planned position is updated to ensure that no When the human-driven device drives along the re-determined planned route, the speed change at adjacent moments does not exceed the preset change threshold, ensuring the smooth driving of the unmanned device. For example, according to the attribute information of each reference position in the solid line a before point B in FIG. 5 , the attribute information of part of the planned positions in the solid line c and the solid line e, the attribute information of each planned position in the solid line e is re-determined.
- the unmanned driving device may also update the attribute information of each planned position in the planned route before the calibration planned position only according to part of the attribute information of each reference position in the reference route before the update point.
- the unmanned driving device can determine the distance between point A and point A five times before point A in solid line c based on the attribute information of the reference position from point B to point B in the solid line a.
- the attribute information of the planning location is used to ensure that the unmanned vehicle runs smoothly at point A.
- the unmanned driving device can also determine the speed corresponding to each planned position according to the determined attribute information such as curvature and time of each planned position in the planned route, and according to The determined speed corresponding to each planned position updates the attribute information of each planned position in the re-determined planned route.
- the unmanned device can also re-determine the time corresponding to each planned position, so that when the unmanned device travels along the planned route, the unmanned device can move as fast as possible. In a state of smooth driving, improve the utilization rate of unmanned equipment.
- the unmanned The human-driven device can determine the velocity direction of each planned location in the planned path and the planned location whose velocity direction is opposite to that of the reference location at the same time, and then determine the calibration planned location according to the time of each planned location.
- the unmanned device can determine the coordinates of the planned position corresponding to each moment and its corresponding reference position in the Cartesian coordinate system, and determine the speed corresponding to the reference position and the speed corresponding to the planned position, and through the reference The product of the speed corresponding to the position and the speed corresponding to the planned position is used to judge whether the speed of the reference position is the same as the speed of the planned position. And after determining the planned position whose speed direction is opposite to that of the corresponding reference position, use it as each planned position to be calibrated, then the unmanned device can move each planned position to be calibrated along the direction of the planned path Sorting is carried out, and a certain point is randomly selected from the planning path to be calibrated composed of planning positions to be calibrated as the planning planning position for calibration.
- the unmanned device can select the first planned location to be calibrated in chronological order as the planned location for calibration, so as to ensure that there is no potential safety hazard when the unmanned device travels along the re-determined calibration path .
- the unmanned driving device can also calculate the planned positions to be calibrated according to the chronological order and the time corresponding to each planned calibration position. sorting, and according to the determined sorting, randomly select a certain calibration planning position, or the first planned position to be calibrated at the time of determination, as the calibration planning position.
- the unmanned device when determining the planned route, in order to ensure the immediacy and accuracy of the planned route, the unmanned device can perform a route check on the unmanned device according to the preset planning duration, for example, every ten seconds. Planning, then, in step S100, when the unmanned device is planning the path at the current moment, the motion strategy of the unmanned device in the past planning time can be obtained, and based on the historical moment of the unmanned device The motion strategy to determine the planned path of the unmanned device.
- the path planning method in the present disclosure can also re-plan the future trajectory of the unmanned driving device every preset planning period.
- the unmanned device can continue to driving, and when the speed direction of the calibration planning position is opposite to the speed direction of the calibration reference position, at the calibration planning position, the speed direction of the unmanned equipment may change suddenly, therefore, the unmanned equipment can be based on the Compare the velocity directions of the quasi-planned position and the calibrated reference position for path planning.
- the unmanned driving can first determine whether the velocity direction of the calibration reference position is opposite to the velocity direction of the calibration planning position, wherein the method for determining whether the velocity direction is reverse can refer to the method in the above step S102.
- the unmanned device can determine the first calibration path according to the calibration planning position, and determine the second calibration path according to the first calibration path, and according to the planning The path before the calibration planning position, the first calibration path and the second calibration path in the path are re-determined as the planning path.
- the unmanned device can determine the calibration path according to the calibration planning position and the corresponding speed and speed direction of the calibration planning position, and according to the calibration path, and In the planned path, the path before the planned position is calibrated, and the planned path is re-determined.
- the driverless device can also determine the calibration reference position based on the calibration circle O corresponding to the calibration planning position, and then determine the planning path. As shown in Figure 6a and Figure 6b.
- Fig. 6a is a schematic diagram of determining the calibration planning position provided by the present disclosure. Similar to Fig. 4a, the solid line a is the reference path of the unmanned equipment, and the solid line b and the solid line c are combined to form the planned path of the unmanned equipment, wherein , the solid line b is the path before the planned position is calibrated in the planned path, the solid line c is the path after the planned position is calibrated in the planned path, point D is the planned position for calibration, point Z is the closest point to point D in the reference path, V 1 is the velocity at point D, then the direction of V 1 is the velocity direction of point D, and the direction of V 2 is the normal direction of the velocity direction of point D.
- the unmanned equipment determines the distance from the point D to the position of the preset minimum turning radius of the unmanned equipment, as the center O, and then determines the calibration circle, and determines the distance from the calibration circle , the point E closest to the reference path is used as the end point of the first calibration path, and the point Q closest to the calibration circle on the reference path is determined as the calibration reference position.
- the calibration reference position Q does not lag behind the point Z closest to the calibration planning position.
- the arrow direction is the path direction. Therefore, the unmanned driving device can calibrate the reference position point Q based on the calibration planning position point D, and determine the planned route, as shown in FIG. 6b.
- Fig. 6b is a schematic diagram of determining a planned path of an unmanned device provided in the present disclosure. Similar to Figure 6a, the solid line a is the reference path of the unmanned equipment, the solid line b is the path before the calibration planning position in the planning path, point D is the calibration planning position, point Q is the calibration reference position, and point E is the first the end point of the calibration path, the unmanned driving device can use the end point E of the first calibration path as the starting point, and determine the second calibration path e according to the path after the reference path point Q. Therefore, the unmanned driving device can determine that the planned route is composed of the route b before the calibration of the planned position in the planned route, the first calibration route d, and the second calibration route e. That is to say, the solid line b, the solid line d and the solid line e constitute the planned path of the unmanned device. Among them, the arrow direction is the path direction.
- the unmanned driving device can determine the reference path according to the location of the unmanned driving device at each historical moment, the strategy executed by the unmanned driving device, and the like. As shown in Figure 7.
- Fig. 7 is a schematic diagram of the reference path for determining the unmanned driving device provided by the present disclosure.
- the solid line a, dotted line b, dotted line c, and solid line d are lane lines, and the dotted line b and dotted line c represent that each lane is in the same direction , the white cuboid represents unmanned equipment, the gray cuboid indicates other vehicles, and the dotted horizontal line e is the history of unmanned equipment determined by the location of each historical moment of the unmanned equipment and the movement strategy of the unmanned equipment.
- the reference path of the unmanned equipment can be determined as the solid line f, that is, the lane centerline of the lane between the dotted line c and the solid line d is the reference path of the unmanned equipment.
- the direction of the arrow is the path direction, that is, the driving direction of the unmanned equipment.
- the unmanned equipment can determine the composition of lanes in the same direction A total lane, and determine the lane centerline of the total lane as the reference path. For example, let the lanes between the solid line a and the solid line d form a total lane, and determine the lane centerline of the total lane as the reference path, that is, the lane centerline of the lane between the dashed line b and the dashed line c is the Reference paths for unmanned devices.
- the lane line in the middle can be determined as the reference path. For example, assuming that the lane between dotted line b and dotted line c is in the same direction as the lane between dotted line c and dotted line d, then dotted line c can be determined as the reference path.
- the unmanned driving device can also perform path planning based on the various strategies in the driving process of the unmanned driving device and the pre-stored high-precision map, and determine that there is no obstacle factor. Under the influence, the trajectory that the unmanned equipment can drive is used as the reference path of the unmanned equipment. As shown in Figure 8.
- FIG. 8 is a schematic diagram of determining a reference route and a planned route of an unmanned driving device provided in the present disclosure. Similar to Figure 7, the solid line a, dotted line b, dotted line c, and solid line d in Figure 8 are lane lines, and the dotted line b and dotted line c indicate that each lane is in the same direction, and the unmanned driving device in Figure 8 needs to execute the strategy In order to drive to the first lane on the left and continue driving along this lane, the unmanned device can perform path planning according to the pre-stored high-precision map and the motion strategy executed by the unmanned device, and determine the location of the unmanned device.
- the reference path that is, the solid line g
- the unmanned equipment can recognize and determine the obstacles (eg, part A in the figure) and the reference path according to the target object, and carry out Path planning, determining the planned path of the unmanned device, that is, the dotted line h, wherein the direction of the arrow is the path direction, that is, the driving direction of the unmanned device.
- the path planning method provided in the present disclosure is to adjust the planned dotted line h so that when the unmanned driving device drives according to the planned path, reverse driving will not occur.
- the unmanned device when determining the reference route, in order to avoid the situation that the pre-stored high-precision map is not enough to describe the lane lines around the unmanned device, and thus the accurate reference route cannot be determined, in step S100, the unmanned device It can also identify the environmental data of unmanned equipment and determine the reference path.
- the unmanned device may first acquire the image collected by the unmanned device.
- the image can be obtained by a collection device pre-installed in the driverless device.
- the collection device may include image collection devices such as a monocular camera and a binocular camera.
- the unmanned driving device can also obtain point cloud data collected by the unmanned driving device, and the collecting device can include collecting devices such as lidar.
- the unmanned device can perform target recognition on the acquired image, determine the position of the lane line and the position of each obstacle in the image, and then determine the position of the lane centerline of the lane where the unmanned device is located according to the position of the lane line. Location.
- the unmanned driving device determines the position of the lane line, it can also perform target recognition on the acquired point cloud data to determine the position of the lane line in the image.
- the unmanned driving device may use the determined position of the lane centerline of the lane where the unmanned driving device is located as the reference path of the unmanned driving device.
- the unmanned driving device can perform path planning based on the determined reference path and the positions of obstacles determined by object recognition in the image, and use the planned path as the planned path of the unmanned driving device.
- the present disclosure also provides a path planning method for an unmanned driving device, referring to FIG. 9 , the method includes the following steps S900-S906.
- S900 Obtain the attribute information of each reference position in the reference path, and the attribute information of each planned position in the planned path of the unmanned device.
- the attribute information at least includes: time, path curvature, speed direction and speed of the unmanned device.
- S902 according to the direction of the planned path, sequentially determine whether the speed direction of each planned position is opposite to that of the reference position at the same time, if so, use the planned position with the opposite speed direction as the calibration planned position.
- S902 reference may be made to the description in S102 above, which will not be repeated here.
- S904 Determine a calibration reference position in the reference path, and plan a calibration path starting from the calibration planning position according to the reference path after the calibration reference position in the reference path.
- the calibration path starting from the calibration planning position is planned, refer to the description in S904 above, and will not be repeated here.
- the manners of determining the calibration reference position in the reference path in S904 include but are not limited to the following three.
- Method 1 Randomly determine a point from the path after the point closest to the calibration planning position in the reference path as the calibration reference position. For the first method, refer to the description in S104 above, and details will not be repeated here.
- Method 2 The calibration planning position is projected to obtain the reference position of the calibration planning position in the Fresnel coordinate system, and the reference position of the calibration planning position in the Fresnel coordinate system is used as the calibration reference position.
- the second method refer to the description corresponding to FIG. 3 above, and details are not repeated here.
- Method 3 Determine the calibration circle, and use the point closest to the calibration circle on the reference path as the calibration reference position.
- the center of the calibration circle is in the normal direction of the velocity direction of the calibration planning position, and the distance between the center of the circle and the calibration planning position is preset Minimum turning radius for unmanned vehicles.
- the third method refer to the descriptions corresponding to FIG. 6a and FIG. 6b above, and details are not repeated here.
- S906 Re-determine the planned route according to the planned route before calibrating the planned position in the planned route and the calibrated route, and control the unmanned device to drive along the planned route.
- the implementation manner of S906 may refer to the description in S106 above, which will not be repeated here.
- the above is the path planning method for unmanned equipment provided by one or more embodiments of the present disclosure, and the present disclosure also provides a corresponding path planning device for unmanned equipment.
- FIG. 10 is a schematic diagram of a path planning device for unmanned equipment provided by the present disclosure, including:
- the acquiring module 200 is configured to acquire the attribute information of each reference position in the reference route, and the attribute information of each planned position in the planned route of the unmanned device, the attribute information at least includes: time, the speed of the unmanned device direction and speed.
- the determination module 202 is used to sequentially determine whether the speed direction of each planned position is opposite to that of a reference position at the same time according to the direction of the planned path, and if so, use the planned position with the opposite speed direction as the calibration planned position.
- the calibration module 204 is configured to determine a calibration reference position in the reference path according to the point closest to the calibration planning position in the reference path, and according to the reference path after the calibration reference position in the reference path, A calibration path starting from the calibration planning location is planned.
- the planning module 206 is configured to re-determine the planned route according to the planned route before the calibration planned position in the planned route and the calibration route, and control the unmanned device to drive along the planned route.
- the calibration module 204 is configured to determine that the distance from the calibration planning position to the calibration planning position is the preset minimum value of the unmanned equipment in the normal direction of the velocity direction of the calibration planning position.
- the turning radius is the center of the circle, the minimum turning radius is used as the radius, and the calibration planning position is used as the starting point to determine a first calibration path, and the end point of the first calibration path is located at the calibration planning position and the calibration reference position on the connection; with the end point of the first calibration path as the starting point, according to the reference path after the reference position is calibrated in the reference path, path planning is performed to determine the second calibration path, the first calibration path and the The second calibration path constitutes the calibration path.
- the attribute information of the planned position also includes the distance between the planned position and its corresponding reference position, and the curvature of the reference position.
- the determining module 202 is configured to position, determine the curvature of the reference position same as the planning position at the moment, as the reference curvature of the planning position, and determine the distance between the planning position and the same reference position at the time, as the reference distance of the planning position, according to For the direction of the planned path, for each planned position in turn, judge whether the product of the reference curvature of the planned position and the reference distance of the planned position is greater than 1; The speed direction of the position is opposite, otherwise, continue to judge whether the speed direction of the subsequent planned position of the planned path is opposite to the speed direction of the reference position at the same time, until all planned positions are judged.
- the planning module 206 is further configured to determine the first calibration path according to the calibration planning position when the velocity direction of the calibration reference position is opposite to the velocity direction of the calibration planning position, according to determining the second calibration path at the end point of the first calibration path, and according to the first calibration path, the second calibration path, and the planning path before the calibration planning position in the planning path, re- Determine a planned path, when the velocity direction of the calibration reference position is the same as the velocity direction of the calibration planned position, determine the calibration path according to the calibration planned position, and According to the planned path before the calibration of the planned position, re-determine the planned path.
- the determination module 202 is configured to, for each planned position, determine whether the speed direction of the planned position is opposite to the speed direction of the reference position at the same time, and if so, use the planned position as the planned position to be calibrated , sort the planned positions to be calibrated according to the direction of the planned path, and determine the planned calibration position according to the sorting.
- the calibration module 204 is configured to use the calibration reference position as a starting point to re-determine the reference position corresponding to each time, and for the reference position at each time, according to the attribute information of the reference position at that time, Determine the attribute information of the planned location corresponding to the moment, and determine a calibration path starting from the planned calibration location according to the planned location corresponding to each moment.
- the planning module 206 is further configured to, according to the attribute information of each reference position in the reference path before the reference position at the same time as the calibration planning position, the planning path before the calibration planning position, and the attribute information of at least part of the planned positions in the calibration route, and update the attribute information of each planned position in the planned route before the calibration planned position in the planned route.
- FIG. 11 is a schematic diagram of another path planning device for unmanned equipment provided by the present disclosure, including:
- the obtaining module 1100 is used to obtain the attribute information of each reference position in the reference route, and the attribute information of each planned position in the planned route of the unmanned driving device.
- the attribute information at least includes: time, speed direction and speed of the unmanned driving device .
- the determination module 1102 is used to sequentially determine whether the speed direction of each planned position is opposite to that of the reference position at the same time according to the direction of the planned path, and if so, use the planned position with the opposite speed direction as the calibration planned position.
- the calibration module 1104 is configured to determine a calibration reference position in the reference path, and plan a calibration path starting from the calibration planning position according to the reference path after the calibration reference position in the reference path.
- the planning module 1106 is configured to re-determine the planned route according to the planned route before the planned position is calibrated in the planned route and the calibrated route, and control the unmanned driving device to drive along the planned route.
- the calibration module 1104 is configured to randomly determine a point in the path after the point closest to the calibration planning position in the reference path as the calibration reference position; or, project the calibration planning position to obtain the calibration planning position
- For the reference position in the Fresnel coordinate system use the reference position of the calibration planning position in the Fresnel coordinate system as the calibration reference position; or, determine the calibration circle, and use the point closest to the calibration circle on the reference path as the calibration
- the reference position, the center of the calibration circle is in the normal direction of the velocity direction of the calibration planning position, and the distance between the center of the circle and the calibration planning position is the preset minimum turning radius of the unmanned driving device.
- the present disclosure also provides a computer-readable storage medium, which stores a computer program.
- the computer program can be used to execute the path planning method for the unmanned device provided in FIG. A path planning method for a driving device.
- the present disclosure also provides a schematic structure diagram of the unmanned driving device shown in FIG. 12 .
- the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and of course may include hardware required by other services.
- the processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, so as to realize the path planning method for the unmanned device described in FIG. 2 above, or realize the unmanned device shown in FIG. 9 above. path planning method.
- the improvement of a technology can be clearly distinguished as an improvement in hardware (for example, improvements in circuit structures such as diodes, transistors, and switches) or improvements in software (improvement in method flow).
- improvements in circuit structures such as diodes, transistors, and switches
- improvements in software improvement in method flow
- the improvement of many current method flows can be regarded as the direct improvement of the hardware circuit structure.
- Designers almost always get the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that the improvement of a method flow cannot be realized by hardware physical modules.
- a programmable logic device Programmable Logic Device, PLD
- PLD Programmable Logic Device
- FPGA Field Programmable Gate Array
- HDL Hardware Description Language
- ABEL Advanced Boolean Expression Language
- AHDL Altera Hardware Description Language
- HDCal JHDL
- Lava Lava
- Lola MyHDL
- PALASM RHDL
- VHDL Very-High-Speed Integrated Circuit Hardware Description Language
- Verilog Verilog
- the controller may be implemented in any suitable way, for example the controller may take the form of a microprocessor or processor and a computer readable medium storing computer readable program code (such as software or firmware) executable by the (micro)processor , logic gates, switches, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable logic controllers and embedded microcontrollers, examples of controllers include but are not limited to the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20 and Silicone Labs C8051F320, the memory controller can also be implemented as part of the control logic of the memory.
- controller in addition to realizing the controller in a purely computer-readable program code mode, it is entirely possible to make the controller use logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded The same function can be realized in the form of a microcontroller or the like. Therefore, such a controller can be regarded as a hardware component, and the devices included in it for realizing various functions can also be regarded as structures within the hardware component. Or even, means for realizing various functions can be regarded as a structure within both a software module realizing a method and a hardware component.
- a typical implementing device is a computer.
- a computer may be, for example, a personal computer, laptop computer, cellular phone, camera phone, smart phone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device Or a combination of any of these devices.
- the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Accordingly, the present disclosure can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present disclosure may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
- computer-usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.
- These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to operate in a specific manner, such that the instructions stored in the computer-readable memory produce an article of manufacture comprising instruction means, the instructions
- the device realizes the function specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.
- a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
- processors CPUs
- input/output interfaces network interfaces
- memory volatile and non-volatile memory
- Memory may include non-permanent storage in computer-readable media, in the form of random access memory (RAM) and/or nonvolatile memory such as read-only memory (ROM) or flash RAM. Memory is an example of computer readable media.
- RAM random access memory
- ROM read-only memory
- flash RAM flash random access memory
- Computer-readable media including both permanent and non-permanent, removable and non-removable media, can be implemented by any method or technology for storage of information.
- Information may be computer readable instructions, data structures, modules of a program, or other data.
- Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Flash memory or other memory technology, Compact Disc Read-Only Memory (CD-ROM), Digital Versatile Disc (DVD) or other optical storage, Magnetic tape cartridge, tape magnetic disk storage or other magnetic storage device or any other non-transmission medium that can be used to store information that can be accessed by a computing device.
- computer-readable media excludes transitory computer-readable media, such as modulated data signals and carrier waves.
- the embodiments of the present disclosure may be provided as methods, systems or computer program products. Accordingly, the present disclosure can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present disclosure may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
- a computer-usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.
- program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types.
- the present disclosure may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network.
- program modules may be located in both local and remote computer storage media including storage devices.
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Aviation & Aerospace Engineering (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
一种无人驾驶设备的路径规划方法和装置,应用于无人驾驶领域中的无人驾驶设备,如无人车中。在无人驾驶设备的路径规划过程中,按规划路径方向,在规划路径上确定与参考路径速度方向相反的校准规划位置,并在参考路径中根据与校准规划位置距离最近的点,确定校准参考位置,然后以校准规划位置为起点,根据参考路径中校准参考位置后的路径,重新规划该校准规划位置之后的规划路径。
Description
本申请要求于2021年08月04日提交的申请号为202110888658.0、申请名称为“一种无人驾驶设备的路径规划方法及装置”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
本公开涉及无人驾驶技术领域,尤其涉及无人驾驶设备的路径规划。
目前,随着无人驾驶技术的发展,无人驾驶设备的用途愈发广泛。为了保证无人驾驶设备的行驶安全,通常需要对无人驾驶设备的行驶路线进行路径规划。
发明内容
本公开提供无人驾驶设备的路径规划,本公开采用下述技术方案:
本公开提供一种无人驾驶设备的路径规划方法,包括:
获取参考路径中各参考位置的属性信息,以及无人驾驶设备的规划路径中各规划位置的属性信息,所述属性信息至少包括:时刻、所述无人驾驶设备的速度方向以及速度大小;
根据所述规划路径的方向,依次判断各规划位置的速度方向是否与其时刻相同的参考位置的速度方向相反,若是,将速度方向相反的规划位置作为校准规划位置;
根据所述参考路径中距离所述校准规划位置最近的点,在所述参考路径中确定校准参考位置,并根据所述参考路径中所述校准参考位置后的参考路径,规划以所述校准规划位置为起点的校准路径;
根据所述规划路径中所述校准规划位置前的规划路径,以及所述校准路径,重新确定规划路径,并控制所述无人驾驶设备沿着所述规划路径行驶。
本公开提供一种无人驾驶设备的路径规划方法,包括:
获取参考路径中各参考位置的属性信息,以及无人驾驶设备的规划路径中各规划位置的属性信息,所述属性信息至少包括:时刻、所述无人驾驶设备的速度方向以及速度大小;
根据所述规划路径的方向,依次判断各规划位置的速度方向是否与其时刻相同的参考位置的速度方向相反,若是,将速度方向相反的规划位置作为校准规划位置;
在所述参考路径中确定校准参考位置,根据所述参考路径中所述校准参考位置后的参考路径,规划以所述校准规划位置为起点的校准路径;
根据所述规划路径中所述校准规划位置前的规划路径,以及所述校准路径,重新确定规划路径,并控制所述无人驾驶设备沿着所述规划路径行驶。
本公开提供一种无人驾驶设备的路径规划装置,包括:
获取模块,用于获取参考路径中各参考位置的属性信息,以及无人驾驶设备的规划路径中各规划位置的属性信息,所述属性信息至少包括:时刻、所述无人驾驶设备的速度方向以及速度大小;
确定模块,用于根据所述规划路径的方向,依次判断各规划位置的速度方向是否与其时刻相同的参考位置的速度方向相反,若是,将速度方向相反的规划位置作为校准规划位置;
校准模块,用于根据所述参考路径中距离所述校准规划位置最近的点,在所述参考路径中确定校准参考位置,并根据所述参考路径中所述校准参考位置后的参考路径,规划以所述 校准规划位置为起点的校准路径;
规划模块,用于根据所述规划路径中所述校准规划位置前的规划路径,以及所述校准路径,重新确定规划路径,并控制所述无人驾驶设备沿着所述规划路径行驶。
本公开提供一种无人驾驶设备的路径规划装置,包括:
获取模块,用于获取参考路径中各参考位置的属性信息,以及无人驾驶设备的规划路径中各规划位置的属性信息,所述属性信息至少包括:时刻、所述无人驾驶设备的速度方向以及速度大小;
确定模块,用于根据所述规划路径的方向,依次判断各规划位置的速度方向是否与其时刻相同的参考位置的速度方向相反,若是,将速度方向相反的规划位置作为校准规划位置;
校准模块,用于在所述参考路径中确定校准参考位置,并根据所述参考路径中所述校准参考位置后的参考路径,规划以所述校准规划位置为起点的校准路径;
规划模块,用于根据所述规划路径中所述校准规划位置前的规划路径,以及所述校准路径,重新确定规划路径,并控制所述无人驾驶设备沿着所述规划路径行驶。
本公开提供了一种计算机可读存储介质,所述存储介质存储有计算机程序,所述计算机程序被处理器执行时实现上述无人驾驶设备的路径规划方法。
本公开提供了一种电子设备,包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序,所述处理器执行所述程序时实现上述无人驾驶设备的路径规划方法。
本公开提供了一种计算机程序产品,计算机程序产品包括计算机程序或指令,计算机程序或指令被处理器执行,以使计算机实现上述无人驾驶设备的路径规划方法。
此处所说明的附图用来提供对本公开的进一步理解,构成本公开的一部分,本公开的示意性实施例及其说明用于解释本公开,并不构成对本公开的不当限定。在附图中:
图1为相关技术进行路径规划,确定规划路径的示意图;
图2为本公开提供的无人驾驶设备的路径规划方法的流程示意图;
图3为本公开提供的确定校准参考位置的示意图;
图4a为本公开提供的确定第一校准路径的示意图;
图4b为本公开提供的确定校准路径的示意图;
图5为本公开提供的确定规划路径的示意图;
图6a为本公开提供的确定校准规划位置的示意图;
图6b为本公开提供的确定无人驾驶设备的规划路径的示意图;
图7为本公开提供的确定无人驾驶设备的参考路径的示意图;
图8为本公开提供的确定无人驾驶设备的参考路径和规划路径的示意图;
图9为本公开提供的无人驾驶设备的路径规划方法的流程示意图;
图10为本公开提供的无人驾驶设备的路径规划装置示意图;
图11为本公开提供的无人驾驶设备的路径规划装置示意图;
图12为本公开提供的对应于图2和图9的无人驾驶设备的示意图。
为使本公开的目的、技术方案和优点更加清楚,下面将结合本公开实施例及相应的附图对本公开技术方案进行清楚、完整地描述。显然,所描述的实施例仅是本公开一部分实施例,而不是全部的实施例。基于本公开中的实施例,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,都属于本公开保护的范围。
相关技术中,一种常用的无人驾驶设备的路径规划方法是基于无人驾驶设备的参考路径 实现的。示例性的,该无人驾驶设备可获取由各时刻对应的参考位置拟合得到的参考路径,并对无人驾驶设备周围环境进行“感知”,确定无人驾驶设备周围的障碍物的位置,然后根据参考路径和确定出的障碍物的位置,确定无人驾驶设备的规划路径,控制无人驾驶设备沿着规划路径行驶。其中,各参考位置可表征参考路径中各时刻对应的位置以及速度。
相关技术在对无人驾驶设备的行驶路径进行路径规划时,通常可基于两个原则进行规划,其一,无人驾驶设备在规划得到的路径中拍摄到的图像应该是连续的,也就是说,无人驾驶设备在笛卡尔坐标系中的坐标不能跳变,其二,规划路径的方向应该沿着参考路径的方向,也就是说,参考路径和规划路径的方向大致相同。在遵循上述原则以及参考路径中各参考位置的曲率足够小的假设下,相关技术中根据参考路径确定出的规划路径,其路径连续且与参考路径的方向一致,则无人驾驶设备可控制自身沿着规划出的路径。但相关技术中往往会出现参考位置对应的曲率较大的情况。则在上述两个原则不满足,或者参考路径中的参考位置曲率较大时,可能会导致无人驾驶设备急停或无法正常行驶。例如,相关技术在参考路径中的参考位置的曲率较大,且该参考位置周围存在障碍物时,可能会出现确定出的规划路径中,该参考位置对应的规划位置超过下一时刻的参考位置(即,规划路径抄近路)的情况,导致根据下一时刻的参考位置确定出的下一时刻的规划位置在无人驾驶设备后方,则该无人驾驶设备需要反向行驶才能到达下一时刻的规划位置,使得无人驾驶设备存在极大安全隐患。
区别于相关技术中直接控制无人驾驶设备沿着规划路径行驶,导致当参考路径的曲率较大时,规划出的路径是无人驾驶设备出现急停、倒退等情况,存在安全隐患的问题,本公开提供一种可基于规划路径中各点的曲率、速度等对规划路径进行调整,重新确定规划路径的方法,以保证无人驾驶设备的行驶安全。
相关技术在参考路径中的参考位置的曲率较大,且基于该参考位置进行路径规划时,若无人驾驶设备感知到障碍物,则规划出来的路径可能会存在规划路径“抄近路”的情况,如图1所示。
图1为相关技术进行路径规划,确定规划路径的示意图。图中,ABCD所在的曲线为无人驾驶设备的参考路径,虚线为无人驾驶设备通过目标物识别确定出的障碍物,AEFG所在的曲线为相关技术确定出的规划路径,箭头方向为路径方向,且为了实现精准控制,通常确定出的参考路径包含了各时刻对应的参考位置,以及各参考位置的速度,则基于参考路径确定出的规划路径中,同样包含了各时刻对应的规划位置,以及各规划位置对应的速度。图中,点A对应了同时刻的参考位置和规划位置,参考位置点B和规划位置点E是同时刻的,参考位置点C和规划位置点F是同时刻的,参考位置点D和规划位置点G是同时刻的,且参考位置点B为参考位置点A的下一时刻的参考位置,参考位置点C为参考位置点B的下一时刻的参考位置,参考位置点D为参考位置点C的下一时刻的参考位置。同样,规划位置点E为规划位置点A的下一时刻的参考位置,规划位置点F为规划位置点E的下一时刻的参考位置,规划位置点G为规划位置点F的下一时刻的参考位置。
则该无人驾驶设备可首先根据参考位置点A到参考位置B之间的各时刻的参考位置的曲率,以及障碍物的位置,确定如图中规划位置点A到规划位置点E所示的曲线。显然,规划位置点E超过了参考位置点C,则在基于参考位置点B和参考位置点C之间的各参考位置的曲率,确定规划路径时,由于规划位置点E到与其同时刻的参考位置点B的距离较远,导致规划出的与参考位置点C同时刻的规划位置点F,在规划位置点E的后方,无人驾驶设备需要反向行驶才能到达规划位置点F,也就是说,根据参考位置点B到参考位置C之间的各时刻的参考位置的曲率,以及障碍物的位置,确定如图中规划位置点E到规划位置点F所示的曲线。则确定出规划位置点F后,该无人驾驶设备可首先根据参考位置点C到参考位置D之间的各时刻的参考位置的曲率,以及障碍物的位置,确定如图中规划位置点F到规划位置点G所示的曲线。则确定出规划位置点G后,该无人驾驶设备可根据参考位置D后的参考路径 中各参考位置对应的曲率、障碍物的位置等,以G点为起点进行路径规划,确定G点之后的曲线,并将确定出的A点到E点所示的曲线、E点到F点的曲线、F点到G点的曲线以及G点之后的曲线拼接起来,作为无人驾驶设备的规划路径。
显然,根据图1,可确定无人驾驶设备在根据规划路径行驶时,在规划位置E到规划位置F的过程中,需要经过刹车、倒退的情况,存在较大安全隐患。且上述规划出的路径不满足相关技术进行路径规划的第二条原则,可能会导致出现无人驾驶设备无法正常行驶的情况。基于此,如何基于无人驾驶设备的规划路径进行调整,确定无人驾驶设备行驶的路径,是一个亟需解决的问题。基于此,本公开提供一种新的无人驾驶设备路径规划方法,使得可基于根据参考路径和障碍物位置规划出的路径,重新对无人驾驶设备进行路径规划。
以下结合附图,详细说明本公开各实施例提供的技术方案。
图2为本公开提供的无人驾驶设备的路径规划方法的流程示意图,包括以下步骤:
S100:获取参考路径中各参考位置的属性信息,以及无人驾驶设备的规划路径中各规划位置的属性信息,所述属性信息至少包括:时刻、所述无人驾驶设备的速度方向以及速度大小。
为了保证无人驾驶设备的行驶顺利,需要对无人驾驶设备进行路径规划,其中,这里提到的无人驾驶设备可以是指无人车、机器人、自动配送设备等能够实现自动驾驶的设备。基于此,本公开提供的无人驾驶设备的路径规划方法可应用于使用无人驾驶设备进行配送的领域,如,使用无人驾驶设备进行快递、物流、外卖等配送的业务场景。而为了保证无人驾驶设备能够在这些业务场景中顺利行进,需要保证无人驾驶设备路径规划的准确性与安全性。
在本公开提供的一个或多个实施例中,对无人驾驶设备进行路径规划的执行主体可以是无人驾驶设备自身,也可以是服务提供方的服务器,即,服务提供方的服务器可以通过无人驾驶设备上传的数据,对无人驾驶设备进行路径规划。而为了便于描述,下面将仅以无人驾驶设备为执行主体,对本公开提供的无人驾驶设备路径规划的方法进行说明。
示例性的,该无人驾驶设备中可预存有高精地图,于是,该无人驾驶设备可根据预存的高精地图,确定无人驾驶设备所在车道的车道中心线,并将该车道线作为无人驾驶设备的参考路径,则该无人驾驶设备可基于自身当前速度大小和速度方向,以及参考路径的曲率,确定各参考位置的属性信息。其中,针对每个参考位置,该参考位置的属性信息包括:该参考位置对应的时刻、参考路径在该参考位置处的曲率、无人驾驶设备在该参考位置处的速度大小以及速度方向。车道中心线为车道的中心位置组成的曲线。
然后,该无人驾驶设备可获取由采集设备采集到的图像数据或点云数据,作为环境数据,并对环境数据进行识别,确定无人驾驶设备周围的障碍物的位置。
最后,该无人驾驶设备可根据确定出的障碍物的位置,以及确定出的参考路径中的各参考位置的属性信息,确定各时刻对应的规划位置的属性信息,各规划位置可确定出无人驾驶设备的规划路径。其中,与参考位置的属性信息类似,针对每个规划位置,该规划位置的属性信息包括:该规划位置对应的时刻、无人驾驶设备在该规划位置处的速度大小以及速度方向。
需要说明的是,本公开中采用何种方法确定参考路径和规划路径可根据需要进行设置,本公开对此不做限制。
S102:根据所述规划路径的方向,依次判断各规划位置的速度方向是否与其时刻相同的参考位置的速度方向相反,若是,将速度方向相反的规划位置作为校准规划位置。
在本公开提供的一个或多个实施例中,如前所述的,当参考路径的曲率较大时,确定出的规划路径可能会出现路径中的子路径的路径方向与参考路径相反(如,图1中的规划路径),导致存在安全隐患的情况。因此,该无人驾驶设备可从规划路径中,确定出规划路径中路径方向与参考路径相反的规划位置,对该子路径进行调整,即可确定路径方向与参考路径方向 相同的规划路径。
而物体移动的方向,一般取决于物体的速度方向,也就是说,规划路径的路径方向和参考路径的路径方向,取决于该路径中无人驾驶设备的速度方向。于是,可基于无人驾驶设备在初始规划路径中的速度方向,以及对应时刻在参考路径中的速度方向,确定校准规划位置。
示例性的,该无人驾驶设备可根据该规划路径的方向,依次确定各规划位置及其时刻相同的参考位置在笛卡尔坐标系的速度,并确定各规划位置的速度及其时刻相同的参考位置的速度的乘积,并基于乘积等,判断该规划位置的速度与该参考位置的速度是否相同。以及当确定出规划位置的速度方向与其时刻相同的参考位置的速度方向相反时,确定该规划位置为校准规划位置。当该规划位置的速度方向与其时刻相同的参考位置的速度方向相同时,该无人驾驶设备可根据该排序,确定下一规划位置的速度,以及下一参考位置的速度,进而判断下一规划位置的速度方向与其时刻相同的参考位置的速度方向是否相反。
另外,由于无人驾驶设备在进行路径规划时,往往是根据参考路径和距离参考路径的距离,构建弗莱涅尔(Frenet)坐标系,进而在弗莱涅尔坐标系中进行路径规划的。且参考路径和规划路径在笛卡尔坐标系中的表达式,往往不容易确定出,因此,可采用根据规划位置的曲率,以及规划位置和与规划位置时刻相同的参考位置之间的距离,确定该规划位置的速度及其时刻相同的参考位置的速度是否相同。
示例性的,假设参考路径为L(x,y)(s),且参考路径连续,于是,该参考路径满足
其中,s表示参考路径的长度,x,y都是s的函数,针对每个时刻,假设该时刻在参考路径中对应的参考位置的笛卡尔坐标为(x
0,y
0),则该点对应的速度为V
0=(x′
0,y′
0),V
0为该参考位置对应的速度,x′
0和y′
0分别为该参考位置的速度在笛卡尔坐标系中的x轴的方向的速度分量和在y轴的速度分量。在已知以该参考路径和距离该参考路径的距离构建的弗莱涅尔坐标系中,该时刻对应的规划位置与该参考位置之间的距离为l的情况下,令初始参考轨迹为l(s),则根据弗莱涅尔坐标系转笛卡尔坐标系的公式:
为参考路径在参考位置处的法向量,可确定该规划位置在笛卡尔坐标系中的坐标为l(x
1,y
1)(s)=(x
0,y
0)(s)+l*(-y′
0,x′
0)(s)=(x
0-ly′
0,y
0+lx′
0),显然,(-y′
0,x′
0)*(x′
0,y′
0)=0,(-y′
0,x′
0)为参考路径在参考位置处的向量。于是,可确定规划位置对应的速度为V
1=(x′
1,y′
1)=(x′
0-ly″
0,y′
0+lx″
0),则根据规划位置对应的速度和参考位置对应的速度的乘积,即可确定规划位置的速度与参考位置对应的速度是否同向,于是,可确定V
0*V
1=(x′
0,y′
0)(x′
1,y′
1)=(x′
0,y′
0)(x′
0-ly″
0,y′
0+lx″
0),又因为参考路径满足
则可确定
又‖cosθ,sinθ‖=1,则x′
0≡cosθ,y′
0≡sinθ即,x′
0等价于cosθ,y′
0等价于sinθ,则对‖cosθ,sinθ‖求导,可确定
于是,可确定V
1=(x′
0-klx′
0,y′
0-kly′
0),
而想要确定规划位置与参考位置的速度反向的点,使V
0*V
1<0即可,则可确定当且仅当1-kl<0时,规划位置与参考位置对应的速度反向。
于是,该无人驾驶设备可首先针对每个规划位置,确定该规划位置同时刻的参考位置的曲率k,作为参考曲率,以及该规划位置距离与其同时刻的参考位置的距离l,作为参考距离。
然后,根据该规划路径的方向,依次针对每个规划位置,判断该规划位置的参考曲率,与该规划位置的参考距离的乘积是否大于1,即,判断该规划位置对应的kl>1是否成立。
最后,若成立,则该无人驾驶设备可确定该规划位置的速度方向与时刻相同的参考位置的速度方向相反。若不成立,则该无人驾驶设备可确定该规划位置的速度方向与时刻相同的参考位置的速度方向相同,则无人驾驶设备可继续判断该规划路径后续规划位置的速度方向与其时刻相同的参考位置的速度方向是否相同,直至对各规划位置均进行判断为止。其中,规划位置的属性信息中还包括规划位置与其对应的参考位置之间的距离,以及该参考位置的曲率。
当然,若上述未确定出校准规划位置,即,该规划路径中不存在与其相同时刻的参考位置的速度方向相反的规划位置,则可认为该规划路径准确,该无人驾驶设备可控制自身沿着该规划路径行驶。
当然,该无人驾驶设备可沿着该规划路径的方向,依次确定各规划位置的参考曲率以及参考距离,并当确定出速度方向与其时刻相同的参考位置的速度方向相反的规划位置后,不再确定后续规划位置的参考曲率以及参考距离。
需要说明的是,上述速度反向,为两速度夹角大于90度,即,针对任一速度,将该速度沿着另一速度方向和垂直于另一速度方向的方向分解,确定出的沿着另一速度方向的分量为负值,即可确定这两个速度方向是反向的。同样的,速度同向,为两速度夹角小于90度,即,针对任一速度,将该速度沿着另一速度方向和垂直于另一速度方向的方向分解,确定出的沿着另一速度方向的分量为正值,即可确定这两个速度方向是同向的。
S104:根据所述参考路径中距离所述校准规划位置最近的点,在所述参考路径中确定校准参考位置,并根据所述参考路径中所述校准参考位置后的参考路径,规划以所述校准规划位置为起点的校准路径。
在本公开提供的一个或多个实施例中,在确定出校准规划位置后,该无人驾驶设备可对规划路径中该校准规划位置后的规划路径进行调整,而对规划路径中校准规划位置后的路径进行调整,最简单的办法为重新确定该校准规划位置对应的参考位置,作为校准参考位置,并根据重新确定出的校准参考位置后的参考路径,以该校准规划位置为起点进行规划。
示例性的,该无人驾驶设备可首先确定该校准规划位置与参考路径中各点的距离。然后,根据确定出的各距离,从各参考位置中,确定与该校准规划位置距离最近的点。最后,根据确定出的与该校准规划位置距离最近的点,从参考路径中该点后的路径中,随机确定某点,作为该校准规划位置对应的校准参考位置。其中,该校准参考位置为参考路径中,不落后于与校准规划位置距离最近的点的位置。“落后于”是指沿着参考路径的方向,校准参考位置在与校准规划位置距离最近的点之前。
另外,由于无人驾驶设备在行驶过程中,往往会在弗莱涅尔坐标系中,控制无人驾驶设备行驶,因此,该无人驾驶设备还可在弗莱涅尔坐标系中,确定校准参考位置。
示例性的,该无人驾驶设备可根据参考路径和与参考路径之间的距离构建弗莱涅尔坐标系,然后将该校准规划位置进行投影,确定该校准规划位置在弗莱涅尔坐标系中的参考位置,并将该参考位置作为校准参考位置,以及确定该校准规划位置距离校准参考位置的距离。如图3所示。
图3为本公开提供的确定校准参考位置的示意图,实线a代表参考路径,虚线b代表障碍物,实线c代表规划路径,圆点A为校准规划位置,圆点B为与圆点A相同时刻的参考位置,将该校准规划位置进行投影,可确定圆点C为该校准规划位置在该弗莱涅尔坐标系中的参考位置,则该无人驾驶设备可将圆点C作为该校准规划位置对应的校准参考位置,其中,箭头方向为路径方向。
在确定出校准参考位置后,该无人驾驶设备即可根据该参考路径中该校准参考位置后的校准路径,以该校准规划位置为起点,进行路径规划,确定以该校准规划位置为起点的校准路径。
示例性的,该无人驾驶设备可根据该参考路径中该校准参考位置后的参考路径中,各参考位置对应的属性信息,以该校准规划位置为起点,重新确定各规划位置的属性信息,并将重新确定出的各规划位置进行连接,得到以该校准规划位置为起点的校准路径。当然,由于无人驾驶设备通常为在弗莱涅尔坐标系中控制自身行驶,因此,该无人驾驶设备可在弗莱涅尔坐标系中,根据各参考位置的曲率,该校准规划位置和校准参考位置的距离,重新确定各规划位置的曲率,以及各规划位置及其对应的参考位置的距离,并将重新确定出的各规划位置进行连接,得到以该校准规划位置为起点的校准路径。其中,参考路径中该校准参考位置后的参考路径中的各参考位置,也可为以该校准参考位置为起点,沿着该参考路径,重新确定出的。也就是说,该无人驾驶设备可以该校准参考位置为起点,重新确定各时刻对应的参考位置,并针对每个时刻的参考位置,根据该时刻的参考位置的属性信息,确定该时刻对应的规划位置的属性信息,进而根据各时刻对应的规划位置,确定以该校准规划位置为起点的校准路径。
当然,该无人驾驶设备在进行路径规划时,还可根据该无人驾驶设备感知到的周围环境中的障碍物位置,对该路径进行规划,根据参考路径、校准参考位置、校准规划位置以及障碍物的位置等进行路径规划,本公开对于如何进行路径规划的方式不做限制,本公开对于如何确定校准路径的过程不再赘述,对于采用的算法也不做限制,可根据需要设置。
另外,由于校准规划位置的速度方向与参考路径的速度方向相反,因此,仅根据该校准规划位置对应的校准参考位置,确定校准路径,确定出的规划路径可能存在无人驾驶设备的速度突变,导致无人驾驶设备失控的情况,于是,为了避免上述问题,该无人驾驶设备可利用圆弧的平稳过渡的特性,进行路径规划。
示例性的,该无人驾驶设备可从该校准规划位置的速度方向的法线方向上确定圆心,该圆心与该校准规划位置的距离为无人驾驶设备的最小转弯半径,则确定出圆心后,该无人驾驶设备可以该最小转弯半径为半径,确定该校准规划位置对应的校准圆,并以该校准规划位置为起点,以该校准圆与该校准规划位置和校准参考位置的连线的另一交点为终点,确定该校准规划位置对应的校准圆弧,作为第一校准路径。在确定出第一校准路径,该无人驾驶设备可以该第一校准路径的终点为起点,根据该参考路径中校准参考位置后的路径,进行路径规划,确定第二校准路径。如图4a和图4b所示。
图4a为本公开提供的确定第一校准路径的示意图,图中,实线a为无人驾驶设备的参考路径,实线b和实线c组合成该无人驾驶设备的规划路径,其中,实线b为规划路径中校准规划位置前的规划路径,实线c为规划路径中校准规划位置后的规划路径,D点为校准规划位置,Q点为校准参考位置,V
1为D点的速度,则V
1的方向为D点的速度方向,V
2的方向为D点的速度方向的法线方向。于是,该无人驾驶设备在V
2方向上,确定与点D的距离为预设的无人驾驶设备的最小转弯半径的位置,作为圆心O,进而确定校准圆,并确定该校准圆与校准规划位置和校准参考位置的连接线上的另一交点E,则可确定该点E为第一校准路径的终点,且根据圆的特征,该无人驾驶设备可规划得到沿着Q点速度方向的速度分量与D点的速度沿着Q点速度方向的速度分量等大且反向的E点,且确定出的该第一校准路径是连续的。其中,箭头方向为路径方向。于是,该无人驾驶设备可确定出校准路径,如图4b所示。
图4b为本公开提供的确定校准路径的示意图,与图4a类似,实线a为无人驾驶设备的参考路径,实线b为规划路径中校准规划位置前的规划路径,D点为校准规划位置,Q点为校准参考位置,E点为第一校准路径的终点,实线d为第一校准路径,于是,该无人驾驶设备可以该第一校准路径的终点点E为起点,根据该参考路径点Q后的路径,确定第二校准路径e。于是,该无人驾驶设备可确定校准路径为第一校准路径d和第二校准路径e组成。也就是说,实线d和实线e组成了该无人驾驶设备的校准路径。其中,箭头方向为路径方向。
当然,上述确定出的E点,其速度沿着Q点速度方向的速度分量与D点的速度沿着Q 点速度方向的速度分量反向即可。
S106:根据所述规划路径中所述校准规划位置前的规划路径,以及所述校准路径,确定规划路径,并控制所述无人驾驶设备沿着所述规划路径行驶。
在本公开提供的一个或多个实施例中,在确定出校准路径后,该无人驾驶设备可将规划路径中该校准规划位置前的路径,以及确定出的校准路径进行拼接,得到该无人驾驶设备的规划路径,如图5所示。
图5为本公开提供的确定规划路径的示意图,图中,实线a为参考路径,虚线b为障碍物,实线c和实线d组成规划路径,实线e为校准路径,其中,实线c为规划路径中校准规划位置前的路径,实线d为规划路径中校准规划位置后的路径,圆点A为校准规划位置,圆点B为与圆点A相同时刻的参考位置,则该无人驾驶设备可确定实线c和实线e组成的路径为无人驾驶设备的规划路径,箭头方向为路径方向。
进一步的,如前所述的,该无人驾驶设备还可确定校准圆弧和校正路径,则该无人驾驶设备还可将规划路径中该校准规划位置前的路径,确定出的第一校准路径以及第二校准路径进行拼接,得到该无人驾驶设备的规划路径。以图4b为例,显然,规划路径为实线b、实线d、实线e组成的路径。
在确定出规划路径后,该无人驾驶设备可控制自身沿着该规划路径行驶。控制方式可为基于运动策略模型确定,该无人驾驶设备可将该规划路径作为输入,输入到该运动策略模型中,得到相应的运动策略,则该无人驾驶设备可基于确定出的运动策略,控制无人驾驶设备行驶。
当然,也可为该无人驾驶设备根据自身当前速度、规划路径中各规划位置的曲率、速度等,确定出自身的运动策略,并根据该运动策略控制自身行驶。
另外,由于原始的规划路径中的校准规划位置的速度方向与其同时刻的参考位置的速度方向相反,而规划路径中的校准规划位置前的各规划位置的速度方向与其同时刻的参考位置的速度方向相同。显然,无人驾驶设备在从起点到达校准规划位置的过程中,经历了减速过程,而无人驾驶设备在沿着重新规划出的规划路径行驶时,并不需要如原来的规划路径中的减速操作。因此,该无人驾驶设备可首先确定与校准规划位置同时刻的参考位置,作为更新点,然后根据该更新点之前的参考路径中的各参考位置的属性信息、该校准规划位置之前的参考路径以及校准路径中至少部分规划位置的属性信息(如,校准路径中前五个时刻对应的规划位置),将该校准规划位置前的规划路径中的各规划位置的属性信息进行更新,以保证无人驾驶设备沿着重新确定出的规划路径行驶时,相邻时刻的速度变化量不超过预设的变化阈值,保证无人驾驶设备平稳行驶。如,根据图5中B点之前的实线a中各参考位置的属性信息,实线c以及实线e中的部分规划位置的属性信息,重新确定实线e中各规划位置的属性信息。
当然,该无人驾驶设备还可仅根据部分该更新点之前的参考路径中的各参考位置的属性信息,将该校准规划位置前的规划路径中的各规划位置的属性信息进行更新。以图5为例,该无人驾驶设备可基于实线a中,B点至B点前五个时刻的参考位置的属性信息,确定实线c中,A点至A点前五个时刻的规划位置的属性信息,以保证无人车在A点处平稳行驶。
进一步的,在规划路径已重新确定出的情况下,该无人驾驶设备还可根据确定出的该规划路径中各规划位置的曲率、时刻等属性信息,确定各规划位置对应的速度,并根据确定出的各规划位置对应的速度,对重新确定出的规划路径中的各规划位置的属性信息进行更新。
当然,在上述确定各规划位置对应的速度的同时,该无人驾驶设备还可重新确定各规划位置对应的时刻,以使得无人驾驶设备沿着规划路径行驶时,尽可能使无人驾驶设备处于平稳行驶的状态,提高无人驾驶设备的利用率。
基于图2的无人驾驶设备的路径规划方法,通过沿着规划路径的方向,依次判断各规划 位置的速度方向是否与其时刻相同的参考位置的速度方向相反,确定位于规划路径的各规划位置中,速度方向与其对应的参考位置的速度方向相反的校准规划位置,并根据参考路径中与该校准规划位置距离最近的点,确定校准参考位置,并根据参考路径中该校准参考位置后的路径,以该校准规划位置为起点,进行路径规划,确定校准路径,并基于规划路径和校准路径,确定无人驾驶设备行驶的规划路径。本方法在参考路径对应的曲率较大时,规划出的规划路径中,不会出现无人驾驶设备急停、倒退等情况,提高了无人驾驶设备的路径规划的效率和安全性。
另外,依次确定各规划位置的速度方向与其相同时刻的参考位置的速度方向是否相反,可能需要较长时间,而无人驾驶设备的运动策略等需要实时确定,因此,在步骤S102中,该无人驾驶设备可确定规划路径中各规划位置的速度方向及其相同时刻的参考位置的速度方向相反的规划位置,再根据各规划位置的时刻,确定校准规划位置。
示例性的,该无人驾驶设备可确定各时刻对应的规划位置及其对应的参考位置分别在笛卡尔坐标系中的坐标,并确定参考位置对应的速度和规划位置对应的速度,以及通过参考位置对应的速度和规划位置对应的速度的乘积,判断该参考位置的速度与该规划位置的速度是否相同。并在确定出速度方向与其对应的参考位置的速度方向相反的规划位置后,将其作为各待校准规划位置,则该无人驾驶设备可沿着该规划路径的方向,将各待校准规划位置进行排序,并从各待校准规划位置组成的待校准规划路径中,随机选择某点,作为校准规划位置。当然,优选地,该无人驾驶设备可按照时间顺序,选择最先的待校准规划位置,作为校准规划位置,以保证无人驾驶设备沿着重新确定出的校准路径行驶时,不存在安全隐患。
当然,由于规划路径的方向即为时间先后顺序,因此,在确定校准规划位置时,该无人驾驶设备还可根据时间先后顺序,以及各校准规划位置对应的时刻,将各待校准规划位置进行排序,并根据确定出的排序,随机选择某校准规划位置,或确定时刻最先的待校准规划位置,作为校准规划位置。
进一步的,在确定规划路径时,为了保证规划出的路径的即时性和准确性,该无人驾驶设备可根据预设的规划时长,如,每隔十秒,对无人驾驶设备进行一次路径规划,于是,在步骤S100中,该无人驾驶设备被以当前时刻进行路径规划时,可获取过去的规划时长内的无人驾驶设备的运动策略等,并基于无人驾驶设备的历史时刻对应的运动策略,确定无人驾驶设备的规划路径。
更进一步,本公开中的路径规划的方法,也可为每隔预设的规划时长,重新将无人驾驶设备未来的运动轨迹进行规划。
另外,在确定出校准规划位置对应的校准参考位置后,若该校准规划位置的速度方向与该校准参考位置的速度方向同向,显然,该无人驾驶设备可根据该校准规划位置的速度继续行驶,而当该校准规划位置的速度方向与该校准参考位置的速度方向反向时,在该校准规划位置,无人驾驶设备的速度方向或突然变化,因此,该无人驾驶设备可基于该比较准规划位置和校准参考位置的速度方向,进行路径规划。
示例性的,该无人驾驶可首先判断校准参考位置的速度方向与校准规划位置的速度方向是否反向,其中,该判断是否反向的方法可参考上述步骤S102中的方法。
当校准参考位置的速度方向与校准规划位置的速度方向相反时,该无人驾驶设备可根据校准规划位置,确定第一校准路径,并根据第一校准路径,确定第二校准路径,以及根据规划路径中校准规划位置前的路径、第一校准路径以及第二校准路径,重新确定规划路径。
当校准参考位置的速度方向与校准规划位置的速度方向相同时,该无人驾驶设备可根据该校准规划位置以及该校准规划位置对应的速度及速度方向,确定校准路径,并根据校准路径,以及规划路径中校准规划位置前的路径,重新确定规划路径。
另外,为了使得确定出的校准路径尽量与参考路径之间的距离更近,则该无人驾驶设备 还可基于校准规划位置对应的校准圆O,确定校准参考位置,进而确定规划路径。如图6a和图6b所示。
图6a为本公开提供的确定校准规划位置的示意图,与图4a类似,实线a为无人驾驶设备的参考路径,实线b和实线c组合成该无人驾驶设备的规划路径,其中,实线b为规划路径中校准规划位置前的路径,实线c为规划路径中校准规划位置后的路径,D点为校准规划位置,Z点是参考路径中距离D点最近的点,V
1为D点的速度,则V
1的方向为D点的速度方向,V
2的方向为D点的速度方向的法线方向。于是,该无人驾驶设备在V
2方向上,确定与点D的距离为预设的无人驾驶设备的最小转弯半径的位置,作为圆心O,进而确定校准圆,并确定距离该校准圆上,距离参考路径最近的点E,作为第一校准路径的终点,以及确定参考路径上,距离该校准圆最近的点Q,作为校准参考位置。显然,校准参考位置Q不落后于距离校准规划位置最近的点Z。其中,箭头方向为路径方向。于是,该无人驾驶设备可基于校准规划位置点D,校准参考位置点Q,确定规划路径,如图6b所示。
图6b为本公开提供的确定无人驾驶设备的规划路径的示意图。与图6a类似,实线a为无人驾驶设备的参考路径,实线b为规划路径中校准规划位置前的路径,D点为校准规划位置,Q点为校准参考位置,E点为第一校准路径的终点,则该无人驾驶设备可以该第一校准路径的终点点E为起点,根据该参考路径点Q后的路径,确定第二校准路径e。于是,该无人驾驶设备可确定规划路径为规划路径中校准规划位置前的路径b、第一校准路径d以及第二校准路径e组成。也就是说,实线b、实线d和实线e组成了该无人驾驶设备的规划路径。其中,箭头方向为路径方向。
进一步的,无人驾驶设备在行驶过程中,还可能因为超车等策略,导致无人驾驶设备所在车道出现变化,但确定出的参考路径在无人驾驶设备执行超车策略时,不应发生变化。因此,该无人驾驶设备可根据无人驾驶设备各历史时刻所在位置,无人驾驶设备执行的策略等,确定参考路径。如图7所示。
图7为本公开提供的确定无人驾驶设备的参考路径的示意图,图中,实线a、虚线b、虚线c、实线d为车道线,虚线b和虚线c表征了各车道为同向的,白色长方体表示无人驾驶设备,灰色长方体表示其他车辆,点横线e为由无人驾驶设备各历史时刻所在位置,以及无人驾驶设备的运动策略等确定出的无人驾驶设备的历史时刻和未来时刻的运动轨迹,于是,可确定无人驾驶设备的参考路径为实线f,即,虚线c和实线d之间的车道的车道中心线,为无人驾驶设备的参考路径。其中,箭头方向为路径方向,即,无人驾驶设备的行驶方向。
更进一步的,无人驾驶设备行驶过程中,往往会因为执行的策略而变换车道,而无人驾驶设备的参考路径应为一条连续曲线,因此,该无人驾驶设备可确定同向的车道组成一条总车道,并确定总车道的车道中心线为参考路径。如,令实线a和实线d之间的各车道组成一条总车道,并确定该总车道的车道中心线为参考路径,即,虚线b和虚线c之间的车道的车道中心线为该无人驾驶设备的参考路径。当然,若同向的各车道的车道数为偶数,则可确定中间的车道线为参考路径。如,假设虚线b和虚线c之间的车道和虚线c和虚线d之间的车道为同向,则可确定虚线c为参考路径。
另外,为了进一步保证参考路径为连续曲线,该无人驾驶设备还可基于无人驾驶设备行驶过程中的各策略,以及预存的高精地图,进行路径规划,确定出在不存在障碍物因素的影响下,无人驾驶设备可行驶的轨迹,作为该无人驾驶设备的参考路径。如图8所示。
图8为本公开提供的确定无人驾驶设备的参考路径和规划路径的示意图。与图7类似,图8中的实线a、虚线b、虚线c、实线d为车道线,虚线b和虚线c表征了各车道为同向,且图8中无人驾驶设备需执行策略为行驶至左侧第一条车道并沿着该车道继续行驶,则该无人驾驶设备可根据预存的高精地图和无人驾驶设备执行的运动策略,进行路径规划,确定无人驾驶设备的参考路径,即,实线g,在确定出无人驾驶设备的参考路径后,该无人驾驶设 备可根据目标物识别确定出的障碍物(如,图中A部分),以及参考路径,进行路径规划,确定该无人驾驶设备的规划路径,即,虚线h,其中,箭头方向为路径方向,即,无人驾驶设备的行驶方向。而本公开提供的路径规划方法即是对于规划出的虚线h进行调整,以使无人驾驶设备根据规划路径行驶时,不会出现反向行驶的情况。
进一步的,在确定参考路径时,为了避免出现预存的高精地图不足以描述无人驾驶设备周围的车道线,进而无法确定出准确的参考路径的情况,在步骤S100中,该无人驾驶设备还可对无人驾驶设备的环境数据进行识别,确定参考路径。
示例性的,该无人驾驶设备可首先获取无人驾驶设备采集到的图像。其中,该图像可由预先安装在无人驾驶设备中的采集设备获取。该采集设备可包括单目相机、双目相机等图像采集设备。当然,该无人驾驶设备还可获取无人驾驶设备采集到的点云数据,则该采集设备可包括激光雷达等采集设备。
其次,该无人驾驶设备可对获取到的图像进行目标物识别,确定图像中车道线的位置和各障碍物的位置,继而根据车道线的位置确定无人驾驶设备所在车道的车道中心线的位置。其中,该无人驾驶设备在确定车道线的位置时,还可对获取到的点云数据进行目标物识别,确定图像中车道线的位置。
然后,该无人驾驶设备可将确定出的无人驾驶设备所在车道的车道中心线的位置,作为该无人驾驶设备的参考路径。
最后,该无人驾驶设备可基于确定出的参考路径,以及对图像进行目标物识别确定出的各障碍物的位置,进行路径规划,将规划得到的路径作为无人驾驶设备的规划路径。
本公开还提供了一种无人驾驶设备的路径规划方法,参见图9,该方法包括如下的S900-S906。
S900,获取参考路径中各参考位置的属性信息,以及无人驾驶设备的规划路径中各规划位置的属性信息,属性信息至少包括:时刻、路径曲率、无人驾驶设备的速度方向以及速度大小。其中,S900的实现方式可参见上文S100中的说明,此处不再赘述。
S902,根据规划路径的方向,依次判断各规划位置的速度方向是否与其时刻相同的参考位置的速度方向相反,若是,将速度方向相反的规划位置作为校准规划位置。其中,S902的实现方式可参见上文S102中的说明,此处不再赘述。
S904,在参考路径中确定校准参考位置,并根据参考路径中校准参考位置后的参考路径,规划以校准规划位置为起点的校准路径。其中,S904中根据参考路径中校准参考位置后的参考路径,规划以校准规划位置为起点的校准路径,可参见上文S904中的说明,此处不再进行赘述。而对于S904中的在参考路径中确定校准参考位置的方式,包括但不限于如下三种。
方式一,从参考路径中位于距离校准规划位置最近的点之后的路径中,随机确定一点作为校准参考位置。方式一可参见上文S104中的说明,此处不再赘述。
方式二,对校准规划位置进行投影,得到校准规划位置在弗莱涅尔坐标系中的参考位置,将校准规划位置在弗莱涅尔坐标系中的参考位置作为校准参考位置。方式二可参见上文图3对应的说明,此处不再赘述。
方式三,确定校准圆,将参考路径上距离校准圆最近的点作为校准参考位置,校准圆的圆心在校准规划位置的速度方向的法线方向上,圆心与校准规划位置的距离为预设的无人驾驶设备的最小转弯半径。方式三可参见上文图6a和图6b对应的说明,此处不再赘述。
S906,根据规划路径中校准规划位置前的规划路径,以及校准路径,重新确定规划路径,并控制无人驾驶设备沿着规划路径行驶。其中,S906的实现方式可参见上文S106中的说明,此处不再赘述。
以上为本公开的一个或多个实施例提供的无人驾驶设备的路径规划方法,本公开还提供了相应的无人驾驶设备的路径规划装置。
图10为本公开提供的无人驾驶设备的路径规划装置示意图,包括:
获取模块200,用于获取参考路径中各参考位置的属性信息,以及无人驾驶设备的规划路径中各规划位置的属性信息,所述属性信息至少包括:时刻、所述无人驾驶设备的速度方向以及速度大小。
确定模块202,用于根据所述规划路径的方向,依次判断各规划位置的速度方向是否与其时刻相同的参考位置的速度方向相反,若是,将速度方向相反的规划位置作为校准规划位置。
校准模块204,用于根据所述参考路径中距离所述校准规划位置最近的点,在所述参考路径中确定校准参考位置,并根据所述参考路径中所述校准参考位置后的参考路径,规划以所述校准规划位置为起点的校准路径。
规划模块206,用于根据所述规划路径中所述校准规划位置前的规划路径,以及所述校准路径,重新确定规划路径,并控制所述无人驾驶设备沿着所述规划路径行驶。
在一些实施方式中,所述校准模块204,用于在所述校准规划位置的速度方向的法线方向上,确定与所述校准规划位置的距离为预设的所述无人驾驶设备的最小转弯半径处为圆心,以所述最小转弯半径为半径,以所述校准规划位置为起点,确定第一校准路径,所述第一校准路径的终点位于所述校准规划位置和所述校准参考位置的连线上;以所述第一校准路径的终点为起点,根据所述参考路径中校准参考位置后的参考路径,进行路径规划,确定第二校准路径,所述第一校准路径和所述第二校准路径组成校准路径。
在一些实施方式中,所述规划位置的属性信息中还包括所述规划位置与其对应的参考位置之间的距离,以及所述参考位置的曲率,所述确定模块202,用于针对每个规划位置,确定与该规划位置时刻相同的参考位置的曲率,作为该规划位置的参考曲率,以及确定该规划位置与所述时刻相同的参考位置之间的距离,作为该规划位置的参考距离,根据所述规划路径的方向,依次针对每个规划位置,判断该规划位置的参考曲率,与该规划位置的参考距离乘积是否大于1,若是,则该规划位置的速度方向与其时刻相同的所述参考位置的速度方向相反,否则,继续判断所述规划路径后续规划位置的速度方向是否与其时刻相同的参考位置的速度方向相反,直至对各规划位置均进行判断为止。
在一些实施方式中,所述规划模块206,还用于当所述校准参考位置的速度方向与所述校准规划位置的速度方向相反时,根据所述校准规划位置,确定第一校准路径,根据所述第一校准路径的终点,确定所述第二校准路径,并根据所述第一校准路径,所述第二校准路径,以及所述规划路径中所述校准规划位置前的规划路径,重新确定规划路径,当所述校准参考位置的速度方向与所述校准规划位置的速度方向相同时,根据所述校准规划位置,确定校准路径,并根据所述校准路径,以及所述规划路径中所述校准规划位置前的规划路径,重新确定规划路径。
在一些实施方式中,所述确定模块202,用于针对每个规划位置,判断该规划位置的速度方向是否与其同时刻的参考位置的速度方向相反,若是,将该规划位置作为待校准规划位置,根据所述规划路径的方向,将各待校准规划位置进行排序,并根据所述排序,确定校准规划位置。
在一些实施方式中,所述校准模块204,用于以所述校准参考位置为起点,重新确定各时刻对应的参考位置,针对每个时刻的参考位置,根据该时刻的参考位置的属性信息,确定该时刻对应的规划位置的属性信息,根据各时刻对应的规划位置,确定以所述校准规划位置为起点的校准路径。
在一些实施方式中,所述规划模块206,还用于根据与所述校准规划位置同时刻的参考位置之前的参考路径中各参考位置的属性信息、所述校准规划位置之前的规划路径以及所述校准路径中至少部分规划位置的属性信息,更新所述规划路径中所述校准规划位置前的规划 路径中各规划位置的属性信息。
图11为本公开提供的另一种无人驾驶设备的路径规划装置示意图,包括:
获取模块1100,用于获取参考路径中各参考位置的属性信息,以及无人驾驶设备的规划路径中各规划位置的属性信息,属性信息至少包括:时刻、无人驾驶设备的速度方向以及速度大小。
确定模块1102,用于根据规划路径的方向,依次判断各规划位置的速度方向是否与其时刻相同的参考位置的速度方向相反,若是,将速度方向相反的规划位置作为校准规划位置。
校准模块1104,用于在参考路径中确定校准参考位置,并根据参考路径中校准参考位置后的参考路径,规划以校准规划位置为起点的校准路径。
规划模块1106,用于根据规划路径中校准规划位置前的规划路径,以及校准路径,重新确定规划路径,并控制无人驾驶设备沿着规划路径行驶。
在一些实施方式中,校准模块1104,用于从参考路径中位于距离校准规划位置最近的点之后的路径中,随机确定一点作为校准参考位置;或者,对校准规划位置进行投影,得到校准规划位置在弗莱涅尔坐标系中的参考位置,将校准规划位置在弗莱涅尔坐标系中的参考位置作为校准参考位置;或者,确定校准圆,将参考路径上距离校准圆最近的点作为校准参考位置,校准圆的圆心在校准规划位置的速度方向的法线方向上,圆心与校准规划位置的距离为预设的无人驾驶设备的最小转弯半径。
本公开还提供了一种计算机可读存储介质,该存储介质存储有计算机程序,计算机程序可用于执行上述图2提供的无人驾驶设备的路径规划方法,还可用于执行图9提供的无人驾驶设备的路径规划方法。
本公开还提供了图12所示的无人驾驶设备的示意结构图。如图12所述,在硬件层面,该电子设备包括处理器、内部总线、网络接口、内存以及非易失性存储器,当然还可能包括其他业务所需要的硬件。处理器从非易失性存储器中读取对应的计算机程序到内存中然后运行,以实现上述图2所述的无人驾驶设备的路径规划方法,或者实现上述图9所示的无人驾驶设备的路径规划方法。当然,除了软件实现方式之外,本公开并不排除其他实现方式,比如逻辑器件抑或软硬件结合的方式等等,也就是说以下处理流程的执行主体并不限定于各个逻辑单元,也可以是硬件或逻辑器件。
在20世纪90年代,对于一个技术的改进可以很明显地区分是硬件上的改进(例如,对二极管、晶体管、开关等电路结构的改进)还是软件上的改进(对于方法流程的改进)。然而,随着技术的发展,当今的很多方法流程的改进已经可以视为硬件电路结构的直接改进。设计人员几乎都通过将改进的方法流程编程到硬件电路中来得到相应的硬件电路结构。因此,不能说一个方法流程的改进就不能用硬件实体模块来实现。例如,可编程逻辑器件(Programmable Logic Device,PLD)(例如现场可编程门阵列(Field Programmable Gate Array,FPGA))就是这样一种集成电路,其逻辑功能由用户对器件编程来确定。由设计人员自行编程来把一个数字系统“集成”在一片PLD上,而不需要请芯片制造厂商来设计和制作专用的集成电路芯片。而且,如今,取代手工地制作集成电路芯片,这种编程也多半改用“逻辑编译器(logic compiler)”软件来实现,它与程序开发撰写时所用的软件编译器相类似,而要编译之前的原始代码也得用特定的编程语言来撰写,此称之为硬件描述语言(Hardware Description Language,HDL),而HDL也并非仅有一种,而是有许多种,如ABEL(Advanced Boolean Expression Language)、AHDL(Altera Hardware Description Language)、Confluence、CUPL(Cornell University Programming Language)、HDCal、JHDL(Java Hardware Description Language)、Lava、Lola、MyHDL、PALASM、RHDL(Ruby Hardware Description Language)等,目前最普遍使用的是VHDL(Very-High-Speed Integrated Circuit Hardware Description Language)与Verilog。本领域技术人员也应该清楚,只需要将方法流程用上述几种硬件描述 语言稍作逻辑编程并编程到集成电路中,就可以很容易得到实现该逻辑方法流程的硬件电路。
控制器可以按任何适当的方式实现,例如,控制器可以采取例如微处理器或处理器以及存储可由该(微)处理器执行的计算机可读程序代码(例如软件或固件)的计算机可读介质、逻辑门、开关、专用集成电路(Application Specific Integrated Circuit,ASIC)、可编程逻辑控制器和嵌入微控制器的形式,控制器的例子包括但不限于以下微控制器:ARC 625D、Atmel AT91SAM、Microchip PIC18F26K20以及Silicone Labs C8051F320,存储器控制器还可以被实现为存储器的控制逻辑的一部分。本领域技术人员也知道,除了以纯计算机可读程序代码方式实现控制器以外,完全可以通过将方法步骤进行逻辑编程来使得控制器以逻辑门、开关、专用集成电路、可编程逻辑控制器和嵌入微控制器等的形式来实现相同功能。因此这种控制器可以被认为是一种硬件部件,而对其内包括的用于实现各种功能的装置也可以视为硬件部件内的结构。或者甚至,可以将用于实现各种功能的装置视为既可以是实现方法的软件模块又可以是硬件部件内的结构。
上述实施例阐明的系统、装置、模块或单元,可以由计算机芯片或实体实现,或者由具有某种功能的产品来实现。一种典型的实现设备为计算机。示例性的,计算机例如可以为个人计算机、膝上型计算机、蜂窝电话、相机电话、智能电话、个人数字助理、媒体播放器、导航设备、电子邮件设备、游戏控制台、平板计算机、可穿戴设备或者这些设备中的任何设备的组合。
为了描述的方便,描述以上装置时以功能分为各种单元分别描述。当然,在实施本公开时可以把各单元的功能在同一个或多个软件和/或硬件中实现。
本领域内的技术人员应明白,本公开的实施例可提供为方法、系统、或计算机程序产品。因此,本公开可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且,本公开可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本公开是参照根据本公开实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器,使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中,使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品,该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上,使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理,从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
在一个典型的配置中,计算设备包括一个或多个处理器(CPU)、输入/输出接口、网络接口和内存。
内存可能包括计算机可读介质中的非永久性存储器,随机存取存储器(RAM)和/或非易失性内存等形式,如只读存储器(ROM)或闪存(flash RAM)。内存是计算机可读介质的示例。
计算机可读介质包括永久性和非永久性、可移动和非可移动媒体可以由任何方法或技术来实现信息存储。信息可以是计算机可读指令、数据结构、程序的模块或其他数据。计算机 的存储介质的例子包括,但不限于相变内存(PRAM)、静态随机存取存储器(SRAM)、动态随机存取存储器(DRAM)、其他类型的随机存取存储器(RAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、快闪记忆体或其他内存技术、只读光盘只读存储器(CD-ROM)、数字多功能光盘(DVD)或其他光学存储、磁盒式磁带,磁带磁磁盘存储或其他磁性存储设备或任何其他非传输介质,可用于存储可以被计算设备访问的信息。按照本文中的界定,计算机可读介质不包括暂存电脑可读媒体(transitory media),如调制的数据信号和载波。
还需要说明的是,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、方法、商品或者设备不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种过程、方法、商品或者设备所固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括所述要素的过程、方法、商品或者设备中还存在另外的相同要素。
本领域技术人员应明白,本公开的实施例可提供为方法、系统或计算机程序产品。因此,本公开可采用完全硬件实施例、完全软件实施例或结合软件和硬件方面的实施例的形式。而且,本公开可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本公开可以在由计算机执行的计算机可执行指令的一般上下文中描述,例如程序模块。一般地,程序模块包括执行特定任务或实现特定抽象数据类型的例程、程序、对象、组件、数据结构等等。也可以在分布式计算环境中实践本公开,在这些分布式计算环境中,由通过通信网络而被连接的远程处理设备来执行任务。在分布式计算环境中,程序模块可以位于包括存储设备在内的本地和远程计算机存储介质中。
本公开中的各个实施例均采用递进的方式描述,各个实施例之间相同相似的部分互相参见即可,每个实施例重点说明的都是与其他实施例的不同之处。尤其,对于系统实施例而言,由于其基本相似于方法实施例,所以描述的比较简单,相关之处参见方法实施例的部分说明即可。
以上所述仅为本公开的实施例而已,并不用于限制本公开。对于本领域技术人员来说,本公开可以有各种更改和变化。凡在本公开的精神和原理之内所作的任何修改、等同替换、改进等,均应包含在本公开的权利要求范围之内。
Claims (21)
- 一种无人驾驶设备的路径规划方法,其中,所述方法包括:获取参考路径中各参考位置的属性信息,以及无人驾驶设备的规划路径中各规划位置的属性信息,所述属性信息至少包括:时刻、所述无人驾驶设备的速度方向以及速度大小;根据所述规划路径的方向,依次判断各规划位置的速度方向是否与其时刻相同的参考位置的速度方向相反,若是,将速度方向相反的规划位置作为校准规划位置;根据所述参考路径中距离所述校准规划位置最近的点,在所述参考路径中确定校准参考位置,并根据所述参考路径中所述校准参考位置后的参考路径,规划以所述校准规划位置为起点的校准路径;根据所述规划路径中所述校准规划位置前的规划路径,以及所述校准路径,重新确定规划路径,并控制所述无人驾驶设备沿着所述规划路径行驶。
- 如权利要求1所述的方法,其中,根据所述参考路径中所述校准参考位置后的参考路径,规划以所述校准规划位置为起点的校准路径,包括:在所述校准规划位置的速度方向的法线方向上,确定与所述校准规划位置的距离为预设的所述无人驾驶设备的最小转弯半径处为圆心,以所述最小转弯半径为半径,以所述校准规划位置为起点,确定第一校准路径,所述第一校准路径的终点位于所述校准规划位置和所述校准参考位置的连线上;以所述第一校准路径的终点为起点,根据所述参考路径中校准参考位置后的参考路径,进行路径规划,确定第二校准路径,所述第一校准路径和所述第二校准路径组成校准路径。
- 如权利要求1所述的方法,其中,所述规划位置的属性信息中还包括所述规划位置与其对应的参考位置之间的距离,以及所述参考位置的曲率;根据所述规划路径的方向,依次判断各规划位置的速度方向是否与其时刻相同的参考位置的速度方向相反,包括:针对每个规划位置,确定与该规划位置时刻相同的参考位置的曲率,作为该规划位置的参考曲率,以及确定该规划位置与所述时刻相同的参考位置之间的距离,作为该规划位置的参考距离;根据所述规划路径的方向,依次针对每个规划位置,判断该规划位置的参考曲率,与该规划位置的参考距离乘积是否大于1;若是,则该规划位置的速度方向与其时刻相同的所述参考位置的速度方向相反;否则,继续判断所述规划路径后续规划位置的速度方向是否与其时刻相同的参考位置的速度方向相反,直至对各规划位置均进行判断为止。
- 如权利要求2所述的方法,其中,所述方法还包括:当所述校准参考位置的速度方向与所述校准规划位置的速度方向相反时,根据所述校准规划位置,确定第一校准路径,根据所述第一校准路径的终点,确定所述第二校准路径,并根据所述第一校准路径,所述第二校准路径,以及所述规划路径中所述校准规划位置前的规划路径,重新确定规划路径;当所述校准参考位置的速度方向与所述校准规划位置的速度方向相同时,根据所述校准规划位置,确定校准路径,并根据所述校准路径,以及所述规划路径中所述校准规划位置前的规划路径,重新确定规划路径。
- 如权利要求1所述的方法,其中,根据所述规划路径的方向,依次判断各规划位置的速度方向是否与其时刻相同的参考位置的速度方向相反,若是,将速度方向相反的规划位置作为校准规划位置,包括:针对每个规划位置,判断该规划位置的速度方向是否与其同时刻的参考位置的速度方向 相反,若是,将该规划位置作为待校准规划位置;根据所述规划路径的方向,将各待校准规划位置进行排序,并根据所述排序,确定校准规划位置。
- 如权利要求1所述的方法,其中,根据所述参考路径中所述校准参考位置后的参考路径,规划以所述校准规划位置为起点的校准路径,包括:以所述校准参考位置为起点,重新确定各时刻对应的参考位置;针对每个时刻的参考位置,根据该时刻的参考位置的属性信息,确定该时刻对应的规划位置的属性信息;根据各时刻对应的规划位置,确定以所述校准规划位置为起点的校准路径。
- 如权利要求6所述的方法,其中,所述方法还包括:根据与所述校准规划位置同时刻的参考位置之前的参考路径中各参考位置的属性信息、所述校准规划位置之前的规划路径以及所述校准路径中至少部分规划位置的属性信息,更新所述校准规划位置前的规划路径中各规划位置的属性信息。
- 一种无人驾驶设备的路径规划方法,其中,所述方法包括:获取参考路径中各参考位置的属性信息,以及无人驾驶设备的规划路径中各规划位置的属性信息,所述属性信息至少包括:时刻、所述无人驾驶设备的速度方向以及速度大小;根据所述规划路径的方向,依次判断各规划位置的速度方向是否与其时刻相同的参考位置的速度方向相反,若是,将速度方向相反的规划位置作为校准规划位置;在所述参考路径中确定校准参考位置,根据所述参考路径中所述校准参考位置后的参考路径,规划以所述校准规划位置为起点的校准路径;根据所述规划路径中所述校准规划位置前的规划路径,以及所述校准路径,重新确定规划路径,并控制所述无人驾驶设备沿着所述规划路径行驶。
- 如权利要求8所述的方法,其中,在所述参考路径中确定校准参考位置,包括:从所述参考路径中位于距离所述校准规划位置最近的点之后的路径中,随机确定一点作为所述校准参考位置;或者,对所述校准规划位置进行投影,得到所述校准规划位置在弗莱涅尔坐标系中的参考位置,将所述校准规划位置在弗莱涅尔坐标系中的参考位置作为所述校准参考位置;或者,确定校准圆,将所述参考路径上距离所述校准圆最近的点作为所述校准参考位置,所述校准圆的圆心在所述校准规划位置的速度方向的法线方向上,所述圆心与所述校准规划位置的距离为预设的所述无人驾驶设备的最小转弯半径。
- 一种无人驾驶设备的路径规划装置,其中,所述装置包括:获取模块,用于获取参考路径中各参考位置的属性信息,以及无人驾驶设备的规划路径中各规划位置的属性信息,所述属性信息至少包括:时刻、所述无人驾驶设备的速度方向以及速度大小;确定模块,用于根据所述规划路径的方向,依次判断各规划位置的速度方向是否与其时刻相同的参考位置的速度方向相反,若是,将速度方向相反的规划位置作为校准规划位置;校准模块,用于根据所述参考路径中距离所述校准规划位置最近的点,在所述参考路径中确定校准参考位置,并根据所述参考路径中所述校准参考位置后的参考路径,规划以所述校准规划位置为起点的校准路径;规划模块,用于根据所述规划路径中所述校准规划位置前的规划路径,以及所述校准路径,重新确定规划路径,并控制所述无人驾驶设备沿着所述规划路径行驶。
- 如权利要求10所述的装置,其中,所述校准模块,用于在所述校准规划位置的速度方向的法线方向上,确定与所述校准规划位置的距离为预设的所述无人驾驶设备的最小转弯半径处为圆心,以所述最小转弯半径为半径,以所述校准规划位置为起点,确定第一校准路 径,所述第一校准路径的终点位于所述校准规划位置和所述校准参考位置的连线上;以所述第一校准路径的终点为起点,根据所述参考路径中校准参考位置后的参考路径,进行路径规划,确定第二校准路径,所述第一校准路径和所述第二校准路径组成校准路径。
- 如权利要求10所述的装置,其中,所述规划位置的属性信息中还包括所述规划位置与其对应的参考位置之间的距离,以及所述参考位置的曲率;所述确定模块,用于针对每个规划位置,确定与该规划位置时刻相同的参考位置的曲率,作为该规划位置的参考曲率,以及确定该规划位置与所述时刻相同的参考位置之间的距离,作为该规划位置的参考距离;根据所述规划路径的方向,依次针对每个规划位置,判断该规划位置的参考曲率,与该规划位置的参考距离乘积是否大于1;若是,则该规划位置的速度方向与其时刻相同的所述参考位置的速度方向相反;否则,继续判断所述规划路径后续规划位置的速度方向是否与其时刻相同的参考位置的速度方向相反,直至对各规划位置均进行判断为止。
- 如权利要求11所述的装置,其中,所述规划模块,还用于当所述校准参考位置的速度方向与所述校准规划位置的速度方向相反时,根据所述校准规划位置,确定第一校准路径,根据所述第一校准路径的终点,确定所述第二校准路径,并根据所述第一校准路径,所述第二校准路径,以及所述规划路径中所述校准规划位置前的规划路径,重新确定规划路径;当所述校准参考位置的速度方向与所述校准规划位置的速度方向相同时,根据所述校准规划位置,确定校准路径,并根据所述校准路径,以及所述规划路径中所述校准规划位置前的规划路径,重新确定规划路径。
- 如权利要求10所述的装置,其中,所述确定模块,用于针对每个规划位置,判断该规划位置的速度方向是否与其同时刻的参考位置的速度方向相反,若是,将该规划位置作为待校准规划位置;根据所述规划路径的方向,将各待校准规划位置进行排序,并根据所述排序,确定校准规划位置。
- 如权利要求10所述的装置,其中,所述校准模块,用于以所述校准参考位置为起点,重新确定各时刻对应的参考位置;针对每个时刻的参考位置,根据该时刻的参考位置的属性信息,确定该时刻对应的规划位置的属性信息;根据各时刻对应的规划位置,确定以所述校准规划位置为起点的校准路径。
- 如权利要求15所述的装置,其中,所述规划模块,还用于根据与所述校准规划位置同时刻的参考位置之前的参考路径中各参考位置的属性信息、所述校准规划位置之前的规划路径以及所述校准路径中至少部分规划位置的属性信息,更新所述规划路径中所述校准规划位置前的规划路径中各规划位置的属性信息。
- 一种无人驾驶设备的路径规划装置,其中,所述装置包括:获取模块,用于获取参考路径中各参考位置的属性信息,以及无人驾驶设备的规划路径中各规划位置的属性信息,所述属性信息至少包括:时刻、所述无人驾驶设备的速度方向以及速度大小;确定模块,用于根据所述规划路径的方向,依次判断各规划位置的速度方向是否与其时刻相同的参考位置的速度方向相反,若是,将速度方向相反的规划位置作为校准规划位置;校准模块,用于在所述参考路径中确定校准参考位置,并根据所述参考路径中所述校准参考位置后的参考路径,规划以所述校准规划位置为起点的校准路径;规划模块,用于根据所述规划路径中所述校准规划位置前的规划路径,以及所述校准路径,重新确定规划路径,并控制所述无人驾驶设备沿着所述规划路径行驶。
- 如权利要求17所述的装置,其中,所述校准模块,用于从所述参考路径中位于所述距离校准规划位置最近的点之后的路径中,随机确定一点作为所述校准参考位置;或者,对所述校准规划位置进行投影,得到所述校准规划位置在弗莱涅尔坐标系中的参考位置,将所 述校准规划位置在弗莱涅尔坐标系中的参考位置作为所述校准参考位置;或者,确定校准圆,将所述参考路径上距离所述校准圆最近的点作为所述校准参考位置,所述校准圆的圆心在所述校准规划位置的速度方向的法线方向上,所述圆心与所述校准规划位置的距离为预设的所述无人驾驶设备的最小转弯半径。
- 一种非临时性计算机可读存储介质,其中,所述非临时性计算机可读存储介质存储有计算机程序,所述计算机程序被处理器执行时实现上述权利要求1-9任一项所述的方法。
- 一种无人驾驶设备,包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序,其中,所述处理器执行所述程序时实现上述权利要求1-9任一项所述的方法。
- 一种计算机程序产品,其中,所述计算机程序产品包括计算机程序或指令,所述计算机程序或指令被处理器执行,以使计算机实现权利要求1-9任一项所述的方法。
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110888658.0A CN113340311B (zh) | 2021-08-04 | 2021-08-04 | 一种无人驾驶设备的路径规划方法及装置 |
CN202110888658.0 | 2021-08-04 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2023010877A1 true WO2023010877A1 (zh) | 2023-02-09 |
Family
ID=77480555
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2022/085562 WO2023010877A1 (zh) | 2021-08-04 | 2022-04-07 | 无人驾驶设备的路径规划 |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN113340311B (zh) |
WO (1) | WO2023010877A1 (zh) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113340311B (zh) * | 2021-08-04 | 2021-11-05 | 北京三快在线科技有限公司 | 一种无人驾驶设备的路径规划方法及装置 |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150153182A1 (en) * | 2013-02-07 | 2015-06-04 | Google Inc. | System and method for calibrating a navigation heading |
CN108248611A (zh) * | 2016-12-29 | 2018-07-06 | 华为技术有限公司 | 一种自动驾驶的方法、汽车控制设备、汽车及系统 |
CN111399523A (zh) * | 2020-06-02 | 2020-07-10 | 北京三快在线科技有限公司 | 一种路径规划的方法及装置 |
CN111665844A (zh) * | 2020-06-23 | 2020-09-15 | 北京三快在线科技有限公司 | 一种路径规划方法及装置 |
CN112955358A (zh) * | 2018-11-02 | 2021-06-11 | 祖克斯有限公司 | 轨迹生成 |
CN113074748A (zh) * | 2021-03-29 | 2021-07-06 | 北京三快在线科技有限公司 | 一种无人驾驶设备的路径规划方法及装置 |
CN113340311A (zh) * | 2021-08-04 | 2021-09-03 | 北京三快在线科技有限公司 | 一种无人驾驶设备的路径规划方法及装置 |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10948300B2 (en) * | 2018-12-27 | 2021-03-16 | Beijing Voyager Technology Co., Ltd. | Systems and methods for path determination |
-
2021
- 2021-08-04 CN CN202110888658.0A patent/CN113340311B/zh active Active
-
2022
- 2022-04-07 WO PCT/CN2022/085562 patent/WO2023010877A1/zh active Application Filing
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150153182A1 (en) * | 2013-02-07 | 2015-06-04 | Google Inc. | System and method for calibrating a navigation heading |
CN108248611A (zh) * | 2016-12-29 | 2018-07-06 | 华为技术有限公司 | 一种自动驾驶的方法、汽车控制设备、汽车及系统 |
CN112955358A (zh) * | 2018-11-02 | 2021-06-11 | 祖克斯有限公司 | 轨迹生成 |
CN111399523A (zh) * | 2020-06-02 | 2020-07-10 | 北京三快在线科技有限公司 | 一种路径规划的方法及装置 |
CN111665844A (zh) * | 2020-06-23 | 2020-09-15 | 北京三快在线科技有限公司 | 一种路径规划方法及装置 |
CN113074748A (zh) * | 2021-03-29 | 2021-07-06 | 北京三快在线科技有限公司 | 一种无人驾驶设备的路径规划方法及装置 |
CN113340311A (zh) * | 2021-08-04 | 2021-09-03 | 北京三快在线科技有限公司 | 一种无人驾驶设备的路径规划方法及装置 |
Also Published As
Publication number | Publication date |
---|---|
CN113340311B (zh) | 2021-11-05 |
CN113340311A (zh) | 2021-09-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10137896B2 (en) | Method and system for operating autonomous driving vehicles using graph-based lane change guide | |
US10459441B2 (en) | Method and system for operating autonomous driving vehicles based on motion plans | |
CN111665844B (zh) | 一种路径规划方法及装置 | |
WO2018179539A1 (en) | Method for controlling host vehicle and control system of host vehicle | |
CN112348293A (zh) | 一种障碍物的轨迹预测方法及装置 | |
CN111208838A (zh) | 一种无人驾驶设备的控制方法及装置 | |
US20240053163A1 (en) | Graphical user interface and user experience elements for head up display devices | |
CN111338360B (zh) | 一种规划车辆行驶状态的方法及装置 | |
CN111062372B (zh) | 一种预测障碍物轨迹的方法及装置 | |
CN113341941B (zh) | 一种无人驾驶设备的控制方法及装置 | |
CN113968243B (zh) | 一种障碍物轨迹预测方法、装置、设备及存储介质 | |
JP2023502834A (ja) | サンプル生成、ニューラルネットワーク訓練、データ処理の方法及び装置 | |
WO2022144010A1 (zh) | 无人驾驶设备的控制 | |
US20220314980A1 (en) | Obstacle tracking method, storage medium and unmanned driving device | |
WO2023010877A1 (zh) | 无人驾驶设备的路径规划 | |
WO2023115909A1 (zh) | 一种无人设备控制方法、装置、存储介质及电子设备 | |
CN116795105A (zh) | 一种车辆避障方法、装置及设备 | |
CN114148350B (zh) | 一种无人设备的控制方法及装置 | |
CN112987754B (zh) | 一种无人设备的控制方法、装置、存储介质及电子设备 | |
CN117095371A (zh) | 一种目标检测方法及检测装置 | |
CN116954209A (zh) | 一种模型训练方法、装置、存储介质及电子设备 | |
CN113848913A (zh) | 一种无人驾驶设备的控制方法及控制装置 | |
CN113074734B (zh) | 一种轨迹规划方法、装置、存储介质及电子设备 | |
CN113815651B (zh) | 一种无人设备控制方法、装置、设备及存储介质 | |
CN116841299B (zh) | 一种导览机器人的自主巡游控制方法及装置 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 22851601 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: 22851601 Country of ref document: EP Kind code of ref document: A1 |