CN112622924B

CN112622924B - Driving planning method and device and vehicle

Info

Publication number: CN112622924B
Application number: CN201910907005.5A
Authority: CN
Inventors: 于宁
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2019-09-24
Filing date: 2019-09-24
Publication date: 2023-06-09
Anticipated expiration: 2039-09-24
Also published as: CN112622924A

Abstract

The embodiment of the application discloses a driving planning method and device, a vehicle and a non-transient computer readable storage medium storing computer instructions, and belongs to the field of automatic driving. The driving planning method comprises the following steps: determining a global path of the vehicle on the journey based on the journey parameters and vehicle parameters; and adjusting the real-time speed of the vehicle and the planned track of the vehicle on the global path in the second time based on the global path and the feedback information of the motion control state of the vehicle in the first time. Thereby enabling speed and trajectory planning to more closely match the capabilities of the vehicle and to accommodate more and more complex scenarios.

Description

Driving planning method and device and vehicle

Technical Field

The embodiments of the present application relate to the field of automatic driving, and in particular, to a driving planning method and apparatus, a vehicle, and a non-transitory computer readable storage medium storing computer instructions.

Background

The automatic driving vehicle is used as a complex software and hardware combination system, and the safe and reliable operation of the automatic driving vehicle requires the cooperative work of a plurality of modules such as vehicle-mounted hardware, sensor integration, perception prediction, control planning and the like. The autopilot vehicle core software module comprises the following parts: software modules such as Perception (Prediction), routing (Routing), decision-making (Planning) and Control (Control), wherein Routing is used for global path-making, decision-making is used for real-time driving Planning, and the data flow between the modules is usually unidirectional. However, in the related art, the problem that the planning result does not conform to the capability of the vehicle and the problem that the planning result cannot adapt to more scenes cannot be avoided in the planning process of the global path and the real-time driving.

Disclosure of Invention

The application provides a driving planning method and device, a vehicle and a non-transitory computer readable storage medium storing computer instructions.

The embodiment of the application provides a driving planning method, which comprises the following steps:

determining a global path of the vehicle on the journey based on the journey parameters and vehicle parameters;

and adjusting the real-time speed of the vehicle and the planned track of the vehicle on the global path in the second time based on the global path and the feedback information of the motion control state of the vehicle in the first time.

Optionally, the determining the global path of the vehicle on the journey based on the journey parameter and the vehicle parameter includes:

determining an initial path of the trip consisting of at least one sub-path based on a start point of the trip, an end point of the trip, and map information;

determining a first sub-path from the at least one sub-path that does not conform to the relevant parameters of the vehicle;

selecting a second sub-path replacing the first sub-path based on the relevant parameters of the vehicle;

the global path is generated based on the second sub-path and other sub-paths of the initial path than the first sub-path.

Optionally, the method further comprises:

a motion control command for a first time is determined based on a real-time speed of the vehicle and a planned trajectory of the vehicle on the global path in the first time.

Optionally, the method further comprises:

and acquiring a control error between the motion control execution state of the vehicle and the motion control instruction in the first time, and taking the control error as feedback information of the motion control state of the vehicle in the first time.

Optionally, the relevant parameters of the vehicle include at least one of the following:

the vehicle profile parameters, the vehicle power parameters, the vehicle capacity level parameters.

The embodiment of the application provides a driving planning device, which comprises:

the route module is used for determining a global path of the vehicle on the journey based on the journey parameters and the vehicle parameters;

the decision planning module is used for adjusting the real-time speed of the vehicle and the planned track of the vehicle on the global path in the second time based on the global path and the feedback information of the motion control state of the vehicle in the first time; wherein the first time is earlier than the second time.

Optionally, the routing module is configured to determine an initial path of the trip, which is formed by at least one sub-path, based on a start point of the trip, an end point of the trip and map information, and determine a first sub-path that does not conform to relevant parameters of the vehicle from the at least one sub-path; selecting a second sub-path replacing the first sub-path based on the relevant parameters of the vehicle; the global path is generated based on the second sub-path and other sub-paths of the initial path than the first sub-path.

Optionally, the apparatus further includes:

the motion control module is used for determining motion control instructions of a first time based on the real-time speed of the vehicle and the planned track of the vehicle on the global path in the first time.

Optionally, the decision planning module is configured to obtain a control error between a motion control execution state of the vehicle and a motion control instruction in a first time, and use the control error as feedback information of the motion control state of the vehicle in the first time.

The embodiment of the application also provides a vehicle, which comprises:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein, the liquid crystal display device comprises a liquid crystal display device,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of the preceding claims.

The present application also provides a non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of the preceding claims.

The present application also provides a computer program product comprising a computer program which, when executed by a processor, implements a method as described above.

One embodiment of the above application has the following advantages or benefits: and adding relevant parameters of the vehicle when global path planning is performed, and taking feedback information of the motion control state of the first time into consideration to adjust the speed and the track planning of the second time. Therefore, the generated global path can be more in line with the capability of the vehicle by considering the related parameters of the vehicle, and the speed and the track planning can be more in line with the capability of the vehicle by combining the execution condition of the control instruction when the speed and the track planning are carried out, and can be suitable for more and more complex scenes.

Other effects of the above alternative will be described below in connection with specific embodiments.

Drawings

The drawings are for better understanding of the present solution and do not constitute a limitation of the present application. Wherein:

FIG. 1 is a schematic diagram of a driving planning method according to the present application;

FIG. 2 is a schematic illustration of a high-precision map and a generic electronic navigation map;

FIG. 3 is a schematic diagram of a trajectory planning of the present application;

FIG. 4 is a schematic diagram of an architecture between the various functions of the present application;

FIG. 5 is a schematic diagram of the structure of the driving planning apparatus of the present application;

FIG. 6 is a second schematic diagram of the structure of the driving planning apparatus of the present application;

fig. 7 is a block diagram of a vehicle for implementing a driving planning method of an embodiment of the present application.

Detailed Description

Exemplary embodiments of the present application are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present application to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

The application provides a driving planning method, as shown in fig. 1, comprising the following steps:

s101: determining a global path of the vehicle on the journey based on the journey parameters and vehicle parameters;

s102: based on the global path and feedback information of the motion control state of the vehicle in the first time, adjusting the real-time speed of the vehicle and the planned track of the vehicle on the global path in the second time; wherein the first time is earlier than the second time.

The method provided by the embodiment can be applied to an automatic driving vehicle. First, description will be made regarding control of an automatically driven vehicle: an autonomous vehicle may also be called an unmanned vehicle, in which a software and hardware combination system is provided, and safe and reliable operation of the system requires cooperative work of a plurality of modules, such as vehicle-mounted hardware, sensor integration, perception prediction, control planning, and the like.

The control functions of the autonomous vehicle may include:

and a sensing (permission) function, which is responsible for detecting and calculating objects and attributes of the surrounding environment from the sensor data.

And a Prediction (Prediction) function, which is responsible for processing the perception data and supplementing the motion trend and motion trail Prediction information of the obstacle.

The Routing function is used for searching a global traffic path on the map according to the starting point and the ending point of the vehicle, and the global traffic path is used as a global path planned in real time by the back-end absolute planning module.

Decision & Planning (Decision & Planning) functions are used to make behavioral decisions on the global path in combination with road boundaries, perceived obstacles, and vehicle kinematics rules, resulting in real-time trajectory and speed Planning.

And a Control function, which is responsible for following the planning result of the decision response strategy planning module, converting the track and speed planning into Control quantities such as throttle, brake, steering wheel angle and the like, and issuing the Control quantities to the vehicle through CANBus so as to drive the vehicle to drive according to the expected track and speed.

The routing function is used for generating a global path and sending the result to the downstream decision planning module, wherein in the related technology, the generation of the global path mainly depends on a vehicle starting point, a vehicle finishing point and a map, and the shortest path passable line is found out.

In the decision planning function, a behavior decision, a track planning result and a speed planning result are generated, and the track planning result and the speed planning result are unidirectionally transmitted to the motion control function at the rear end.

The embodiment is mainly aimed at the routing and decision planning and is adjusted to meet the requirements of complex scenes. In particular the number of the elements,

In the processing of the routing function, the relevant parameters of the vehicle are increased. Wherein the relevant parameters of the vehicle may include at least one of: the vehicle profile parameters, the vehicle power parameters, the vehicle capacity level parameters.

The profile parameters of the vehicle may include width, height, etc. of the vehicle; accordingly, some roads having a width smaller than the width of the vehicle and a passing height lower than the height of the vehicle may be excluded based on the profile parameters of the vehicle.

The power parameters of the vehicle may include a minimum turning radius of the vehicle, etc. Some roads having a turning radius smaller than the minimum turning radius of the vehicle may be excluded based on the power parameters of the vehicle.

The capability level parameter of the vehicle may be a composite index, for example, may include a hundred kilometer take over time or a hundred kilometer crash take over time of the vehicle. The hundred kilometers take over time can be understood as the time that the vehicle is converted into manual control in hundred kilometers running; the hundred kilometer collision takeover count is understood to be the count of only manual takeover made to avoid a safety collision. Or, the comprehensive indexes of the vehicle can also comprise hundred kilometer emergency brake times, hundred kilometer non-accident brake times, hundred kilometer positioning abnormal times, automatic driving system processing time delay and the like. In this embodiment, the number of times of taking over for hundred kilometers is mainly focused, and in general, the higher the capability level of a vehicle is, the higher the number of times of taking over for hundred kilometers is, and accordingly, the more complex scenes, for example, areas with more people flow, etc., can be adapted. The capability level parameters of the vehicle can be determined according to obstacle sensing technologies such as camera shooting, for example, if the obstacle sensing technology is poor, the capability level of the corresponding vehicle is low; in the case where the scene type is artificially divided, the division of the scene may include the specified area range in the scene, the corresponding scene type, the lowest capability of passing vehicles, and the like, and at this time, it may be determined whether or not the area range of the corresponding scene can be passed according to the capability of the vehicles.

Based on this, in S101, the determining the global path of the vehicle on the trip based on the trip parameter and the vehicle parameter includes the following various processing manners:

a mode one,

the global path is generated based on the second sub-path and other sub-paths in the initial path than the first sub-path.

In this way, a shortest path can be planned from the map information as an initial path according to the start point and the end point set by the user.

Dividing the initial path into a plurality of sub-paths; the division may be performed according to the same length, or may be performed at will, which is not limited herein.

Sequentially selecting sub-paths from the plurality of sub-paths, judging whether the width or the through height of the selected sub-paths is larger than the width of the vehicle and/or is higher than the height of the vehicle, and if not, taking the selected sub-paths as first sub-paths; it should be further understood that, at this time, whether the selected sub-path is to be the first sub-path may also be determined by determining whether the selected sub-path meets the capability level of the vehicle, for example, the sub-path is within an area of a scene that is manually divided, and the scene designates the lowest capability level of the passing vehicle, and when the capability of the vehicle is equal to or lower than the lowest capability level of the passing vehicle, the path may be determined to be the first sub-path;

Then the starting point and the end point of the first sub-path can be used as the starting point and the end point of the second sub-path, one path which can replace the first sub-path is selected, whether the selected path meets the requirements of relevant parameters of the vehicle is judged, if so, the path is used as the second sub-path, and the second sub-path replaces the first sub-path.

And the like, until the judgment and the processing of all sub-paths of the initial path are completed, the obtained path is the global path.

A second mode,

The method comprises the steps that firstly, all roads which do not meet the requirements of the relevant parameters of the vehicle in map information are removed based on the relevant parameters of the vehicle;

then, a global path is generated from the remaining roads included in the map information based on the start point and the end point.

Similarly, in the present embodiment, a road having a width smaller than the width of the vehicle may be deleted from the map information based on the height and/or width of the vehicle, and a road having a lower pass-through height than the height of the vehicle may be deleted. Roads that do not meet the capability level requirements of the vehicle may also be deleted from the map information based on the capability level parameters of the vehicle. It may also be determined whether to delete certain roads by the lowest capability level of the passing vehicle. It may also be determined whether the road is able to meet the power parameters of the vehicle, such as whether the turning radius of the curve is greater than the minimum turning radius of the vehicle, and if not, the portion of the road may be deleted.

Through the above processing, the processing for the global path is completed, and the difference between the processing and the prior art is that the related parameters of the vehicle are considered in the planning of the global path, so that the problem that the global path planned based on the shortest path principle only cannot meet the index of the vehicle is avoided.

Further, in the solution provided in this embodiment, the method further includes:

determining a motion control instruction for a first time based on a real-time speed of the vehicle and a planned trajectory of the vehicle on the global path in the first time;

wherein the motion control instructions include at least one of: a direction control command, an accelerator control command and a brake control command.

The first time and the second time in this embodiment can be understood as control frames for generating control instructions in each of the real-time path plans. That is, the generation of the motion control instruction may be periodic, and each period of generation of the motion control instruction may be understood as one frame as described above. The first time and the second time are adjacent two frames that generate motion control instructions.

Wherein the speed and trajectory planning may comprise:

Determining a length range to be planned based on the global path and the current position of the vehicle in the current frame; wherein, the length range can be understood as a length range starting from the current position of the vehicle in the global path;

a real-time speed of the vehicle over the length range and a planned trajectory of the vehicle on the global path are then determined.

The current frame may be the first time, that is, when the current frame is at the first time, the current vehicle position and the global path are combined to plan the real-time speed within the length range and plan the track.

The length range may be calculated based on a current speed of the vehicle and a preset duration. The preset duration can be determined according to actual conditions or current speed; for example, the preset duration may be preset to be fixed 10s; alternatively, a plurality of preset durations may be configured, and a shorter preset duration, such as 5s, may be used if the current speed is above a preset speed threshold, and a longer preset duration, such as 10s, may be used if the current speed is not above the preset speed threshold. In this way, the length of the part of the path that is currently planned can be determined.

Further, the speed of travel in the length range is determined, and trajectory planning is also possible. The track planning is performed, and whether an obstacle exists in the part of the path or not can be determined by combining the results of the sensing function and the prediction function, if the obstacle exists, the type of the obstacle is static or dynamic, and if the obstacle exists, a specific position needs to be determined for the static obstacle; in addition, if the obstacle is a dynamic obstacle, a prediction function is required to be combined to predict the movement trend and movement track of the dynamic obstacle.

It should be noted that, the map information in this embodiment may be a high-precision map, and in an automatic driving vehicle, a complex automatic driving task is completed mainly by loading the high-precision map. The difference between the high-precision map and the common navigation electronic map is as follows:

from the perspective of users, the main differences between the high-precision map and the traditional electronic map are: the user of the high-precision map is an automatic driving system, and the user of the traditional electronic map is a human driver.

Referring to fig. 2, a conventional general navigation electronic map (left side in the drawing) depicts a road, a part of the road distinguishes lanes, and a high-precision map (right side in the drawing) not only depicts a road, but also accurately depicts a plurality of lanes on a road, and truly reflects the actual pattern of the lanes.

The traditional electronic map can not fully display the details of the lane shape, but the high-precision map can fully conform to the real lane in order to enable an automatic driving system to better recognize traffic conditions, so that a driving scheme is made in advance, the details of the lane shape can be displayed in detail and accurately, and the places of the lane shape are widened and narrowed.

As shown in fig. 2, in the high-precision map, the map includes a plurality of lanes, for example, lanes (Lane) 1-10. At least one Lane may form a road, for example, lanes (Lane) 1, 2, 3 may form a road, lanes (Lane) 4, 5, 6, 7 may form another road, and other components are similar and will not be described again. It should be understood that fig. 2 is only an example, and more expression elements such as road shoulders, traffic lights, etc. may be present in the actual high-precision map, which is not exhaustive in this embodiment.

The high-precision map can contain driving reference lines of all lanes; correspondingly, in this embodiment, when generating the track plan, a driving reference line corresponding to the lane capable of avoiding the static obstacle and the dynamic obstacle in the length range may be selected, and finally, a track planning result is formed.

In performing trajectory planning, one example may be: and constructing a driving reference line based on discrete points of the lane center line in a high-precision map loaded in the automatic driving vehicle, and then carrying out track planning and speed planning according to the driving reference line. The result of the trajectory planning may be a trajectory curve. The track curve is composed of a series of track points, wherein the information corresponding to each track point can comprise position coordinates formed by x, y and z, coordinates of the position coordinates represented by s and l under the Frenet coordinate system after the position coordinates are converted, and related information such as speed, acceleration, curvature, navigation angle, relative time and the like, which are not exhaustive.

For example, the resulting speed plan may include the speeds to be reached at the specified locations; the track planning can be shown in fig. 3, which shows a section of track planning result in a certain length, and it can be seen that the section of track planning is passing through lane 2-lane 5-lane 8.

Determining a motion control instruction can be that determining a position in the length range where braking and accelerator control are required according to a speed planning result, and determining a braking amount or an accelerator amount at the corresponding position; and determining the position where the steering wheel is required to be controlled to turn in the length range and the steering wheel turning and angle at the corresponding positions according to the result of the track planning, so as to generate control instructions aiming at the brake, the throttle and the steering wheel.

Further, in the embodiment S102, the method for acquiring the feedback information of the motion control state of the vehicle may be: acquiring a control error between a motion control state of the vehicle and a motion control instruction in a first time, and taking the control error as feedback information of the motion control state of the vehicle in the first time;

wherein the feedback information of the motion control state includes at least one of:

control errors of directions, control errors of an accelerator and control errors of a brake.

Further, when the vehicle is controlled, whether a PID or MPC algorithm is adopted, more or less control errors may exist, so that the vehicle enters an unexpected position or a vehicle state, and further, the follow-up planning fails; or the control function cannot be normally executed according to the planning result given by the decision-making planning, or even if the control function transmits the planning solution to the vehicle controller, the vehicle cannot be completely executed according to the planning result due to the vehicle dynamics limitation. The scheme needs to be correspondingly adjusted based on the control error.

Specifically, during the first time, when the vehicle executes the control command, the downstream control function determines that the corresponding control cannot be performed or the corresponding planning result cannot be performed, for example, the steering and the angle of the steering wheel cannot be matched or only the steering with a smaller angle cannot be performed at a certain speed, and then the control error of the direction between the motion control execution state and the control command during the first time can be obtained. Accordingly, feedback information of the motion control state is determined according to the control error of the first time, then the speed of the corresponding length range in the second time and the trajectory plan are adjusted based on the control error of the direction of the first time, at this time, the start point of the length range can be advanced to the current position of the vehicle when in the second time, then the corresponding trajectory plan of the second time can be determined based on the control error of the direction of the first time, and the speed at the different position can be determined based on the redetermined trajectory plan in the second time to redetermine the speed plan of the second time. The manner of redetermining the trajectory plan and the speed plan is the same as that described above, and will not be described here again.

For example, under a certain steering angle, the throttle cannot execute a corresponding control command, but only can steer under a smaller throttle amount, and at this time, the control error of the throttle between the motion control execution state and the control command in the first time can be obtained. Correspondingly, after the control error is acquired, the speed and the track planning of the length range are adjusted again based on the control error of the throttle in a second time, at this time, the starting point of the length range can be advanced to the current position of the vehicle in the second time, then the speed planning can be readjusted based on the control error of the throttle, for example, the corresponding speed at different positions can be reduced, so that the adjusted speed can meet the control requirement of the throttle in the second time; when determining the track planning of the second time, a new track can be determined to be reselected by combining the control error of the throttle, so that the result of the new track planning in the second time can meet the capability of the throttle. The control error of the brake and the corresponding adjustment mode in the second time can be processed in the same way, but the braking quantity corresponding to the speed reduction can be adjusted by combining the control error of the brake at the position where the speed reduction is determined.

It should be further understood that the following adjustment manners for the three control errors are described above, and the speed and the path planning can be adjusted by combining the three control errors when the method is actually applied.

In another case, after the control command is issued in the first time, the vehicle cannot execute certain planning at a preset moment, for example, the speed cannot reach a preset speed planning, or an error exists between the position and the preset position, at this moment, the situation that the vehicle enters an unexpected position or a vehicle state due to at least one of a control error of a direction, a control error of an accelerator and a control error of a brake when the vehicle is actually executed can be further determined, and the situation that the vehicle enters the unexpected position or the vehicle state is further analyzed; and then combining the adjustment modes to carry out the speed and track planning adjustment of the second time.

It should be noted that the adjustment of the speed and trajectory planning may be performed in real time or periodically, for example, once every 1 s; that is, the first time may be 1s, and the second time may be 2s.

In an example, the system framework of fig. 4 is illustrated, and the positioning, map function, sensing and prediction functions in fig. 4 are the same as those described above, and are not repeated here; the routing and decision planning in fig. 4 is described in detail as follows: when the routing function generates a global path, relevant parameters of the vehicle are increased; and when the decision-making planning is carried out on the frame, the feedback information (namely the control error) of the motion control state of the previous frame is added, then the speed and the track planning of the frame are adjusted based on the feedback information of the previous frame, and the speed and the track planning result after the adjustment of the frame are sent to the motion control function.

Therefore, the scheme provided by the application can increase the relevant parameters of the vehicle when the global path planning is performed, and the feedback information of the motion control state of the first time is considered to adjust the speed and the track planning of the second time. Therefore, the generated global path can be more in line with the capability of the vehicle by considering the related parameters of the vehicle, and the speed and the track planning can be more in line with the capability of the vehicle by combining the execution condition of the control instruction when the speed and the track planning are carried out, and can be suitable for more and more complex scenes.

As shown in fig. 5, the present application provides a driving planning apparatus, including:

a routing module 301, configured to determine a global path of the vehicle on the trip based on a parameter of the trip and a parameter of the vehicle;

the decision planning module 302 is configured to adjust the real-time speed of the vehicle and the planned track of the vehicle on the global path in the second time based on the global path and feedback information of the motion control state of the vehicle in the first time; wherein the first time is earlier than the second time.

The device provided by the embodiment can be arranged in an automatic driving vehicle. First, description will be made regarding control of an automatically driven vehicle: an autonomous vehicle may also be called an unmanned vehicle, in which a software and hardware combination system is provided, and safe and reliable operation of the system requires cooperative work of a plurality of modules, such as vehicle-mounted hardware, sensor integration, perception prediction, control planning, and the like.

As shown in fig. 6, the driving planning apparatus for an automatic driving vehicle may specifically include:

and a Perception module for detecting and calculating the object and the attribute of the surrounding environment from the sensor data.

And a Prediction (Prediction) module, which is responsible for processing the perception data and supplementing the motion trend and motion trail Prediction information of the obstacle.

The Routing module 301 is configured to search a global traffic path on a map according to a start point and an end point of a vehicle, and use the global traffic path as a global path planned in real time by the back-end block planning module.

The Decision-making (Planning) module 302 is configured to make behavior decisions on the global path in combination with road boundaries, perceived obstacles, and vehicle kinematics rules, so as to obtain a real-time trajectory and speed plan.

A Control (Control) module 303, responsible for following the planning result of the decision response strategy planning module, converting the track and speed plan into Control quantities such as throttle, brake, steering wheel angle and the like, and issuing the Control quantities to the vehicle through CANBus to drive the vehicle to run according to the expected track and speed.

The present embodiment is mainly directed to the foregoing routing module 301 and decision planning module 302 for processing, so as to more adapt to the requirements of complex scenarios. In particular the number of the elements,

relevant parameters of the vehicle are added in the processing of the routing module 301. Wherein the relevant parameters of the vehicle may include at least one of: the vehicle profile parameters, the vehicle power parameters, the vehicle capacity level parameters. The relevant parameters of the vehicle may be preset in the routing module.

The capability level parameter of the vehicle may be a comprehensive index, for example, the capability level parameter may include the number of times the vehicle takes over for hundred kilometers, that is, the number of times the vehicle is converted into manual control during travel for hundred kilometers. Generally, the higher the capability level of a vehicle, the higher the number of times of taking over for hundred kilometers, and correspondingly, the more complex scenes, such as areas with more people, etc., can be adapted. The capability level parameters of the vehicle can be determined according to obstacle sensing technologies such as camera shooting, for example, if the obstacle sensing technology is poor, the capability level of the corresponding vehicle is low; in the case where the scene type is artificially divided, the division of the scene may include the specified area range in the scene, the corresponding scene type, the lowest capability of passing vehicles, and the like, and at this time, it may be determined whether or not the area range of the corresponding scene can be passed according to the capability of the vehicles.

Based on this, the routing module 301 may include various processes as follows:

A mode one,

Determining an initial path of the journey constituted by at least one sub-path based on a start point of the journey, an end point of the journey and map information, determining a first sub-path from the at least one sub-path that does not conform to relevant parameters of the vehicle; selecting a second sub-path replacing the first sub-path based on the relevant parameters of the vehicle; the global path is generated based on the second sub-path and other sub-paths of the initial path than the first sub-path.

A second mode,

the motion control module 303 is configured to determine a motion control instruction at a first time based on a real-time speed of the vehicle and a planned trajectory of the vehicle on the global path at the first time.

Making speed and trajectory planning with respect to decision planning module 302 may include:

determining a length range to be planned based on the global path and the current position of the vehicle; wherein the length range may be understood as a length range starting from the current position of the vehicle in the global path; the speed and trajectory planning of the vehicle traveling in real time in the partial path is then determined.

Further, the decision-making module 302 obtains a control error between the motion control execution state of the vehicle and the motion control command in the first time, and uses the control error as feedback information of the motion control state of the vehicle in the first time;

Specifically, when the control command of the first time is executed in the first time, the downstream control function determines that the corresponding control cannot be performed or the corresponding planning result cannot be performed, for example, the steering and the angle of the steering wheel cannot be matched or only the steering of a smaller angle can be performed at a certain speed, and then the control error of the direction between the motion control execution state and the control command can be obtained. Accordingly, after the control error is obtained, the decision-making module 302 adjusts the speed and the trajectory plan of the length range corresponding to the second time based on the control error of the direction again, at this time, the start point of the length range may be advanced to the current position of the vehicle, then the corresponding trajectory plan in the second time may be determined based on the control error of the direction, and the speed at the different position may be determined based on the determined trajectory plan to determine the speed plan again. The manner of redetermining the trajectory plan and the speed plan is the same as that described above, and will not be described here again.

For example, under a certain steering angle, the throttle cannot execute a corresponding control command, but only can steer under a smaller throttle amount, and at this time, the control error of the throttle between the motion control execution state and the control command can be obtained. Correspondingly, after the control error of the first time is acquired, the decision-making planning module 302 adjusts the speed and the track plan of the length range based on the control error of the accelerator in the second time again, at this time, the starting point of the length range can be advanced to the corresponding position of the vehicle in the second time, and then the speed plan of the second time can be readjusted based on the control error of the accelerator, for example, the corresponding speed at different positions can be reduced, so that the adjusted speed can meet the control requirement of the accelerator; when determining the track planning, a new track of the second time can be determined to be reselected by combining the control error of the throttle, so that the result of the new track planning can meet the capacity of the throttle. The control error of the brake and the corresponding adjustment mode can be processed in the same way, and the braking quantity corresponding to the speed reduction can be adjusted by combining the control error of the brake only at the position where the speed reduction is required.

In another case, after the control command is issued at the first time, the vehicle cannot execute certain plans, for example, the speed cannot reach the preset speed plan or the position and the preset position have errors, at this time, the situation that the vehicle enters an unexpected position or a vehicle state due to at least one of the control error of the direction, the control error of the accelerator and the control error of the brake when the vehicle is actually executed can be further determined, and the situation that the vehicle enters the unexpected position or the vehicle state is further analyzed; and then carrying out subsequent speed and track planning adjustment on the second time by combining the adjustment mode.

It should be noted that the adjustment of the speed and trajectory planning may be performed in real time or periodically, for example, once every 1 s.

Therefore, the scheme provided by the application can increase the relevant parameters of the vehicle when the global path planning is performed, and the feedback information of the motion control state of the first time is considered to adjust the speed and the track planning of the second time. Therefore, the generated global path can be more in line with the capability of the vehicle by considering the related parameters of the vehicle, and the speed and track planning can be more in line with the capability of the vehicle by combining the execution condition of the control instruction of the previous frame when the speed and track planning is carried out, and can be suitable for more and more complex scenes.

According to embodiments of the present application, there is also provided a vehicle, a readable storage medium, and a computer program product.

As shown in fig. 7, is a block diagram of a vehicle according to a driving planning method that performs an embodiment of the present application. Vehicles are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The vehicle may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the application described and/or claimed herein.

As shown in fig. 7, the vehicle includes: one or more processors 401, memory 402, and interfaces for connecting the components, including a high-speed interface and a low-speed interface. The various components are interconnected using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions executing within the vehicle, including instructions stored in or on memory to display graphical information of a graphical user interface (Graphical User Interface, GUI) on an external input/output device, such as a display apparatus coupled to the interface. In other embodiments, multiple processors and/or multiple buses may be used, if desired, along with multiple memories and multiple memories. Also, multiple vehicles may be connected, with each device providing a portion of the necessary operations (e.g., as a server array, a set of blade servers, or a multiprocessor system). In fig. 7, a processor 401 is taken as an example, and further, the processor in fig. 7 may be provided with each functional module of the driving planning apparatus.

Memory 402 is a non-transitory computer-readable storage medium provided herein. Wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to perform the driving planning method provided herein. The non-transitory computer readable storage medium of the present application stores computer instructions for causing a computer to execute the driving planning method provided by the present application.

The memory 402 is used as a non-transitory computer readable storage medium for storing non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/modules corresponding to the driving planning method in the embodiments of the present application. The processor 401 executes various functional applications of the server and data processing, i.e., implements the driving planning method in the above-described method embodiment, by running non-transitory software programs, instructions, and modules stored in the memory 402.

Memory 402 may include a storage program area that may store an operating system, at least one application program required for functionality, and a storage data area; the storage data area may store data created from the use of the vehicle planned for driving, etc. In addition, memory 402 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory 402 may optionally include memory remotely located with respect to processor 401, which may be connected to the drive-planned vehicle via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The vehicle that executes the driving planning method of the present embodiment may further include: an input device 403 and an output device 404. The processor 401, memory 402, input device 403, and output device 404 may be connected by a bus or otherwise, for example in fig. 7.

The input device 403 may receive input numeric or character information and generate key signal inputs related to user settings and function control of the vehicle being planned for driving, such as a touch screen, keypad, mouse, trackpad, touchpad, pointer stick, one or more mouse buttons, trackball, joystick, etc. input devices. The output device 404 may include a display apparatus, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibration motors), among others. The display device may include, but is not limited to, a liquid crystal display (Liquid Crystal Display, LCD), a light emitting diode (Light Emitting Diode, LED) display, and a plasma display. In some implementations, the display device may be a touch screen.

Various implementations of the systems and techniques described here can be implemented in digital electronic circuitry, integrated circuitry, application specific integrated circuits (Application Specific Integrated Circuits, ASIC), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

These computing programs (also referred to as programs, software applications, or code) include machine instructions for a programmable processor, and may be implemented in a high-level procedural and/or object-oriented programming language, and/or in assembly/machine language. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, programmable logic devices (programmable logic device, PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., CRT (Cathode Ray Tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local area network (Local Area Network, LAN), wide area network (Wide Area Network, WAN) and the internet.

The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

According to the technical scheme of the embodiment of the application, a part of images with larger similarity are filtered out when the images are stored, so that redundant images are filtered out when the images are stored, storage and transmission pressure is reduced, and the workload of subsequent sorting is also saved.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present application may be performed in parallel, sequentially, or in a different order, provided that the desired results of the technical solutions disclosed in the present application can be achieved, and are not limited herein.

The above embodiments do not limit the scope of the application. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application are intended to be included within the scope of the present application.

Claims

1. A driving planning method, comprising:

determining a global path of the vehicle on the journey based on the acquired journey parameters and relevant parameters of the vehicle;

Based on the global path and feedback information of the motion control state of the vehicle in the first time, adjusting the real-time speed of the vehicle and the planned track of the vehicle on the global path in the second time; wherein the first time is earlier than the second time; the relevant parameters of the vehicle are associated with the capability of the vehicle, including the power parameters of the vehicle and the capability level parameters of the vehicle; the capability level parameter of the vehicle is used for representing the adaptability of the vehicle to the complex environment and the capability of the vehicle for sensing obstacles, and is related to the classified scene types, wherein the classified scene types comprise the lowest capability of passing vehicles;

the determining the global path of the vehicle on the journey based on the journey parameters and the related parameters of the vehicle comprises:

Generating the global path based on the second sub-path and other sub-paths in the initial path except the first sub-path;

the method further comprises the steps of:

acquiring a control error between a motion control state of the vehicle and a motion control instruction in a first time, and taking the control error as feedback information of the motion control state of the vehicle in the first time, wherein the feedback information of the motion control state comprises at least one of the following: control errors of directions, control errors of an accelerator and control errors of a brake;

the adjusting the real-time speed of the vehicle and the planned track of the vehicle on the global path in the second time based on the feedback information of the global path and the motion control state of the vehicle in the first time comprises the following steps:

and adjusting the starting point of the length range corresponding to the second time to the current position of the vehicle in the second time based on the global path and the feedback information of the motion control state of the first time, determining a track plan corresponding to the second time based on the feedback information of the motion control state, and determining the speed at different positions based on the redetermined track plan to redetermine the speed plan of the second time.

2. The method according to claim 1, wherein the method further comprises:

3. A driving planning apparatus, the apparatus comprising:

the route module is used for determining a global path of the vehicle on the journey based on the acquired journey parameters and the relevant parameters of the vehicle;

the decision planning module is used for adjusting the real-time speed of the vehicle and the planned track of the vehicle on the global path in the second time based on the feedback information of the global path and the motion control state of the vehicle in the first time; wherein the first time is earlier than the second time; the relevant parameters of the vehicle are associated with the capability of the vehicle, including the power parameters of the vehicle and the capability level parameters of the vehicle; the capability level parameter of the vehicle is used for representing the adaptability of the vehicle to the complex environment and the capability of the vehicle for sensing obstacles, and is related to the classified scene types, wherein the classified scene types comprise the lowest capability of passing vehicles;

The routing module is used for determining an initial path of the journey formed by at least one sub-path based on the starting point of the journey, the ending point of the journey and map information, and determining a first sub-path which does not accord with the relevant parameters of the vehicle from the at least one sub-path; selecting a second sub-path replacing the first sub-path based on the relevant parameters of the vehicle; generating the global path based on the second sub-path and other sub-paths except the first sub-path in the initial path;

the decision planning module is configured to obtain a control error between a motion control execution state and a motion control instruction of the vehicle in a first time, and take the control error as feedback information of the motion control state of the vehicle in the first time, where the feedback information of the motion control state includes at least one of the following: control errors of directions, control errors of an accelerator and control errors of a brake;

and adjusting the start point of the length range corresponding to the second time to the current position of the vehicle in the second time based on the feedback information of the global path and the motion control state of the first time, determining a track plan corresponding to the second time based on the feedback information of the motion control state, and determining the speed at different positions based on the re-determined track plan to re-determine the speed plan of the second time.

4. A device according to claim 3, characterized in that the device further comprises:

5. A vehicle, characterized by comprising:

at least one processor; and

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-2.

6. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-2.

7. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any of claims 1-2.