CN114812585A

CN114812585A - Path planning method and device

Info

Publication number: CN114812585A
Application number: CN202110115030.7A
Authority: CN
Inventors: 朱正达; 张磊; 冉旭; 王睿
Original assignee: Momenta Suzhou Technology Co Ltd
Current assignee: Momenta Suzhou Technology Co Ltd
Priority date: 2021-01-27
Filing date: 2021-01-27
Publication date: 2022-07-29
Also published as: WO2022160634A1

Abstract

The embodiment of the invention discloses a path planning method and a device, wherein the method comprises the following steps: obtaining relevant information of a current decision-making plan corresponding to a target object; determining a reachable state set corresponding to a target object based on the current state of a preset layered state machine, the jump relation among the states, the current decision planning related information and a preset driving limiting condition; acquiring planning track information corresponding to each reachable state in the reachable state set; determining a target state corresponding to the target object from all reachable states based on planning track information corresponding to each reachable state, a level corresponding to each reachable state and evaluation factors, wherein the level corresponding to each reachable state is the level of the reachable state in a preset layered state machine; and controlling the preset layered state machine to jump from the current state to the target state so that the target object runs based on the planned track information corresponding to the target state, thereby improving the rationality of path planning.

Description

Path planning method and device

Technical Field

The invention relates to the technical field of path planning, in particular to a path planning method and device.

Background

In high-speed and urban road traffic, a path planning module of an automatic driving vehicle needs to plan a reasonable track in real time according to a map task under the condition of meeting traffic regulations and normal driving habits of human drivers, and the reasonable track is delivered to a bottom layer control module for execution, and the state of the automatic driving vehicle is updated and maintained in an upstream user interaction interface so as to show the intention of the automatic driving vehicle and corresponding driving behaviors to passengers of the automatic driving vehicle and pedestrians and vehicles around the passengers.

At present, in the process of planning a track, a path planning module generally determines a target state directly based on a skip relation among states of a preset state machine and a current state, and plans a reasonable track based on current environment information, map information and pose information of an automatic driving vehicle acquired by an upper information acquisition module, a target state to be skipped to and a preset path planning algorithm.

In the process, the target state is directly determined based on the skip relation among the states of the preset state machine and the current state, the determined target state may not be the optimal target state, and the determined track may not be the most reasonable track.

Disclosure of Invention

The invention provides a path planning method and a path planning device, which aim to improve the rationality of path planning. The specific technical scheme is as follows:

in a first aspect, an embodiment of the present invention provides a path planning method, where the method includes:

obtaining relevant information of a current decision-making plan corresponding to a target object;

determining a reachable state set corresponding to the target object based on a current state of a preset layered state machine, a jump relation among states, the current decision planning related information and a preset driving limiting condition, wherein the preset layered state machine comprises: jump relations and hierarchical relations among the states corresponding to the target object;

acquiring planning track information corresponding to each reachable state in the reachable state set;

determining a target state corresponding to the target object from all reachable states based on planning track information corresponding to each reachable state, a level corresponding to each reachable state and evaluation factors, wherein the level corresponding to each reachable state is the level of the reachable state in a preset layered state machine;

and controlling the preset hierarchical state machine to jump from the current state to the target state so as to enable the target object to run based on the planned track information corresponding to the target state.

Optionally, the current decision planning related information includes: current surrounding perception information, current pose information, current map information, and prediction information of the obstacle of the target object.

Optionally, the step of determining a reachable state set corresponding to the target object based on the current state of the preset hierarchical state machine, the jump relationship between the states, the current decision planning related information, and a preset driving limiting condition includes:

preprocessing the specified information in the current decision-making planning related information, and judging whether each information in the current decision-making planning related information is effective or not;

and under the condition that the obtained current decision-making planning related information is effective, determining an accessible state set corresponding to the target object based on the current state of a preset layered state machine, the jump relation among the states, the current decision-making planning related information and a preset driving limiting condition.

Optionally, the step of determining the target state corresponding to the target object from all reachable states based on the planning trajectory information corresponding to each reachable state, the hierarchy corresponding to each reachable state, and the evaluation factor includes:

judging whether the reachable state set has a reachable state in which the corresponding execution tag is the necessary execution tag, wherein the skip tag is: a label determined based on current surrounding awareness information and/or current map information in the current decision plan related information;

if the reachable state set is determined to have the corresponding execution tag as the reachable state of the tag to be executed, determining the reachable state with the highest corresponding current priority as the state to be evaluated based on the current priority corresponding to the top level state corresponding to each reachable state; determining whether the planning track information corresponding to the state to be evaluated is feasible or not based on the planning track information corresponding to the state to be evaluated and the evaluation factor corresponding to the state to be evaluated, wherein the reachable state corresponding to the execution tag has the highest priority;

if the evaluation result represents that the planning track information corresponding to the state to be evaluated is feasible, determining a target state corresponding to the target object from the state to be evaluated based on the feasible planning track information;

and if the evaluation result represents that the planning track information corresponding to the state to be evaluated is not feasible, returning to execute the current priority corresponding to the top level state corresponding to each reachable state, and determining the reachable state with the highest corresponding current priority as the state to be evaluated.

Optionally, if the to-be-evaluated state includes reachable states which are mutually public parent states and are in the same level; the reachable states which have public father states and are in the same level have a time sequence stage transition relation;

the step of determining whether the planning track information corresponding to the state to be evaluated is feasible or not based on the planning track information corresponding to the state to be evaluated and the evaluation factor corresponding to the state to be evaluated includes:

aiming at to-be-evaluated states which have public father states and are in the same level, sequentially determining a reachable state which is not evaluated currently and has the first transition relation of the corresponding time sequence stage as the current to-be-evaluated state based on the sequence of the transition relation of the time sequence stage corresponding to each to-be-evaluated state;

determining an evaluation index value corresponding to the current state to be evaluated based on the planning track information corresponding to the current state to be evaluated and the evaluation factor corresponding to the current state to be evaluated;

if the rating index value corresponding to the current state to be evaluated represents: the planning track information corresponding to the current state to be evaluated is feasible, and whether an unevaluated state exists in the state to be evaluated is judged;

if yes, returning to the slave state to be evaluated, and determining an unacevated reachable state with the first transition relation of the corresponding time sequence stage as the current state to be evaluated;

and if the evaluation result does not exist, or the planning track information corresponding to the current state to be evaluated is determined to be not feasible, obtaining the evaluation result whether the planning track information corresponding to the state to be evaluated is feasible or not.

Optionally, the step of determining a target state corresponding to the target object from states to be evaluated based on the feasible planning track information includes:

and determining the reachable state of the transition relation of the corresponding time sequence stage in the reachable states corresponding to the feasible planning track information as the target state corresponding to the target object.

Optionally, the method further includes:

if it is determined that the corresponding execution tag does not exist in the reachable state set and is the reachable state in which the tag needs to be executed, determining an evaluation index value corresponding to the reachable state based on the planning track information corresponding to the reachable state and the evaluation factor corresponding to the reachable state for each reachable state;

and determining the target state corresponding to the target object from all the reachable states based on the evaluation index value corresponding to each reachable state.

Optionally, the step of obtaining the planning track information corresponding to each reachable state in the reachable state set includes:

and determining planning track information corresponding to each reachable state in the reachable state set based on a path planning algorithm corresponding to each reachable state in the reachable state set and current surrounding perception information, current pose information, current map information and prediction information of the barrier of the target object in the current decision planning related information.

Optionally, the method further includes:

and determining a visualization signal and visualization information corresponding to the target state based on the target state, and outputting the visualization signal and visualization information to enable the target object to be correspondingly displayed based on the visualization signal and visualization information.

In a second aspect, an embodiment of the present invention provides a path planning apparatus, where the apparatus includes:

a first obtaining module configured to obtain current decision-making planning related information corresponding to a target object;

a first determining module, configured to determine, based on a current state of a preset hierarchical state machine, a skip relationship between states, the current decision-making planning related information, and a preset driving limiting condition, a reachable state set corresponding to the target object, where the preset hierarchical state machine includes: jump relations and hierarchical relations among the states corresponding to the target object;

a second obtaining module configured to obtain planning track information corresponding to each reachable state in the reachable state set;

the second determining module is configured to determine a target state corresponding to the target object from all reachable states based on planning track information corresponding to each reachable state, a level corresponding to each reachable state and evaluation factors, wherein the level corresponding to each reachable state is a level of the reachable state in a preset layered state machine;

and the control module is configured to control the preset hierarchical state machine to jump from the current state to the target state so as to enable a target object to run based on the planned track information corresponding to the target state.

Optionally, the current decision-making plan related information includes: current surrounding perception information, current pose information, current map information, and prediction information of the obstacle of the target object.

Optionally, the first determining module is specifically configured to pre-process the specified information in the current decision-making plan related information, and determine whether each piece of information in the current decision-making plan related information is valid;

Optionally, the second determining module includes:

a determining unit, configured to determine whether there is a reachable state in the reachable state set where the corresponding execution tag is an execution-required tag, where the skip tag is: a label determined based on current surrounding awareness information and/or current map information in the current decision plan related information;

a first determining unit, configured to determine, if it is determined that there is an reachable state in the reachable state set in which a corresponding execution tag is a tag that must be executed, a reachable state with a highest corresponding current priority as a state to be evaluated, based on a current priority corresponding to a top-level state corresponding to each reachable state; determining whether the planning track information corresponding to the state to be evaluated is feasible or not based on the planning track information corresponding to the state to be evaluated and the evaluation factor corresponding to the state to be evaluated, wherein the reachable state corresponding to the execution tag has the highest priority;

the second determining unit is configured to determine a target state corresponding to the target object from the state to be evaluated based on feasible planning track information if the evaluation result represents that the planning track information corresponding to the state to be evaluated is feasible;

and if the evaluation result represents that the planning track information corresponding to the state to be evaluated is not feasible, returning to trigger the first determining unit.

the first determining unit is specifically configured to sequentially determine, for to-be-evaluated states which have public father states and are in the same level, an reachable state which is currently not evaluated and has the earliest corresponding time sequence stage transition relationship based on the sequence of the time sequence stage transition relationships corresponding to the to-be-evaluated states, and the reachable state is the current to-be-evaluated state;

Optionally, the second determining unit is specifically configured to determine, as the target state corresponding to the target object, the reachable state that corresponds to the time sequence stage transition relationship and is the last reachable state of the reachable states corresponding to the feasible planning trajectory information.

Optionally, the second determining module further includes:

a third determining unit, configured to determine, for each reachable state, an evaluation index value corresponding to the reachable state based on the planning trajectory information corresponding to the reachable state and the evaluation factor corresponding to the reachable state if it is determined that the corresponding execution tag does not exist in the reachable state set as a reachable state in which the tag must be executed;

and determining the target state corresponding to the target object from all reachable states based on the evaluation index value corresponding to each reachable state.

Optionally, the second obtaining module is specifically configured to determine planning trajectory information corresponding to each reachable state in the reachable state set based on a path planning algorithm corresponding to each reachable state in the reachable state set and current surrounding perception information, current pose information, current map information, and prediction information of an obstacle of a target object in the current decision-making planning related information.

Optionally, the apparatus further comprises:

and the determination output module is configured to determine a visualization signal and visualization information corresponding to the target state based on the target state and output the visualization signal and visualization information so that the target object is correspondingly displayed based on the visualization signal and visualization information.

As can be seen from the above, the method and device for path planning provided in the embodiments of the present invention obtain the current decision-making planning related information corresponding to the target object; determining a reachable state set corresponding to a target object based on the current state of a preset layered state machine, the jump relation among the states, the current decision planning related information and a preset driving limiting condition, wherein the preset layered state machine comprises: jump relations and hierarchical relations among the states of the target object; acquiring planning track information corresponding to each reachable state in the reachable state set; determining a target state corresponding to the target object from all reachable states based on planning track information corresponding to each reachable state, a level corresponding to each reachable state and evaluation factors, wherein the level corresponding to each reachable state is the level of the reachable state in a preset layered state machine; and controlling the preset layered state machine to jump from the current state to the target state so as to enable the target object to run based on the planned track information corresponding to the target state.

By applying the embodiment of the invention, the reachable state set which can be jumped from the next state of the preset layered state machine is determined based on the current state of the preset layered state machine, the jump relation among the states, the related information of the current decision planning and the preset driving limiting condition, namely, the reachable state set at the next moment of the target object corresponding to the preset layered state machine is determined, and then the most reasonable reachable state of the corresponding planning track information, namely the target state, is determined from the reachable state set by utilizing the rationality of the planning track information corresponding to each reachable state, so that the rationalization and the accuracy of the state of the target object at the next moment are determined, the rationality of the path planning is improved, and in the planning process, the reachable state is determined firstly, and then the planning track information corresponding to the reachable state is obtained, so that the planning information is evaluated, the planning framework has the advantages that the target state is determined from the reachable state, the planning framework is more generalizable, extensible and interpretable, new scenes and action modes can be quickly defined and embedded aiming at new problems and scenes which actually emerge, and a new path planning algorithm is adapted. Of course, not all of the advantages described above need to be achieved at the same time in the practice of any one product or method of the invention.

The innovation points of the embodiment of the invention comprise:

1. the method comprises the steps of firstly determining an reachable state set, further analyzing evaluation results of planning track information corresponding to all reachable states in the reachable state set, determining the most reasonable reachable state from the reachable state set to serve as a target state, achieving reasonable and accurate determination of the state of a target object at the next moment, and achieving improvement of the rationality of path planning. And in the planning process, firstly, the reachable state is determined, and then the planning track information corresponding to the reachable state is obtained, so that the target state is determined from the reachable state through the evaluation of the planning information.

2. The method comprises the steps of firstly determining the validity of each piece of information in the current decision planning related information, and executing a subsequent path planning process under the condition that the current decision planning related information is valid so as to ensure the safety and the rationality of the path planning.

3. And when determining that the planning track corresponding to the reachable state base of the tag to be executed is infeasible, sequentially carrying out downward arbitration to ensure that the determined target state is more reasonable and better conforms to the current environment condition.

4. When the reachable state set does not have the reachable state in which the corresponding execution tag is the necessary execution tag, the evaluation index values corresponding to the reachable states can be determined in parallel, so that the most reasonable reachable state is determined as the target state.

5. Setting a time sequence stage transition relation aiming at the child state with the public parent state, determining the evaluation index value corresponding to each child state by combining the time sequence stage transition relation, namely determining the feasibility of the planning track information corresponding to each child state, limiting the execution sequence of the child state with the public parent state through the time sequence stage transition relation, and ensuring the optimality and the continuity of the target object in each state jump.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It is to be understood that the drawings in the following description are merely exemplary of some embodiments of the invention. For a person skilled in the art, without inventive effort, further figures can be obtained from these figures.

Fig. 1 is a schematic flow chart of a path planning method according to an embodiment of the present invention;

FIGS. 2A and 2B are schematic diagrams of state jump logic of a default hierarchical state machine;

fig. 3 is a schematic structural diagram of a path planning apparatus according to an embodiment of the present invention.

Detailed Description

The technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. It is to be understood that the described embodiments are merely a few embodiments of the invention, and not all embodiments. All other embodiments, which can be obtained by a person skilled in the art without inventive effort based on the embodiments of the present invention, are within the scope of the present invention.

It is to be noted that the terms "comprises" and "comprising" and any variations thereof in the embodiments and drawings of the present invention are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.

The invention provides a path planning method and a path planning device, which aim to improve the rationality of path planning. The following provides a detailed description of embodiments of the invention.

Fig. 1 is a schematic flow chart of a path planning method according to an embodiment of the present invention. The method may comprise the steps of:

s101: and obtaining the relevant information of the current decision-making plan corresponding to the target object.

The path planning method provided by the embodiment of the invention can be applied to any electronic equipment with computing capacity, and the electronic equipment can be a terminal or a server. In one implementation, the functional software for implementing the path planning method may be in the form of a separate client software, or may be in the form of a plug-in to a currently associated client software, for example, in the form of a functional module of an automatic driving system.

The target object may be an object that needs to be subjected to path planning, such as an autonomous vehicle and a robot. In one implementation, when the target object is an autonomous vehicle, the electronic device implementing the path planning method may be a vehicle-mounted device, and is disposed in the target object, and may directly obtain current decision-making planning related information corresponding to the target object. In another case, the electronic device implementing the path planning method may also be an off-board device, and the corresponding electronic device may be connected to the data processing device corresponding to the target object to obtain the current decision-making planning related information corresponding to the target object, which is sent by the data processing device corresponding to the target object.

In one implementation of the present invention, the current decision plan related information may include, but is not limited to: current surrounding perception information, current pose information, current map information, and prediction information of the obstacle of the target object. The current map information may refer to map information corresponding to an environment where the target object is located. The predicted information of the obstacle may include, but is not limited to: predicted travel trajectory of the obstacle and travel parameter information.

The current decision-making planning related information is information for assisting decision-making planning and path planning, wherein the decision-making planning is a state to which a target object needs to jump, and the target object drives based on path information corresponding to the state to which the target object needs to jump, so that path planning is achieved. The current decision plan related information is: based on the information determined from the sensor data collected by the sensor set for the target object, the sensor set for the target object may include, but is not limited to: image acquisition equipment, wheel speed sensors, radar, IMU (Inertial measurement unit), GPS (Global Positioning System), GNSS (Global Navigation Satellite System), and the like.

S102: and determining an reachable state set corresponding to the target object based on the current state of a preset layered state machine, the jump relation among the states, the current decision planning related information and a preset driving limiting condition.

The preset layering state machine comprises: jump relation and hierarchical relation among the states corresponding to the target object.

The electronic equipment is locally or connected with a storage device, a preset layered state machine is prestored, the preset layered state machine comprises various states corresponding to corresponding target objects, and the preset layered state machine comprises jump relations and hierarchical relations among the states corresponding to the target objects.

The preset hierarchical state machine comprises states in the same hierarchy and states in different hierarchies. Different states can represent different executed actions of the target object, that is, a certain state of a certain level in the preset hierarchical state machine can display a certain action mode representing the target object. Jumping of the state of the preset hierarchical state machine may control a corresponding execution action of the target object, i.e., a transition of an action mode.

A state of a next hierarchy corresponding to a state of a certain hierarchy may be referred to as a sub-state of the state, and different sub-states corresponding to the state may be considered as: the operation mode corresponding to this state is divided or staged. For example: the target object is an autonomous vehicle, and as shown in fig. 2A, the preset hierarchical state machine, i.e., "the hierarchical state machine" described in fig. 2A, may include: lane keeping, lane changing, lane borrowing and the like are in the states of a first level, namely a top level, wherein lane changing can comprise sub-states of a second level, such as lane changing preparation and lane changing execution, and lane changing can also comprise a lane changing returning sub-state. Accordingly, the predetermined hierarchical state machine may include two levels of states. For example: the preset layering state machine comprises: the lane keeping and the parking beside may be in a state of a first hierarchy, wherein the parking beside may include a sub-state of a second hierarchy such as deceleration and execution of the parking beside.

According to the different action modes of the target object, namely the continuous division of the execution action, a preset hierarchical state machine containing more levels of states can be constructed. For example: the sub-state lane change execution at the second level may further include: lower level sub-states such as driving to, entering, and traveling in a target lane, etc.

It is understood that the state at the lowest level in the preset hierarchical state machine may be considered to correspond to a specific subdivision scenario, for example: based on the above example, the target object is in a scene that requires lane change preparation, the target object is in a scene that requires lane change execution, and the like; the lane keeping does not correspond to the state of the next hierarchy, and the target object is in a scene where the target object is required to be in the lane keeping. It needs to complete trajectory planning and obtain corresponding planning trajectory information.

The preset driving limiting condition is a condition for limiting a driving mode of the target object, for example, the preset driving limiting condition may include a traffic rule to be observed in an area where the target object is located, may also include a limiting condition corresponding to a task executed by the target object, and may also include an experience condition and a comprehensiveness condition that are artificially added to limit a driving behavior of the target object. In one case, the conditions of human added experience and comprehension include, but are not limited to: conditions for defining the number of required computational scenarios and the range of constraints, the number of scenarios being determined by the data of the determined reachable states. The execution tasks of the target object may include, but are not limited to: the target object needs to travel to each destination; the target object needs to complete the task of the driving action in the driving process, and the like.

In the embodiment of the invention, the function of allowing the condition to be manually added can be reserved, so that other conditions can be added and opened after the path planning capability boundary of the subsequent electronic equipment is expanded.

In order to plan a better path and a better decision, it is necessary to ensure that there is continuity between the determined series of states, i.e. the execution actions of the target object, for example: the target object in the turning situation, the former state is left turn, and in order to maintain the motion consistency, the latter state should be left turn, so as to avoid the problem that the target object turns left and right in the turning situation. Correspondingly, the reachable state set needs to be determined by combining the current state of the preset hierarchical state machine.

In this step, the electronic device may detect a current state of the preset hierarchical state, and then, based on the current state of the preset hierarchical state machine and a jump relationship between the states, determine a state that can jump from the current state from the states of the preset hierarchical state machine as a standby state, and further, based on the current decision-making planning related information and the preset driving limiting condition, select a state that satisfies the preset driving limiting condition and/or meets the current decision-making planning related information from the standby state as an reachable state corresponding to the target object, so as to obtain a reachable state set corresponding to the target object.

For example: the preset travel limiting condition includes: under the condition that the target object is prohibited from keeping jumping from the lane to the lane changing when entering the sight area, determining that an accident vehicle appears in front of the target object or a rapidly crossing pedestrian appears suddenly from a blind area of the target object based on the related information of the current decision plan.

S103: and acquiring planning track information corresponding to each reachable state in the reachable state set.

Wherein the planned trajectory information includes but is not limited to: and skipping to the track information required to be driven by the target object after the corresponding reachable state is reached, driving parameter information of the target object and related driving parameter information of other objects which have an interactive relation with the target object.

The driving parameter information of the target object may include, but is not limited to: average velocity information, acceleration information, and rotation angle information. The related driving parameter information of other objects having an interactive relationship with the target object may include, but is not limited to: average velocity information, acceleration information, and rotation angle information.

Other objects that have an interactive relationship with the target object may refer to: objects that are dodged from the target object and/or objects that are dodged from the target object, i.e. objects that are affected by the action performed by the target object, such as: when the target object changes lanes, the target position is the position where the target object is inserted into the lane change, and the target position is the object behind the target position of the target lane to which lane change is required.

In one case, after the electronic device determines the reachable state set, the current state, the current decision-making planning related information, and the preset driving limiting condition are sent to other devices, so that the planning track information corresponding to each reachable state is determined by the other devices and sent to the electronic device. Correspondingly, the electronic equipment obtains planning track information corresponding to each reachable state in the reachable state set.

In an implementation manner of the present invention, the preset hierarchical state and each state in the hierarchical state correspond to a corresponding path planning algorithm for planning a path, and after the electronic device determines the reachable state set, the electronic device may determine, for each reachable state in the reachable state set, the planning trajectory information corresponding to the reachable state based on the path planning algorithm corresponding to the reachable state, current surrounding perception information of the target object in the current decision-making planning related information, current pose information, current map information, and prediction information of the obstacle.

S104: and determining a target state corresponding to the target object from all reachable states based on the planning track information corresponding to each reachable state, the hierarchy corresponding to each reachable state and the evaluation factors.

And the level corresponding to the reachable state is the level of the reachable state in a preset layered state machine.

The electronic equipment determines an evaluation index value corresponding to each reachable state according to the track planning information corresponding to the reachable state, the level corresponding to the reachable state and the evaluation factors, and further determines a reachable state which represents the most reasonable track planning information corresponding to the reachable state from all reachable states according to the evaluation index value corresponding to each reachable state to serve as a target state corresponding to the target object.

Wherein, under the condition that the evaluation index value exists in the form of a penalty term, that is, the lower the evaluation index value is, the more reasonable the trajectory planning information corresponding to the representation reachable state is, the most reasonable reachable state can refer to the reachable state with the smallest value of the corresponding evaluation index value; when the evaluation index value exists in a form of a non-penalty item, that is, the higher the evaluation index value is, the more reasonable the trajectory planning information corresponding to the representation reachable state is, the most reasonable reachable state may refer to a reachable state in which the value of the corresponding evaluation index value is the largest.

The process of determining the evaluation index value corresponding to each reachable state based on the trajectory planning information corresponding to each reachable state, the hierarchy corresponding to each reachable state, and the evaluation factors can be understood as a process of constructing an arbitration tree for the reachable state set, that is, a process of evaluating and arbitrating the planning trajectory information corresponding to each reachable state, and after the construction of the arbitration tree is completed, that is, the evaluation index value corresponding to each reachable state is determined, the final most reasonable target state of the corresponding trajectory planning information obtained in the process can be determined based on a depth-first principle, and the trajectory planning information corresponding to the final most reasonable target state can be determined.

In one case, the evaluation factors may include, but are not limited to: safety, comfort, traffic efficiency of the track, preset running limiting conditions, task execution of the target object and other factors.

In the evaluation and arbitration process of the planning trajectory information corresponding to the states of different hierarchies, different evaluation factor combinations are generally used to avoid the situation of local optimization. For the evaluation arbitration of the low-level state, factors such as different avoidance decisions of specific obstacles, namely safety and the like need to be considered, and relevant factors such as tasks executed by target objects and scene environments where the target objects are located can not be considered; the evaluation arbitration of the high-level state needs to consider factors such as tasks executed by the target object, the scene environment and the specific requirements of the traffic rules of the area where the target object is located.

In one case, the evaluation factors may include, but are not limited to: the track safety, the track comfort, the track traffic efficiency and the track corresponding preset execution penalty items.

The determination of the evaluation index value corresponding to the safety of the trajectory may be performed by performing collision detection determination of a space-time dimension based on the planned trajectory in the planned trajectory information corresponding to the reachable state and the predicted trajectory of the object having no interaction relationship with the other target object. The uncertainty of the prediction intention and the distribution of locus points of the predicted locus of other objects having no interactive relation with the target object need to be considered, so as to measure probability information of collision conditions of the planned locus in the planned locus information corresponding to the reachable state. It can be used in the evaluation arbitration of different avoidance decisions of obstacles under certain scenarios, for example: the method is used when the target object is in the lane-changing stage to select the position to be inserted into the target road to be changed, namely the gap between two objects in the target road.

Only objects that do not interact with the host vehicle are considered in the collision check. It is further explained here that an object without interaction generally refers to a vehicle whose own behavior does not interfere with a track, or whose own behavior does not affect the behavior of the other vehicle (such as a leading vehicle for lane keeping), and needs to be comprehensively judged in combination with a scene; the interactive object means that the behavior of the own vehicle (for completing tasks or ensuring safety) can affect other vehicles, such as vehicles behind a target lane when the own vehicle changes lanes. And (4) screening out targets which need interaction and do not need interaction based on empirical rules from the algorithm perspective.

In one implementation, a safety threshold of the trajectory may be set to determine whether the planned trajectory is safe and feasible using a rough mode or a precise mode, which is expressed by the following formula (1):

wherein, J _safety An evaluation index value representing the safety correspondence of the planned trajectory; p is a radical of _collide Representing probability information of collision of the planning track in the planning track information corresponding to the reachable state calculated in the accurate mode; k is a radical of _collide Representing a preset weight coefficient in an accurate mode; n is _collide And information indicating whether the planned trajectory collides in the planned trajectory information corresponding to the reachable state in the rough mode.

p _collide The calculation of the method depends on the prediction information of the obstacles in the current decision planning related information, wherein the prediction information of the obstacles comprises the prediction tracks of the obstacles, and the prediction track corresponding to each obstacle comprises a plurality of track points; the calculation can have two modes, the first mode is that for each obstacle, track points in a predicted track corresponding to the obstacle are sampled, and the collision corresponding to the obstacle is obtained through samplingThe collision track corresponding to the barrier comprises a plurality of sampling track points; aiming at each obstacle, carrying out point-by-point collision check by utilizing a sampling track point at a certain moment in a collision track corresponding to the obstacle and a track point at the moment in a planning track corresponding to the reachable state of the target object, and counting the number of the sampling track points which are corresponding to the obstacle and have collision; for each obstacle, calculating the ratio of the number of the collided track points corresponding to the obstacle to the total number of the track points by using the number of the collided sampled track points corresponding to the obstacle and the total number of the track points as the ratio corresponding to the obstacle; and determining the probability information of collision corresponding to the planning track information corresponding to the reachable state according to the ratio corresponding to all the obstacles.

The process of performing point-by-point collision inspection by using the sampling track point at a certain moment in the collision track corresponding to the obstacle and the track point at the moment in the planning track corresponding to the reachable state of the target object is as follows: determining whether the position of the target object and the obstacle is overlapped at a certain moment or not according to the position and pose information of the target object and the polygonal model representing the target object at the certain moment, and the position and pose information of the obstacle and the polygonal model representing the obstacle, and if the position is overlapped, collision occurs; otherwise, no position overlap occurs and no collision occurs. The total number of the track points may refer to the total number of the track points in the planned track corresponding to the reachable state of the target object, or may refer to the total number of the track points in the predicted track obtained by the method.

The process of determining the probability information of collision corresponding to the planned trajectory information corresponding to the reachable state according to the ratio corresponding to all the obstacles may be: and counting the number of the obstacles of which the corresponding ratio exceeds a preset ratio threshold, and determining the probability information of collision corresponding to the planning track information corresponding to the reachable state based on the number and the total number of the obstacles.

And the second method comprises the following steps: obtaining the collision probability of the track points point by point according to the relative position between the track points in the planning track corresponding to the reachable state of the target object and the track points in the predicted track information of the obstacle and the space probability distribution condition of the track points in the predicted track information of the obstacle; and selecting the collision probability of the track point with the maximum numerical value as the collision probability corresponding to the planning track information corresponding to the reachable state of the target object.

In the above process of obtaining the collision probability of the track points, the method that can determine the collision probability of two tracks when the two tracks collide with each other can be referred to in the related art, for example: under the condition that the spatial probability distribution condition of the track points in the predicted track information of the obstacle is discretized, the spatial probability distribution condition of the track points in the predicted track information of the obstacle and the weight corresponding to each pair of track points can be directly used for comparing with the track points in the planned track of the target object, and the collision probability of the track points is determined. And under the condition that the spatial probability distribution condition of the track points in the predicted track information of the obstacles is continuous and integrable, simplifying the target object into a circular model, determining the collision between the track point of the planned track of the target object and the track points in the predicted track information of each obstacle, and obtaining the collision probability of the track points.

The rough mode or the precise mode is selected and used, and the setting can be performed according to actual setting, such as a scene, and the scene and the state have a corresponding relation.

The evaluation index value corresponding to the safety of the track exists in the form of a penalty term, and the higher the evaluation index value corresponding to the safety of the track is, the lower the safety of the track corresponding to the planning track information representing the reachable state is.

The determination of the evaluation index value corresponding to the passing efficiency of the trajectory needs to consider the average speed per hour v of the planned trajectory in the planned trajectory information corresponding to the reachable state of the target object, and also needs to consider the average speed per hour change delta v of the ith object caused by avoiding the target object in the object set phi having an interactive relationship with the target object _i (ii) a For objects of different priorities, the coefficient k can be used _i And distinguishing to obtain a preset value. Wherein, the evaluation index value part corresponding to each object in the object set phi having interaction relation with the target object is determined in the evaluation index value corresponding to the passing efficiency of the trackThe fixed process can be expressed by the following formula (2):

J _interaction ＝∑ _i∈Φ -k _i Δv _i ； (2)

wherein, J _interaction And (3) the evaluation index value part corresponding to each object in the object set phi having an interactive relation with the target object in the evaluation index values corresponding to the traffic efficiency of the track. Δ v _i Can be determined from the current ambient perceptual information.

The evaluation index value corresponding to the passing efficiency of the track exists in the form of a penalty item, and the larger the evaluation index value corresponding to the passing efficiency of the track is, the lower the passing efficiency of the track corresponding to the planning track information representing the reachable state is.

On one hand, the acceleration a corresponding to the planned track in the planned track information corresponding to the reachable state of the target object can be considered, and correspondingly, the determination mode of the first part of the evaluation index values corresponding to the comfort of the track can be represented by the following formula (3);

J _comfort ＝k _comfort *a； (3)

wherein, J _comfort A first partial value k of evaluation index values corresponding to the comfort of the trajectory _comfort And the coefficient value corresponding to the acceleration a is a preset value.

On the other hand, in the case of a lane change or a turn, the determination of the evaluation index value corresponding to the comfort of the trajectory may also take into account the lateral acceleration a that is generated _lat Accordingly, the determination manner of the second partial value in the evaluation index value corresponding to the comfort of the trajectory can be expressed by the following formula (4);

J _LCManeuver ＝k _LCManeuver *a _lat ； (4)

wherein, J _LCManeuver Second partial value k of evaluation index values corresponding to comfort of trajectory _LCManeuver And a coefficient value corresponding to the lateral acceleration a is a preset value.

The evaluation index value corresponding to the comfort of the track exists in the form of a penalty item, and the higher the evaluation index value corresponding to the comfort of the track is, the lower the comfort of the track corresponding to the planning track information representing the reachable state is.

In the process of determining the evaluation index value corresponding to the planning track information corresponding to the reachable state, the evaluation index value can be determined by n _LCNeed E {0,1} to indicate whether the execution tag corresponding to the reachable state is a must-execute tag, where n may be _LCNeed When the number is 1, the execution tag corresponding to the reachable state is the necessary execution tag, n _LCNeed If the number of the execution tags is 1, the execution tag corresponding to the reachable state is not an indispensable execution tag, and whether the preset execution penalty item J corresponding to the track is added or not is determined according to whether the execution tag corresponding to the reachable state is the indispensable execution tag or not _LCNeed 。

S105: and controlling the preset layered state machine to jump from the current state to the target state so as to enable the target object to run based on the planned track information corresponding to the target state.

After the target state is determined by the electronic device, the preset layered state machine can be controlled to jump from the current state to the target state, and the planned trajectory information corresponding to the target state is output, so that the target object runs based on the planned trajectory information corresponding to the target state.

By applying the embodiment of the invention, the reachable state set which can be jumped from the next state of the preset layered state machine is determined based on the current state of the preset layered state machine, the jump relation among the states, the related information of the current decision planning and the preset driving limiting condition, namely, the reachable state set at the next moment of the target object corresponding to the preset layered state machine is determined, and then the reachable state which is the most reasonable reachable state of the corresponding planning track information, namely the target state, is determined from the reachable state set by utilizing the rationality of the planning track information corresponding to each reachable state, so that the rationalization and the accuracy of the state at the next moment of the target object are determined, the rationality of the path planning is improved, and in the planning process, the reachable state is determined firstly, and then the planning track information corresponding to the reachable state is obtained, so that the planning information is evaluated, the planning framework has the advantages that the target state is determined from the reachable state, the planning framework is more generalizable, extensible and interpretable, new scenes and action modes can be quickly defined and embedded aiming at new problems and scenes which actually emerge, and a new path planning algorithm is adapted.

In another embodiment of the present invention, the step S102 may include the following steps 011-:

011: and preprocessing the specified information in the current decision-making planning related information, and judging whether each piece of information in the current decision-making planning related information is effective or not.

012: and under the condition that the obtained current decision-making planning related information is effective, determining an accessible state set corresponding to the target object based on the current state of a preset layered state machine, the jump relation among the states, the current decision-making planning related information and a preset driving limiting condition.

In this implementation manner, in order to ensure the accuracy of the subsequent decision result and the accuracy of the path planning, after the electronic device obtains the current decision planning related information, the electronic device performs preprocessing on the specified information in the current decision planning related information, for example: determining a running track of the target object by using the current pose information and the previous historical pose information; and determining the driving track of each perception target in the current surrounding perception information by using the current surrounding perception information and the historical surrounding perception information, and the like.

And further, determining whether each piece of information in the current decision-making planning related information is effective or not based on the preprocessing result and the specific data of each piece of information in the current decision-making planning related information. For example: determining whether the current pose information is accurate or not based on a specific numerical value of the current pose information in the current decision planning related information and the determined running track of the target object; and determining whether the current surrounding sensing information is accurate or not based on the position information and the type of each sensing target in the current surrounding sensing information and the running track of each sensing target, and determining whether the missed detection and the false detection of the sensing target occur or not, whether the position information of the sensing target is accurate or not and the like. Whether the predicted information of the obstacle is accurate is determined based on a specific numerical value of the predicted information of the obstacle.

And executing a subsequent path planning process under the condition that all information of the current decision planning related information is determined to be effective. So as to ensure the accuracy of the subsequent decision result and the accuracy of the path planning.

In another implementation manner, in a case that it is determined that all pieces of information of the current decision-making plan related information are not valid, the electronic device may determine deceleration trajectory information based on valid information in the current decision-making plan related information, so as to control the target object to perform deceleration driving based on the deceleration trajectory information. And reset the state of the preset hierarchical state machine, for example: the preset hierarchical state and the preset hierarchical state can be reset to the appointed state, so that the safety of the target object and other objects having interaction relation with the target object is ensured.

In one case, in a case where the target object is an autonomous vehicle, after an autonomous driving system of the target object is started, the electronic device may operate at a fixed frequency, and after obtaining a frame of current decision-making plan related information, the electronic device may perform preprocessing on specified information in the current decision-making plan related information and determine whether each piece of information in the current decision-making plan related information is valid.

In another embodiment of the present invention, the step S104 may include the following steps 021-:

021: and judging whether the reachable state set has a reachable state in which the corresponding execution tag is the necessary execution tag.

Wherein, the skip label is: tags determined based on current surrounding perceptual information and/or current map information in the current decision plan related information.

022: if the corresponding execution tag is determined to be the reachable state of the tag which needs to be executed in the reachable state set, determining the reachable state with the highest corresponding current priority as the state to be evaluated based on the current priority corresponding to the top level state corresponding to each reachable state; and determining whether the planning track information corresponding to the state to be evaluated is feasible or not based on the planning track information corresponding to the state to be evaluated and the evaluation factor corresponding to the state to be evaluated.

Wherein the reachable state corresponding to the tag must be executed with the highest priority.

023: and if the evaluation result represents that the planning track information corresponding to the state to be evaluated is feasible, determining a target state corresponding to the target object from the state to be evaluated based on the feasible planning track information.

024: and if the evaluation result represents that the planning track information corresponding to the state to be evaluated is not feasible, returning to execute 022.

When the next state of the target object, namely the planning track of the target object is determined, the safety of the target object and other objects having an interactive relationship with the target object needs to be paid attention to preferentially, and based on the surrounding conditions represented by the current surrounding perception information, the current pose information and the current map information in the current decision-making planning related information, it is inevitable that some actions need to be performed by the target object to avoid the danger of the target object and/or other objects having an interactive relationship with the target object. Accordingly, there is inevitably a difference between mandatory and non-mandatory executions in the determined reachable state. In order to ensure the safety of the target object and other objects with interactive relations, a difference exists between the evaluation arbitration process of planning track information corresponding to the available state which has to be executed and the unavailable state which has not to be executed.

Whether the reachable state needs to be executed or not can be determined through the execution tag corresponding to the reachable state. Wherein, the corresponding execution tag of the reachable state is: tags determined based on current surrounding perceptual information and/or current map information in the current decision plan related information. For example: under the condition that a fault object or a rapidly moving object suddenly appears in a lane in front of the target object in driving is determined through the current surrounding perception information, the target object needs to be driven in a lane changing way; under the condition that no road or no lane is ahead of the target object through the current surrounding perception information and the current map information, the target object needs lane changing driving or turning driving; the method comprises the steps that the situation that the front of a target object in driving is the intersection is determined through current surrounding perception information and current map information, the target object needs to turn left when a task executed by the target object needs to turn left, and correspondingly, the target object needs to turn to drive and the like.

In this implementation manner, in the process of evaluating and arbitrating the planned trajectory information corresponding to each reachable state, the electronic device first determines whether the reachable state set has a reachable state in which the corresponding execution tag is a tag that needs to be executed, if it is determined that the reachable state set has a reachable state in which the corresponding execution tag is a tag that needs to be executed, priority is given to evaluation and arbitration, and when the planned trajectory information corresponding to the reachable state in which the tag needs to be executed is safe and feasible, priority is given to jumping to the reachable state in which the tag needs to be executed.

The reachable state in the reachable state set may include a state at a top level hierarchy or a state at a non-top level hierarchy, and when it is determined that the reachable state set has a reachable state in which the corresponding execution tag must be executed, the evaluation and arbitration may be performed in sequence for the planned trajectory information corresponding to the reachable state based on the priority of the current priority corresponding to the state at the top level hierarchy corresponding to the reachable state, and it is understood that the current priority of the reachable state in which the tag must be executed is the highest.

Specifically, based on the current priority corresponding to the top-level hierarchical state corresponding to each reachable state, the reachable state with the highest corresponding current priority is determined as the state to be evaluated; determining an evaluation index value corresponding to the state to be evaluated based on the planning track information corresponding to the state to be evaluated and the evaluation factor corresponding to the state to be evaluated, and determining whether the planning track information corresponding to the state to be evaluated is feasible or not based on the evaluation index value corresponding to the state to be evaluated; if the evaluation result represents that the planning track information corresponding to the state to be evaluated is feasible, the current reachable state is directly determined as the target state corresponding to the target object; the evaluation arbitration process does not need to be executed according to the planning track information corresponding to other reachable states with low current priority.

And if the evaluation result represents that the planning track information corresponding to the state to be evaluated is not feasible, continuing to evaluate and arbitrate the planning track information corresponding to other reachable states with low current priority, namely returning to execute the current priority corresponding to the top level state corresponding to each reachable state, and determining the reachable state with the highest corresponding current priority as the state to be evaluated.

In one case, if at least one piece of planning track information corresponding to the state to be evaluated is feasible in the planning track information corresponding to the state to be evaluated, it may be determined that the planning track information corresponding to the state to be evaluated is feasible.

Wherein, the top level state corresponding to the reachable state is: the reachable state belongs to a state in a top level in a preset hierarchical state machine. For example: the states of the top level of the preset hierarchical state machine comprise lane keeping, lane changing and lane borrowing; the state lane change of the top level comprises three substates of lane change preparation, lane change execution and lane change return. In one case, the electronic device determines that the reachable state set corresponding to the target object includes three reachable states of lane keeping, lane changing preparation and lane changing execution based on the current state of the preset hierarchical state machine, the jump relationship between the states, the current decision-making plan related information and the preset driving limiting condition. The lane keeping system comprises a lane keeping system, a lane keeping system and a lane keeping system, wherein the lane keeping system is located at a top level, and the state of the corresponding top level is self; lane-change preparation and lane-change execution are sub-states of lane-change, and accordingly, the state of the top level hierarchy corresponding to lane-change preparation and lane-change execution is lane-change.

In another embodiment of the present invention, the state to be evaluated may be one or more of, for example: in connection with the above example, the top-level states corresponding to lane change preparation and lane change execution are top-level state lane change, and accordingly, the current priorities of lane change preparation and lane change execution are the same, and lane change preparation and lane change execution correspond to the same parent state and are in the same level, so that lane change preparation and lane change execution can be considered to be in reachable states that are in common parent states and are in the same level.

When a target object performs a certain series of execution actions during driving, theoretically, there exists a corresponding execution sequence between the series of execution actions, for example: when a target object needs to perform lane change, if a plurality of objects exist on a target road to which the target object is to be changed, when the target object performs lane change, a position where the lane change needs to be inserted, namely a gap between two objects in the target road or the front or the back of the object needs to be determined, then the target object runs to the position near the position where the lane change needs to be determined on the road, and the target object enters the target road after the lane change is performed.

In order to ensure consistency and comfort of execution actions of the target object, if the states to be evaluated include reachable states which have public father states and are in the same level, a time sequence stage transition relation exists among the states, and the time sequence stage transition relation is used for limiting the execution sequence among the states.

Correspondingly, in an embodiment of the present invention, after determining the state to be evaluated, the electronic device determines that the state to be evaluated includes a plurality of conditions, and if the state to be evaluated includes reachable states that are mutually public and are in the same level; there is a timing phase transition relationship between reachable states that are in the same level and have common parent states.

022, comprising the following steps 0221 and 0225:

0221: and aiming at the to-be-evaluated states which have public father states and are in the same level, sequentially determining the reachable state which is not evaluated currently and has the first corresponding time sequence stage transition relation as the current to-be-evaluated state based on the sequence of the time sequence stage transition relation corresponding to each to-be-evaluated state.

0222: and determining an evaluation index value corresponding to the current state to be evaluated based on the planning track information corresponding to the current state to be evaluated and the evaluation factor corresponding to the current state to be evaluated.

0223: if the rating index value corresponding to the current state to be evaluated represents: and the planning track information corresponding to the current state to be evaluated is feasible, and whether an unevaluated state exists in the state to be evaluated is judged.

0224: if yes, the process returns to 0221.

0225: and if the evaluation result does not exist, or the planning track information corresponding to the current state to be evaluated is determined to be not feasible, obtaining the evaluation result whether the planning track information corresponding to the state to be evaluated is feasible or not.

In the implementation mode, the electronic equipment traverses the to-be-evaluated states which are mutually public parent states and are in the same level in the to-be-evaluated states, and sequentially determines the reachable state which is not evaluated currently and has the first corresponding time sequence stage transition relationship based on the sequence of the time sequence stage transition relationship corresponding to each to-be-evaluated state, and the reachable state is the current to-be-evaluated state; and determining an evaluation index value corresponding to the current state to be evaluated based on the planning track information corresponding to the current state to be evaluated and the evaluation factor corresponding to the current state to be evaluated. And then, judging whether the planning track information corresponding to the current state to be evaluated is feasible or not based on the evaluation index value corresponding to the current state to be evaluated, if the rating index value corresponding to the current state to be evaluated represents: the planning trajectory information corresponding to the current state to be evaluated is feasible, whether an unexevated state exists in the state to be evaluated is judged, and if yes, the process continues to be executed 0224; and if the evaluation result does not exist, or the planning track information corresponding to the current state to be evaluated is determined to be not feasible, obtaining the evaluation result whether the planning track information corresponding to the state to be evaluated is feasible or not.

If it is determined that the planning track information corresponding to at least one state is feasible in the state to be evaluated, the evaluation result of whether the planning track information corresponding to the determined state to be evaluated is feasible includes: and representing the feasible information of the planning track information corresponding to the state to be evaluated, and carrying the identification of the feasible state of the planning track information. If it is determined that the planning track information corresponding to all the states in the to-be-evaluated state is not feasible, the determined evaluation result of whether the planning track information corresponding to the to-be-evaluated state is feasible includes: and representing information that the planning track information corresponding to the state to be evaluated is infeasible.

The planned track information corresponding to the sub-state corresponding to the top-level hierarchical state is sub-information of the planned track information corresponding to the top-level hierarchical state, that is, the planned track information corresponding to the sub-state corresponding to the top-level hierarchical state can be combined to form the planned track information corresponding to the top-level hierarchical state. If the sub-state corresponding to the top level state still has the state of the next level, the planned track information corresponding to each state of the next level of the sub-state can be combined to form the planned track information corresponding to the sub-state. And so on. The planning track information corresponding to the states which have public father states and are in the same level can be combined to form the planning track information corresponding to the father states.

For example, the states of the top level of the preset hierarchical state machine include lane keeping, lane changing and lane borrowing; the state lane change of the top level hierarchy comprises three sub-states of lane change preparation, lane change execution and lane change return. The current state of the target object is lane keeping or lane changing preparation, and the reachable state with the highest corresponding current priority is determined as the state to be evaluated based on the current priority corresponding to the top level state corresponding to each reachable state, wherein the state to be evaluated comprises lane changing preparation, lane changing execution and lane changing return; as shown in fig. 2B, the transition relationship of the time sequence stages between lane change preparation, lane change execution and lane change return represents: lane change preparation can be transited to lane change execution, lane change execution can be transited to lane change return, lane change return can be transited to lane change execution, and lane change execution is completed.

Under the condition that the current state of the target object is lane keeping or lane change preparation, the feasibility of arbitrating lane change preparation corresponding planning track information, the feasibility of executing corresponding planning track information by lane change and the feasibility of returning corresponding planning track information by lane change can be sequentially evaluated on the basis of the sequence of time sequence stage transition relations corresponding to the states to be evaluated until the planning track information corresponding to the evaluated and arbitrated states is not feasible, and whether the planning track information corresponding to the states to be evaluated is feasible or not is determined.

Under the condition that the current state of the target object is lane change execution, based on the sequence of the time sequence stage transition relation corresponding to each state to be evaluated, the feasibility of arbitrating lane change execution corresponding planning track information and the feasibility of returning corresponding planning track information by lane change can be sequentially evaluated until the planning track information corresponding to the evaluated and arbitrated state is not feasible, and whether the planning track information corresponding to the state to be evaluated is feasible or not is determined.

And under the condition that the current state of the target object is lane change return, sequentially evaluating the feasibility of arbitration lane change execution and lane change return based on the sequence of the time sequence stage transition relation corresponding to each state to be evaluated until the planning track information corresponding to the evaluated and arbitrated state is not feasible, and determining whether the planning track information corresponding to the state to be evaluated is feasible or not.

As shown in fig. 2A, if the current state of the preset hierarchical state machine, that is, the current state of the target object, is lane keeping, the electronic device determines an reachable state set corresponding to the target object based on the current state of the preset hierarchical state machine, the jump relationship between the states, the current decision-making planning related information, and the preset driving limiting condition, where the "feasible target state set" shown in fig. 2A includes: lane keeping, lane change preparation and lane change execution, i.e. the states of the preset hierarchical state machine may be executed by characterizing the lane keeping jump to lane keeping, or by the lane keeping jump to lane change preparation, or by the lane keeping jump to lane change. The electronic equipment can obtain the corresponding planning track information of each reachable state in the reachable state set; and determining an evaluation index value corresponding to the reachable state based on the planning track information corresponding to each reachable state, the hierarchy corresponding to each reachable state and the evaluation factors, and determining a target state corresponding to the target object from the reachable state based on the evaluation index value corresponding to the reachable state, namely constructing an arbitration tree.

The electronic device may construct an arbitration tree from bottom to top, that is, determine an evaluation index value corresponding to each reachable state, and accordingly, since the lane change preparation and the lane change execution have a common parent state and are in a same level state, as shown in fig. 2A, first, determine an evaluation index value corresponding to the lane change preparation based on the planning trajectory information corresponding to the lane change preparation, the level corresponding to the lane change preparation, and the evaluation factor; the method includes the steps that planning track information corresponding to lane change preparation is evaluated and arbitrated based on evaluation index values corresponding to the lane change preparation, if the evaluation index values corresponding to the lane change preparation represent the planning track information corresponding to the lane change preparation to be feasible, evaluation index values corresponding to the lane change execution are determined based on the planning track information corresponding to the lane change execution, levels corresponding to the lane change execution and evaluation factors, evaluation and arbitration are conducted on the planning track information corresponding to the lane change execution based on the evaluation index values corresponding to the lane change execution, if the evaluation index values corresponding to the lane change execution represent the planning track information corresponding to the lane change execution to be not feasible, in one case, if the execution tag corresponding to the lane change is a necessary execution tag, the corresponding electronic equipment can directly determine the lane change preparation to be in a target state. In another case, if the corresponding execution tag does not exist in the reachable state set, determining an evaluation index value corresponding to lane keeping based on the planning track information corresponding to lane keeping, the hierarchy corresponding to lane keeping and evaluation factors; and determining the optimal planned trajectory information in the planned trajectory information corresponding to the lane keeping and the planned trajectory information corresponding to the lane changing preparation based on the evaluation index value corresponding to the lane keeping and the evaluation index value corresponding to the lane changing preparation, and determining the reachable state corresponding to the optimal planned trajectory information as the target state.

Accordingly, in another embodiment of the present invention, the 023 comprises the following steps:

In this implementation manner, if the evaluation result corresponding to the state to be evaluated represents that the planning track information corresponding to the state to be evaluated is feasible, the identification of the reachable state corresponding to the feasible planning track information is determined based on the evaluation result corresponding to the state to be evaluated, and the reachable state corresponding to the corresponding time sequence stage transition relationship in the reachable state corresponding to the feasible planning track information is determined as the target state corresponding to the target object. For example: taking the above example as a support, if evaluation arbitration is performed sequentially according to the feasibility of preparing the corresponding planned track information by lane change, the feasibility of executing the corresponding planned track information by lane change, and the feasibility of returning the corresponding planned track information by lane change, where it is determined that the planned track information corresponding to lane change preparation is feasible, but the planned track information corresponding to lane change execution is not feasible, it is determined that the lane change preparation is the target state corresponding to the target object. After determining the target state, the electronic device may control the preset hierarchical state machine to jump from the current state to the target state, such as lane change preparation, based on the state transition function.

As shown in fig. 2A, the preset hierarchical state machine may support a scene configuration of a worker, so that the preset hierarchical state machine may perform an extended state and/or a modified state according to an actual usage scene.

In another embodiment of the present invention, the step S104 may include the following steps 025 and 026:

025: if it is determined that the corresponding execution tag does not exist in the reachable state set as the reachable state in which the tag needs to be executed, for each reachable state, an evaluation index value corresponding to the reachable state is determined based on the planning track information corresponding to the reachable state and the evaluation factor corresponding to the reachable state.

026: and determining the target state corresponding to the target object from all reachable states based on the evaluation index value corresponding to each reachable state.

In this implementation manner, if it is determined that there is no reachable state in the reachable state set in which the corresponding execution tag is a reachable state in which the tag must be executed, if each reachable state belongs to the same level, the selection level between the reachable states may be considered to be equal, and accordingly, the electronic device may determine, for each reachable state, an evaluation index value corresponding to the reachable state based on the planning trajectory information corresponding to the reachable state and the evaluation factor corresponding to the reachable state; and then, based on the evaluation index values corresponding to the reachable states, determining a reasonable reachable state which is relatively safe and comfortable from all reachable states as a target state corresponding to the target object.

In another implementation manner of the present invention, if it is determined that there is no reachable state in the reachable state set in which the corresponding execution tag is the necessary execution tag, and there are states belonging to different levels in each reachable state, it is inevitable that there are states that have a common parent state and are in the same level. For the states that have the public parent state and are in the same level, when determining the feasibility of the planning trajectory information corresponding to the states that have the public parent state and are in the same level, i.e., when performing the evaluation arbitration process, the timing phase transition relationship between the states that have the public parent state and are in the same level needs to be considered in combination.

If the feasible planning track information exists in the planning track information corresponding to the states which are mutually in the public father state and in the same level, the evaluation index value which is feasible and corresponds to the state which corresponds to the latest time sequence stage transition relation of the planning track information is returned to be used as a first evaluation index value, and the first evaluation index value is compared with the evaluation index value which corresponds to the father state which is mutually in the public father state and in the same level, so that the optimal state of the corresponding planning track information is determined to be used as a target state. If the evaluation index value exists in a penalty term manner, the larger the evaluation index value corresponding to the reachable state is, the more unreasonable the planning track information corresponding to the reachable state is, and accordingly, the state in which the corresponding planning track information is optimal may be the state in which the corresponding evaluation index value is the smallest.

In another embodiment of the present invention, the method may further include:

and determining a visualization signal and visualization information corresponding to the target state based on the target state, and outputting the visualization signal and the visualization information so as to correspondingly display the target object based on the visualization signal and the visualization information.

In this implementation, it is considered that, in the process of executing the driving process and executing the execution action corresponding to each state, the state to be performed and the action to be performed need to be shown to the corresponding user and other objects having an interaction relationship with the corresponding user. Correspondingly, after the target state is determined, the electronic device may determine and output the visualization signal and the visualization information corresponding to the target state based on the target state, so that the target object is correspondingly displayed based on the visualization signal and the visualization information.

The visual signal may be information for controlling the corresponding presentation of the designated presentation means of the target object determined based on the target state, such as: the target state is lane change, the visual signal is a signal used for controlling the left-turn or right-turn indicator lamp of the target object to flash or continuously light, and the specific left-turn or right-turn indicator lamp is determined based on the planning track information corresponding to the target state. The visual information is information for presentation to a user of the target object, such as: may be information describing the state of the target object about to jump, i.e. the decision result, and/or information describing the action the target object is about to perform, etc.

Corresponding to the above method embodiment, an embodiment of the present invention provides a path planning apparatus, and as shown in fig. 3, the apparatus may include:

a first obtaining module 310 configured to obtain current decision-making plan related information corresponding to a target object;

a first determining module 320, configured to determine, based on a current state of a preset hierarchical state machine, a jump relationship between states, the current decision-making planning related information, and a preset driving limiting condition, a reachable state set corresponding to the target object, where the preset hierarchical state machine includes: jump relations and hierarchical relations among the states corresponding to the target object;

a second obtaining module 330, configured to obtain planning trajectory information corresponding to each reachable state in the reachable state set;

the second determining module 340 is configured to determine a target state corresponding to the target object from all reachable states based on the planning trajectory information corresponding to each reachable state, a level corresponding to each reachable state, and an evaluation factor, where the level corresponding to a reachable state is a level of the reachable state in a preset layered state machine;

and a control module 350 configured to control the preset hierarchical state machine to jump from the current state to the target state, so that the target object travels based on the planned trajectory information corresponding to the target state.

In another embodiment of the present invention, the current decision plan related information comprises: current surrounding perception information, current pose information, current map information, and prediction information of the obstacle of the target object.

In another embodiment of the present invention, the first determining module 320 is specifically configured to pre-process the specified information in the current decision-making plan related information, and determine whether each piece of information in the current decision-making plan related information is valid;

In another embodiment of the present invention, the second determining module 340 includes:

a determining unit (not shown in the figure), configured to determine whether there is a reachable state in the reachable state set where the corresponding execution tag is an execution-required tag, where the jumping tag is: a label determined based on current surrounding awareness information and/or current map information in the current decision plan related information;

a first determining unit (not shown in the figure), configured to determine, if it is determined that there is a reachable state in the reachable state set in which the corresponding execution tag is a tag that needs to be executed, a reachable state with a highest corresponding current priority as a state to be evaluated based on a current priority corresponding to a top-level state corresponding to each reachable state; determining whether the planning track information corresponding to the state to be evaluated is feasible or not based on the planning track information corresponding to the state to be evaluated and the evaluation factor corresponding to the state to be evaluated, wherein the reachable state corresponding to the execution tag has the highest priority;

a second determining unit (not shown in the figure), configured to determine, if the evaluation result represents that the planning trajectory information corresponding to the state to be evaluated is feasible, a target state corresponding to the target object from the state to be evaluated based on the feasible planning trajectory information;

In another embodiment of the present invention, if the to-be-evaluated state includes reachable states that are in the same level and have public parent states with each other; the reachable states which have public father states and are in the same level have a time sequence stage transition relation;

the first determining unit (not shown in the figure) is specifically configured to, for to-be-evaluated states that have a common parent state with each other and are in the same level, sequentially determine, based on a sequence of time sequence stage transition relationships corresponding to the to-be-evaluated states, a reachable state that is currently not evaluated and has the first corresponding time sequence stage transition relationship, and determine the reachable state as the current to-be-evaluated state;

In another embodiment of the present invention, the second determining unit (not shown in the figure) is specifically configured to determine, as the target state corresponding to the target object, the reachable state corresponding to the last time-sequence stage transition relationship in the reachable states corresponding to the feasible planning trajectory information.

In another embodiment of the present invention, the second determining module 340 further includes:

In another embodiment of the present invention, the second obtaining module 330 is specifically configured to determine the planning trajectory information corresponding to each reachable state in the reachable state set based on a path planning algorithm corresponding to each reachable state in the reachable state set and current surrounding perception information, current pose information, current map information, and prediction information of an obstacle of the target object in the current decision-making planning related information.

In another embodiment of the present invention, the apparatus further comprises:

and a determination output module (not shown in the figures) configured to determine a visualization signal and visualization information corresponding to the target state based on the target state, and output the visualization signal and visualization information, so that the target object is correspondingly displayed based on the visualization signal and visualization information.

The system and apparatus embodiments correspond to the system embodiments, and have the same technical effects as the method embodiments, and for the specific description, refer to the method embodiments. The device embodiment is obtained based on the method embodiment, and for specific description, reference may be made to the method embodiment section, which is not described herein again. Those of ordinary skill in the art will understand that: the figures are merely schematic representations of one embodiment, and the blocks or flow diagrams in the figures are not necessarily required to practice the present invention.

Those of ordinary skill in the art will understand that: modules in the devices in the embodiments may be distributed in the devices in the embodiments according to the description of the embodiments, or may be located in one or more devices different from the embodiments with corresponding changes. The modules of the above embodiments may be combined into one module, or further split into multiple sub-modules.

Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims

1. A method of path planning, the method comprising:

determining a reachable state set corresponding to the target object based on a current state of a preset layered state machine, a jump relation among states, the current decision-making planning related information and a preset driving limiting condition, wherein the preset layered state machine comprises: jump relations and hierarchical relations among the states corresponding to the target object;

2. The method of claim 1, wherein the current decision plan related information comprises: current surrounding perception information, current pose information, current map information, and prediction information of the obstacle of the target object.

3. The method as claimed in claim 1, wherein the step of determining the reachable state set corresponding to the target object based on the current state of the preset hierarchical state machine, the jump relationship between the states, the current decision-making planning related information and the preset driving restriction condition comprises:

and under the condition that the obtained relevant information of the current decision-making plan is effective, determining a reachable state set corresponding to the target object based on the current state of a preset hierarchical state machine, the jump relation among the states, the relevant information of the current decision-making plan and a preset running limiting condition.

4. The method according to any one of claims 1 to 3, wherein the step of determining the target state corresponding to the target object from all reachable states based on the planned trajectory information corresponding to each reachable state, the hierarchy corresponding to each reachable state, and the evaluation factor comprises:

5. The method of claim 4, wherein if the states to be evaluated include reachable states that are common parent states to each other and are in the same level; the reachable states which have public father states and are in the same level have a time sequence stage transition relation;

6. The method according to claim 5, wherein the step of determining the target state corresponding to the target object from the states to be evaluated based on the feasible planning trajectory information comprises:

7. The method of claim 4, wherein the method further comprises:

8. The method of claim 1, wherein the step of obtaining planned trajectory information corresponding to each reachable state in the set of reachable states comprises:

9. The method of any one of claims 1-8, further comprising:

10. A path planning apparatus, the apparatus comprising: