A path planning method and apparatus

Abstract

An embodiment of the present invention discloses a path planning method and apparatus. The method includes: obtaining current decision-making planning related information corresponding to a target object; determining a reachable state set corresponding to the target object based on the current state of a preset hierarchical state machine, the transition relationships between states, the current decision-making planning related information, and preset driving limit conditions; obtaining planning trajectory 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 the planning trajectory information corresponding to each reachable state, the level corresponding to each reachable state, and evaluation factors, where the level corresponding to a reachable state is its level in the preset hierarchical state machine; controlling the preset hierarchical state machine to jump from the current state to the target state, so that the target object travels based on the planning trajectory information corresponding to the target state, so as to improve the rationality of path planning.

Description

Technical Field

[0001] The present invention relates to the technical field of path planning, and in particular, to a path planning method and apparatus. Background Art

[0002] In high-speed and urban road traffic, the path planning module of an autonomous vehicle needs to plan a reasonable trajectory in real time according to the map task, satisfying traffic regulations and normal human driver driving habits, and hand it over to the underlying control module for execution. At the same time, the state of the autonomous vehicle is updated and maintained in the upstream user interaction interface to show the intention and corresponding driving behavior of the vehicle to the passengers of the autonomous vehicle and the pedestrians and vehicles interacting with it around.

[0003] Currently, in the process of planning a trajectory, the path planning module generally first directly determines the target state based on the transition relationship between the states of a preset state machine and the current state, and then plans a reasonable trajectory based on the current environmental information, map information, pose information of the autonomous vehicle collected by the upper-layer information acquisition module, the target state to be jumped to, and a preset path planning algorithm.

[0004] In the above process, directly determining the target state based on the transition relationship between the states of the preset state machine and the current state, the determined target state may not be the optimal target state, and thus the determined trajectory may not be the most reasonable trajectory. Summary of the Invention

[0005] The present invention provides a path planning method and apparatus to improve the rationality of path planning. The specific technical solutions are as follows:

[0006] In a first aspect, an embodiment of the present invention provides a path planning method, the method including:

[0007] Obtain the current decision-making planning related information corresponding to the target object;

[0008] Based on the current state of the preset hierarchical state machine, the transition relationship between the states, the current decision-making planning related information, and the preset driving limit conditions, determine the reachable state set corresponding to the target object, where the preset hierarchical state machine includes: the transition relationship and hierarchical relationship between the states corresponding to the target object;

[0009] Obtain the planning trajectory information corresponding to each reachable state in the reachable state set;

[0010] Based on the planning trajectory information corresponding to each reachable state, the level and evaluation factors corresponding to each reachable state, determine the target state corresponding to the target object from all reachable states, where the level corresponding to a reachable state is its level in the preset hierarchical state machine;

[0011] 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.

[0012] Optionally, the current decision-making and planning related information includes: the current surrounding perception information of the target object, the current pose information, the current map information, and the prediction information of obstacles.

[0013] Optionally, 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 states, the current decision-making and planning related information, and the preset driving limit conditions includes:

[0014] Preprocess the specified information in the current decision-making and planning related information, and determine whether each piece of information in the current decision-making and planning related information is valid;

[0015] When it is determined that all the obtained current decision-making and planning related information is valid, based on the current state of the preset hierarchical state machine, the jump relationship between states, the current decision-making and planning related information, and the preset driving limit conditions, determine the reachable state set corresponding to the target object.

[0016] Optionally, 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 level corresponding to each reachable state, and the evaluation factors includes:

[0017] Determine whether there is a reachable state in the reachable state set whose corresponding execution label is the must-execute label, where the jump label is: the label determined based on the current surrounding perception information and / or the current map information in the current decision-making and planning related information;

[0018] If it is determined that there is a reachable state in the reachable state set whose corresponding execution label is the must-execute label, based on the current priority corresponding to the top-level state corresponding to each reachable state, determine the reachable state with the highest current priority as the state to be evaluated; based on the planned trajectory information corresponding to the state to be evaluated and the evaluation factors corresponding to the state to be evaluated, determine the evaluation result of whether the planned trajectory information corresponding to the state to be evaluated is feasible, where the reachable state corresponding to the must-execute label has the highest priority;

[0019] If the evaluation result indicates that the planned trajectory information corresponding to the state to be evaluated is feasible, then based on the feasible planned trajectory information, determine the target state corresponding to the target object from the state to be evaluated;

[0020] If the evaluation result indicates that the planned trajectory information corresponding to the state to be evaluated is infeasible, return to the step of executing the current priority corresponding to the top-level state corresponding to each reachable state, determining the reachable state with the highest current priority corresponding thereto, and using it as the state to be evaluated.

[0021] Optionally, if the states to be evaluated include reachable states that have a common parent state and are at the same level; there is a time-sequence stage transition relationship between the reachable states that have a common parent state and are at the same level;

[0022] The step of determining the evaluation result of whether the planned trajectory information corresponding to the state to be evaluated is feasible based on the planned trajectory information corresponding to the state to be evaluated and the evaluation factors corresponding to the state to be evaluated includes:

[0023] For the states to be evaluated that have a common parent state and are at the same level, based on the sequence of the time-sequence stage transition relationships corresponding to each state to be evaluated, sequentially determine the reachable state that has not been evaluated yet and has the earliest corresponding time-sequence stage transition relationship as the current state to be evaluated;

[0024] Based on the planned trajectory information corresponding to the current state to be evaluated and the evaluation factors corresponding to the current state to be evaluated, determine the evaluation index value corresponding to the current state to be evaluated;

[0025] If the rating index value corresponding to the current state to be evaluated indicates that the planned trajectory information corresponding to the current state to be evaluated is feasible, determine whether there is an unevaluated state among the states to be evaluated;

[0026] If it is determined that there is, return to the step of determining the reachable state that has not been evaluated yet and has the earliest corresponding time-sequence stage transition relationship as the current state to be evaluated from the states to be evaluated;

[0027] If it is determined that there is no, or it is determined that the planned trajectory information corresponding to the current state to be evaluated is infeasible, obtain the evaluation result of whether the planned trajectory information corresponding to the state to be evaluated is feasible.

[0028] Optionally, the step of determining the target state corresponding to the target object from the states to be evaluated based on the feasible planned trajectory information includes:

[0029] Determine the reachable state with the last corresponding time-sequence stage transition relationship among the reachable states corresponding to the feasible planned trajectory information as the target state corresponding to the target object.

[0030] Optionally, the method further includes:

[0031] If it is determined that there is no reachable state in the set of reachable states whose corresponding execution tag is the mandatory execution tag, for each reachable state, based on the planned trajectory information corresponding to the reachable state and the evaluation factors corresponding to the reachable state, determine the evaluation index value corresponding to the reachable state;

[0032] Based on the evaluation index values corresponding to each reachable state, determine the target state corresponding to the target object from all reachable states.

[0033] Optionally, the step of obtaining the planned trajectory information corresponding to each reachable state in the set of reachable states includes:

[0034] Based on the path planning algorithms corresponding to each reachable state in the set of reachable states, and the current surrounding perception information, current pose information, current map information, and predicted information of obstacles of the target object in the current decision-making plan related information, determine the planned trajectory information corresponding to each reachable state in the set of reachable states.

[0035] Optionally, the method further includes:

[0036] Based on the target state, determine the visualization signal and visualization information corresponding to the target state, and output them, so that the target object performs corresponding display based on the visualization signal and visualization information.

[0037] In a second aspect, an embodiment of the present invention provides a path planning device, and the device includes:

[0038] A first obtaining module, configured to obtain the current decision-making plan related information corresponding to the target object;

[0039] A first determining module, configured to determine the set of reachable states corresponding to the target object based on the current state of the preset hierarchical state machine, the jump relationships between states, the current decision-making plan related information, and the preset driving limit conditions, where the preset hierarchical state machine includes: the jump relationships and hierarchical relationships between the states corresponding to the target object;

[0040] A second obtaining module, configured to obtain the planned trajectory information corresponding to each reachable state in the set of reachable states;

[0041] A second determining module, configured to determine the target state corresponding to the target object from all reachable states based on the planned trajectory information corresponding to each reachable state, the level and evaluation factors corresponding to each reachable state, where the level corresponding to the reachable state is its level in the preset hierarchical state machine;

[0042] The control module is 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.

[0043] Optionally, the current decision-making and planning related information includes: the current surrounding perception information of the target object, the current pose information, the current map information, and the prediction information of the obstacles.

[0044] Optionally, the first determination module is specifically configured to preprocess the specified information in the current decision-making and planning related information, and determine whether each piece of information in the current decision-making and planning related information is valid;

[0045] When it is determined that all the currently obtained decision-making and planning related information is valid, based on the current state of the preset hierarchical state machine, the jump relationship between states, the current decision-making and planning related information, and the preset driving limit conditions, determine the reachable state set corresponding to the target object.

[0046] Optionally, the second determination module includes:

[0047] A judgment unit configured to judge whether there is a reachable state in the reachable state set whose corresponding execution label is a mandatory execution label, where the jump label is: a label determined based on the current surrounding perception information and / or the current map information in the current decision-making and planning related information;

[0048] A first determination unit configured to, if it is determined that there is a reachable state in the reachable state set whose corresponding execution label is a mandatory execution label, based on the current priority corresponding to the top-level state corresponding to each reachable state, determine the reachable state with the highest current priority as the state to be evaluated; based on the planned trajectory information corresponding to the state to be evaluated and the evaluation factors corresponding to the state to be evaluated, determine the evaluation result of whether the planned trajectory information corresponding to the state to be evaluated is feasible, where the reachable state corresponding to the mandatory execution label has the highest priority;

[0049] A second determination unit configured to, if the evaluation result indicates that the planned trajectory information corresponding to the state to be evaluated is feasible, based on the feasible planned trajectory information, determine the target state corresponding to the target object from the states to be evaluated;

[0050] If the evaluation result indicates that the planned trajectory information corresponding to the state to be evaluated is not feasible, then trigger the first determination unit to return.

[0051] Optionally, if the states to be evaluated include reachable states that have a common parent state and are at the same level; there is a time-sequence stage transition relationship between the reachable states that have a common parent state and are at the same level;

[0052] The first determination unit is specifically configured to, for the to-be-evaluated states that have a common parent state and are at the same level, determine, in sequence according to the order of the time-sequence stage transition relationships corresponding to the to-be-evaluated states, the reachable state that has not been evaluated currently and whose corresponding time-sequence stage transition relationship is the earliest as the current to-be-evaluated state;

[0053] Based on the planned trajectory information corresponding to the current to-be-evaluated state and the evaluation factors corresponding to the current to-be-evaluated state, determine the evaluation index value corresponding to the current to-be-evaluated state;

[0054] If the rating index value corresponding to the current to-be-evaluated state indicates that the planned trajectory information corresponding to the current to-be-evaluated state is feasible, determine whether there is an unevaluated state among the to-be-evaluated states;

[0055] If it is determined that there is, return to the step of determining, from the to-be-evaluated states, the unevaluated reachable state whose corresponding time-sequence stage transition relationship is the earliest as the current to-be-evaluated state;

[0056] If it is determined that there is none, or it is determined that the planned trajectory information corresponding to the current to-be-evaluated state is not feasible, obtain the evaluation result of whether the planned trajectory information corresponding to the to-be-evaluated state is feasible.

[0057] Optionally, the second determination unit is specifically configured to determine, as the target state corresponding to the target object, the reachable state with the last corresponding time-sequence stage transition relationship among the reachable states corresponding to the feasible planned trajectory information.

[0058] Optionally, the second determination module further includes:

[0059] A third determination unit, configured to, if it is determined that there is no reachable state in the reachable state set whose corresponding execution label is the must-execute label, for each reachable state, based on the planned trajectory information corresponding to the reachable state and the evaluation factors corresponding to the reachable state, determine the evaluation index value corresponding to the reachable state;

[0060] Based on the evaluation index values corresponding to the reachable states, determine, from all the reachable states, the target state corresponding to the target object.

[0061] Optionally, the second obtaining module is specifically configured to determine the planned trajectory information corresponding to each reachable state in the reachable state set based on the path planning algorithms corresponding to the reachable states in the reachable state set and the current surrounding perception information, current pose information, current map information, and predicted information of obstacles of the target object in the current decision-making plan-related information.

[0062] Optionally, the device further includes:

[0063] Determine an output module, 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 performs corresponding display based on the visualization signal and visualization information.

[0064] As can be seen from the above, a path planning method and apparatus provided by an embodiment of the present invention obtain current decision-making planning related information corresponding to a target object; determine a reachable state set corresponding to the target object based on the current state of a preset hierarchical state machine, the jump relationships between states, the current decision-making planning related information, and a preset driving limit condition, where the preset hierarchical state machine includes: the jump relationships and hierarchical relationships between states of the target object; obtain the planned trajectory information corresponding to each reachable state in the reachable state set; determine the target state corresponding to the target object from all reachable states based on the planned trajectory information corresponding to each reachable state, the level corresponding to each reachable state, and evaluation factors, where the level corresponding to a reachable state is its level in the preset hierarchical state machine; 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.

[0065] By applying the embodiment of the present invention, it is possible to first determine a reachable state set that can be jumped to from the next state of a preset hierarchical state machine based on the current state of the preset hierarchical state machine, the jump relationships between states, the current decision-making planning related information, and the preset driving limit condition, that is, to determine the reachable state set of the target object at the next moment corresponding to the preset hierarchical state machine, and then use the rationality of the planned trajectory information corresponding to each reachable state to determine the reachable state with the most reasonable planned trajectory information from the reachable state set, that is, the target state, so as to realize the rational and accurate determination of the state of the target object at the next moment, improve the rationality of path planning, and moreover, in the planning process, first determine the reachable state, and then obtain the planned trajectory information corresponding to the reachable state, so as to determine the target state from the reachable states through the evaluation of the planning information. This planning framework is more generalizable, extensible, and interpretable, and can quickly define and embed new scenarios and action modes for newly emerging practical problems and scenarios, and adapt to new path planning algorithms. Of course, any product or method implementing the present invention does not necessarily need to achieve all the above advantages at the same time.

[0066] The innovation points of the embodiment of the present invention include:

[0067] 1. First, determine the reachable state set, and then analyze the evaluation results of the planned trajectory information corresponding to each reachable state in the reachable state set. Determine the most reasonable reachable state from the reachable state set as the target state, so as to realize the rational and accurate determination of the state of the target object at the next moment and improve the rationality of path planning. Moreover, in the planning process, first determine the reachable state, and then obtain the planned trajectory information corresponding to the reachable state, so as to determine the target state from the reachable states through the evaluation of the planning information. This planning framework is more generalizable, extensible, and interpretable, and can quickly define and embed new scenarios and action patterns for newly emerging practical problems and scenarios, and adapt to new path planning algorithms.

[0068] 2. First, determine the effectiveness of each piece of information in the current decision-making plan-related information. When all the current decision-making plan-related information is effective, execute the subsequent path planning process to ensure the safety and rationality of path planning.

[0069] 3. When there is a reachable state in the reachable state set whose corresponding execution label is the must-execute label, that is, there is a reachable state that must be executed. In this case, use the current priority to evaluate and arbitrate the reachable state with the must-execute label first. When it is determined that the corresponding planned trajectory information is feasible, directly determine this reachable state as the target state. When it is determined that the planned trajectory corresponding to the reachable state with the must-execute label and the reachable state with the highest priority is not feasible, arbitrate downward in turn to ensure that the determined target state is more reasonable and more in line with the current environmental conditions.

[0070] 4. When there is no reachable state in the reachable state set whose corresponding execution label is the must-execute label, the evaluation index values corresponding to each reachable state can be determined in parallel to determine the most reasonable reachable state as the target state.

[0071] 5. For the sub-states with a common parent state, set the time-sequence stage transition relationship, and determine the evaluation index values corresponding to each sub-state in combination with the time-sequence stage transition relationship, that is, determine the feasibility of the planned trajectory information corresponding to each sub-state. Through the time-sequence stage transition relationship, limit the execution order of the sub-states with a common parent state to ensure the optimality and coherence of the state transitions of the target object. Brief Description of the Drawings

[0072] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0073] Figure 1 It is a schematic flowchart of a path planning method provided by an embodiment of the present invention;

[0074] Figure 2A and 2B It is a schematic diagram of the state transition logic of a preset hierarchical state machine;

[0075] Figure 3 It is a schematic structural diagram of a path planning device provided by an embodiment of the present invention. Detailed implementation manners

[0076] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0077] It should be noted that the terms "including" and "having" in the embodiments of the present invention and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally further include steps or units not listed, or may optionally further include other steps or units inherent to these processes, methods, products, or devices.

[0078] The present invention provides a path planning method and device to improve the rationality of path planning. The embodiments of the present invention will be described in detail below.

[0079] Figure 1 It is a schematic flowchart of a path planning method provided by an embodiment of the present invention. The method may include the following steps:

[0080] S101: Obtain the current decision-making planning related information corresponding to the target object.

[0081] The path planning method provided by the embodiments of the present invention can be applied to any electronic device with computing capabilities, and the electronic device can be a terminal or a server. In one implementation, the functional software for implementing the path planning method may exist in the form of a separate client software, or may exist in the form of a plugin of the current related client software. For example, it may exist in the form of a functional module of an autonomous driving system, which is all possible.

[0082] Among them, the target object can be an object that needs to perform path planning, such as an autonomous driving vehicle and a robot. In one implementation, when the target object is an autonomous driving vehicle, the electronic device implementing the path planning method can be an in-vehicle device, which is set on the target object and can directly obtain the current decision-making and planning related information corresponding to the target object. In another case, the electronic device implementing the path planning method can also be a non-vehicle-mounted device. Correspondingly, the electronic device can be connected to the data processing device corresponding to the target object to obtain the current decision-making and planning related information corresponding to the target object sent by the data processing device corresponding to the target object.

[0083] In one implementation manner of the present invention, the current decision-making and planning related information may include, but is not limited to: the current surrounding perception information of the target object, the current pose information, the current map information, and the prediction information of obstacles. Among them, the current map information may refer to the map information corresponding to the environment where the target object is located. The prediction information of obstacles may include, but is not limited to: the predicted driving trajectory of the obstacle and the driving parameter information.

[0084] The current decision-making and planning related information is information used to assist in decision-making and path planning. Among them, decision-making and planning is to determine the state that the target object needs to jump to, and then the target object travels based on the path information corresponding to the state that needs to be jumped to, so as to achieve path planning. The current decision-making and planning related information is information determined based on the sensor data collected by the sensors set on the target object. The sensors set on the target object may include, but are not limited to: image acquisition devices, wheel speed sensors, radars, IMUs (Inertial Measurement Unit, inertial measurement unit), GPSs (Global Positioning System, global positioning system), and GNSSs (Global Navigation Satellite System, global satellite navigation system / global navigation satellite system), etc.

[0085] S102: Determine the reachable state set corresponding to the target object based on the current state of the preset hierarchical state machine, the jump relationships between states, the current decision-making and planning related information, and the preset driving limit conditions.

[0086] The preset hierarchical state machine includes: the jump relationships and hierarchical relationships between the various states corresponding to the target object.

[0087] The preset hierarchical state machine is pre-stored in the local electronic device or the connected storage device. The preset hierarchical state machine contains various states corresponding to the target object, and the jump relationships and hierarchical relationships between the various states corresponding to the target object are included in the preset hierarchical state machine.

[0088] Among them, the preset hierarchical state machine includes states at the same level and states at different levels. Different states can represent different execution actions of the target object, that is, a certain state at a certain level in the preset hierarchical state machine can display and represent a certain action mode of the target object. The transition of the states of the preset hierarchical state machine can control the corresponding execution actions of the target object, that is, the transition of the action mode.

[0089] The states at the next level corresponding to the states at a certain level can be called the sub-states of this state. Different sub-states corresponding to the state can be considered as: the decomposition or stage division of the action mode corresponding to this state. For example: The target object is an autonomous vehicle. As Figure 2A shown, the preset hierarchical state machine, that is, Figure 2A the "hierarchical state machine" described in can include: states at the first level, that is, the top level, such as lane keeping, lane change, and borrowing a lane. Among them, the lane change can include sub-states at the second level, such as lane change preparation and lane change execution. In addition, the lane change can also include a lane change return sub-state. Correspondingly, this preset hierarchical state machine can include two levels of states. For example: The preset hierarchical state machine includes: states at the first level, such as lane keeping and pulling over. Among them, pulling over can include sub-states at the second level, such as deceleration and pulling over execution.

[0090] According to the further division of different action modes of the target object, that is, the execution actions, a preset hierarchical state machine including states with more levels can also be constructed. For example: The sub-state of lane change execution at the second level can also include: lower-level sub-states such as driving towards the target lane, entering the target lane, and driving on the target lane, and so on.

[0091] It can be understood that it can be considered that the states at the lowest level in the preset hierarchical state machine correspond to specific detailed scenarios. For example: Based on the above example, the target object is in a scenario where lane change preparation is required, the target object is in a scenario where lane change execution is required, etc.; lane keeping does not correspond to the states at the next level, and the target object is in a scenario where the target object is keeping in the lane. It needs to perform a complete trajectory planning and obtain the corresponding planned trajectory information.

[0092] The preset driving limit conditions are conditions that limit the driving mode of the target object. For example, the preset driving limit conditions may include traffic rules that need to be observed in the area where the target object is located, may also include the limit conditions corresponding to the tasks executed by the target object, and may also include empirically and generally recognized conditions added manually to restrict the driving behavior of the target object. In one case, the empirically and generally recognized conditions added manually include, but are not limited to: conditions for limiting the number and constraint range of calculation scenarios required, and the number of scenarios is determined by the data of the reachable states determined. The tasks executed by the target object may include, but are not limited to: the task of the target object needing to drive to each destination; the task of driving actions that need to be completed during the driving process of the target object, etc.

[0093] In the embodiment of the present invention, the function of allowing manual addition of conditions can be retained so that other conditions can be added and opened after the expansion of the path planning ability boundary of the subsequent electronic device.

[0094] In order to plan a better path and make a better decision, it is necessary to ensure the coherence of a series of determined states, that is, the execution actions of the target object. For example: for a target object in a turning situation, the previous state is a left turn. To maintain the coherence of the action, the subsequent state should be a left turn to avoid the problem that the target object turns left and right alternately in a turning situation. Correspondingly, it is necessary to determine the reachable state set in combination with the current state of the preset hierarchical state machine.

[0095] In this step, the electronic device can detect the current state of the preset hierarchical state. Furthermore, based on the current state of the preset hierarchical state machine and the jump relationship between states, the states that can be jumped from the current state are determined from the states of the preset hierarchical state machine as standby states. Furthermore, based on the current decision-making planning related information and the preset driving limit conditions, the states that meet the preset driving limit conditions and / or conform to the current decision-making planning related information are selected from the standby states as the reachable states corresponding to the target object, so as to obtain the reachable state set corresponding to the target object.

[0096] For example: the preset driving limit conditions include: the condition that it is prohibited to jump from lane keeping to lane changing when the target object enters the line of sight area. Based on the current decision-making planning related information, it is determined that there is an accident vehicle in front of the target object or a pedestrian suddenly appears and quickly crosses from the blind area of the target object. In such a situation, in order to avoid the collision risk, the target object needs to violate the preset driving limit conditions by pressing the solid line to avoid the collision risk, so as to ensure the safety of the target object, that is, the safety of other vehicles and pedestrians. Correspondingly, at this time, lane changing is determined as a reachable state.

[0097] S103: Obtain the planned trajectory information corresponding to each reachable state in the reachable state set.

[0098] Among them, the planned trajectory information includes, but is not limited to: the trajectory information that the target object needs to travel after jumping to the corresponding reachable state, the driving parameter information of the target object, and the relevant driving parameter information of other objects that have an interaction relationship with the target object.

[0099] The driving parameter information of the target object may include, but is not limited to: average speed information, acceleration information, and turning angle information. The relevant driving parameter information of other objects that have an interaction relationship with the target object may include, but is not limited to: average speed information, acceleration information, and turning angle information.

[0100] Other objects that have an interaction relationship with the target object may refer to: objects that avoid the target object and / or objects that the target object avoids, that is, objects affected by the actions performed by the target object. For example, when the target object changes lanes, the object behind the target position of the target lane to which it needs to change lanes, and the target position is the position where the target object inserts when changing lanes.

[0101] In one case, after the electronic device determines the reachable state set, it sends the reachable state set, the current state, the current decision-making plan related information, and the preset driving limit conditions to other devices, so that other devices can determine the corresponding planned trajectory information for each reachable state and send it to the electronic device. Correspondingly, the electronic device obtains the planned trajectory information corresponding to each reachable state in the reachable state set.

[0102] In one implementation manner of the present invention, each state in the preset hierarchical state machine corresponds to a corresponding path planning algorithm for planning a path. After the electronic device determines the reachable state set, for each reachable state in the reachable state set, based on the path planning algorithm corresponding to the reachable state, the current surrounding perception information, the current pose information, the current map information, and the prediction information of obstacles of the target object in the current decision-making plan related information, it determines the planned trajectory information corresponding to the reachable state.

[0103] S104: Based on the planned trajectory information corresponding to each reachable state, the level corresponding to each reachable state, and the evaluation factors, determine the target state corresponding to the target object from all reachable states.

[0104] Among them, the level corresponding to the reachable state is its level in the preset hierarchical state machine.

[0105] For each reachable state, the electronic device determines the evaluation index value corresponding to the reachable state based on the trajectory planning information corresponding to the reachable state, the level corresponding to the reachable state, and the evaluation factors. Furthermore, based on the evaluation index values corresponding to each reachable state, it determines the reachable state that represents the most reasonable trajectory planning information from all reachable states as the target state corresponding to the target object.

[0106] Among them, when the evaluation index value exists in the form of a penalty term, that is, the lower the evaluation index value, the more reasonable the trajectory planning information corresponding to the reachable state, the most reasonable reachable state can refer to the reachable state with the smallest numerical value of the corresponding evaluation index value; when the evaluation index value exists in the form of a non-penalty term, that is, the higher the evaluation index value, the more reasonable the trajectory planning information corresponding to the reachable state, the most reasonable reachable state can refer to the reachable state with the largest numerical value of the corresponding evaluation index value.

[0107] Among them, the process of determining the evaluation index value corresponding to each reachable state according to the trajectory planning information corresponding to each reachable state, the level corresponding to each reachable state, and the evaluation factors can be understood as the process of constructing an arbitration tree for this reachable state set, that is, the process of evaluating and arbitrating the planned trajectory information corresponding to each reachable state. After the arbitration tree is constructed, that is, after the evaluation index values corresponding to each reachable state are determined, the target state with the most reasonable corresponding trajectory planning information obtained finally can be determined based on the principle of depth-first, and its corresponding trajectory planning information can be determined.

[0108] In one case, the evaluation factors may include but are not limited to: the safety, comfort, traffic efficiency of the trajectory, as well as factors such as preset driving limit conditions and the tasks performed by the target object.

[0109] Among them, in the process of evaluating and arbitrating the planned trajectory information corresponding to the states of different levels, different combinations of evaluation factors are generally used to avoid the situation of local optimality. For the evaluation and arbitration of the states at the lower level, factors such as different avoidance decisions for specific obstacles, that is, safety, etc. need to be considered, and factors such as the tasks performed by the target object and the scene environment where it is located can be not considered; for the evaluation and arbitration of the states at the higher level, factors such as the tasks performed by the target object, the scene environment where it is located, and the specific requirements of the traffic rules in the area where it is located need to be considered.

[0110] In one case, the evaluation factors may include but are not limited to: the safety of the trajectory, the comfort of the trajectory, the traffic efficiency of the trajectory, and the preset execution penalty term corresponding to the trajectory.

[0111] Among them, the determination of the evaluation index value corresponding to the safety of the trajectory can be based on the planned trajectory in the planned trajectory information corresponding to the reachable state and the predicted trajectories of other objects that have no interaction relationship with the target object, and collision detection is carried out in the space-time dimension. It is necessary to consider the uncertainty of the prediction intention and the distribution of the trajectory points of the predicted trajectories of other objects that have no interaction relationship with the target object to measure the probability information of the collision of the planned trajectory in the planned trajectory information corresponding to the reachable state. It can be used when evaluating and arbitrating different avoidance decisions of obstacles in a determined scenario. For example, when the target object is in the lane-changing stage, it is used to select the position to be inserted into the target road to be changed, that is, the gap between which two objects in the target road.

[0112] Here, only the objects that have no interaction with the host vehicle are considered in the collision check. Here, it is further explained that the objects that have no interaction generally refer to the vehicles whose own behaviors and trajectories do not interfere with each other, or the host vehicle's behavior will not affect the behavior of other vehicles (such as the vehicle in front that maintains the lane). It needs to be comprehensively judged in combination with the scenario; the objects that have interaction refer to the behavior of the host vehicle (to complete the task or ensure safety) will affect other vehicles. For example, when the host vehicle changes lanes, the vehicle behind in the target lane. From the algorithm perspective, empirical rules will be used to screen out the targets that need to interact and those that do not need to interact.

[0113] In one implementation, the rough mode or the precise mode can be used to set the safety threshold of the trajectory to determine whether the planned trajectory is safe and feasible. The specific formula (1) is as follows:

[0114]

[0115] Among them, J safety represents the evaluation index value corresponding to the safety of the planned trajectory; p collide represents the probability information of the collision of the planned trajectory in the planned trajectory information corresponding to the reachable state calculated in the precise mode; k collide represents the preset weight coefficient in the precise mode; n collide represents the information on whether the planned trajectory in the planned trajectory information corresponding to the reachable state collides in the rough mode.

[0116] p collideThe calculation depends on the prediction information of obstacles in the current decision-making planning-related information. Among them, the obstacle prediction information includes the predicted trajectory of the obstacle. Each predicted trajectory corresponding to an obstacle includes multiple trajectory points. There are two ways to calculate it. First, for each obstacle, sample the trajectory points in the predicted trajectory corresponding to the obstacle to obtain the collision trajectory corresponding to the obstacle. The collision trajectory corresponding to the obstacle includes multiple sampled trajectory points. For each obstacle, use the sampled trajectory point at a certain moment in the collision trajectory corresponding to the obstacle and the trajectory point at the same moment in the planned trajectory corresponding to the reachable state of the target object to perform point-by-point collision checking, and count the number of sampled trajectory points corresponding to the obstacle that have a collision. For each obstacle, use the number of sampled trajectory points corresponding to the obstacle that have a collision and the total number of trajectory points to calculate the ratio of the number of trajectory points corresponding to the obstacle that have a collision to the total number of trajectory points as the ratio corresponding to the obstacle. According to the ratios corresponding to all obstacles, determine the collision probability information corresponding to the planned trajectory information corresponding to the reachable state.

[0117] Among them, the process of performing point-by-point collision checking using the sampled trajectory point at a certain moment in the collision trajectory corresponding to the obstacle and the trajectory point at the same moment in the planned trajectory corresponding to the reachable state of the target object is as follows: According to the pose information of the target object at a certain moment and the polygonal model representing the target object, as well as the pose information of the obstacle and the polygonal model representing the obstacle, determine whether there is a position overlap between the target object and the obstacle at a certain moment. If there is a position overlap, a collision occurs; otherwise, if there is no position overlap, no collision occurs. The total number of trajectory points can refer to the total number of trajectory points in the planned trajectory corresponding to the reachable state of the target object, or the total number of trajectory points in the predicted trajectory obtained by sampling.

[0118] The process of determining the collision probability information corresponding to the planned trajectory information corresponding to the reachable state according to the ratios corresponding to all obstacles can be: count the number of obstacles whose corresponding ratios exceed the preset ratio threshold, and based on this number and the total number of obstacles, determine the collision probability information corresponding to the planned trajectory information corresponding to the reachable state.

[0119] Second: Point by point, obtain the collision probability of the trajectory point according to the relative position between the trajectory point in the planned trajectory corresponding to the reachable state of the target object and the trajectory point in the predicted trajectory information of the obstacle, and the spatial probability distribution of the trajectory point in the predicted trajectory information of the obstacle. Select the collision probability of the trajectory point with the largest value as the collision probability corresponding to the planned trajectory information corresponding to the reachable state of the target object.

[0120] Among them, for the process of obtaining the collision probability of the trajectory points, any method in the related art that can determine the collision probability of two trajectories can be referred to. For example, when the spatial probability distribution of the trajectory points in the predicted trajectory information of the obstacle is discretely expressed, the spatial probability distribution of the trajectory points in the predicted trajectory information of the obstacle and the weights corresponding to each pair of trajectory points can be directly used to compare with the trajectory points in the planned trajectory of the target object to determine the collision probability of the trajectory points. When the spatial probability distribution of the trajectory points in the predicted trajectory information of the obstacle is continuous and integrable, the target object can be simplified to a circular model to determine the collision between the trajectory points of the planned trajectory of the target object and the trajectory points in the predicted trajectory information of each obstacle, and obtain the collision probability of the trajectory points, etc.

[0121] Among them, the selection of using the rough mode or the precise mode can be set according to the actual situation, such as the scenario. There is a corresponding relationship between the scenario and the state.

[0122] The evaluation index value corresponding to the safety of the trajectory exists in the form of a penalty term. The larger the evaluation index value corresponding to the safety of the trajectory, the lower the safety of the trajectory corresponding to the planned trajectory information of the reachable state.

[0123] To determine the evaluation index value corresponding to the traffic efficiency of the trajectory, it is necessary to consider the average speed v of the planned trajectory in the planned trajectory information corresponding to the reachable state of the target object, and also consider the average speed change Δv of the i-th object in the object set Φ having an interaction relationship with the target object due to avoiding the target object. i ; For objects with different priorities, they can be distinguished by the coefficient k i which is a preset value. Among them, in the evaluation index value corresponding to the traffic efficiency of the trajectory, the determination process of the evaluation index value part corresponding to each object in the object set Φ having an interaction relationship with the target object can be expressed by the following formula (2):

[0124] J interaction =∑ i∈Φ -k i Δv i ; (2)

[0125] Among them, J interaction represents the value of the evaluation index value part corresponding to each object in the object set Φ having an interaction relationship with the target object in the evaluation index value corresponding to the traffic efficiency of the trajectory. Δv i can be determined from the current surrounding perception information.

[0126] The evaluation index value corresponding to the traffic efficiency of the trajectory exists in the form of a penalty term. The larger the evaluation index value corresponding to the traffic efficiency of the trajectory, the lower the traffic efficiency of the trajectory corresponding to the planned trajectory information of the reachable state.

[0127] To determine the evaluation index value corresponding to the comfort of the trajectory, on the one hand, the acceleration a corresponding to the planned trajectory in the planned trajectory information corresponding to the reachable state of the target object can be considered. Correspondingly, the determination method of the first part value in the evaluation index value corresponding to the comfort of the trajectory can be expressed by the following formula (3);

[0128] J comfort = k comfort * a; (3)

[0129] Among them, J comfort represents the first part value in the evaluation index value corresponding to the comfort of the trajectory, and k comfort represents the coefficient value corresponding to the acceleration a, which is a preset value.

[0130] On the other hand, in situations such as lane change or turning, the determination of the evaluation index value corresponding to the comfort of the trajectory can also consider the generated lateral acceleration a lat , and correspondingly, the determination method of the second part value in the evaluation index value corresponding to the comfort of the trajectory can be expressed by the following formula (4);

[0131] J LCManeuver = k LCManeuver * a lat ; (4)

[0132] Among them, J LCManeuver represents the second part value in the evaluation index value corresponding to the comfort of the trajectory, and k LCManeuver represents the coefficient value corresponding to the lateral acceleration a, which is a preset value.

[0133] The evaluation index value corresponding to the comfort of the trajectory exists in the form of a penalty term. The larger the evaluation index value corresponding to the comfort of the trajectory, the lower the comfort of the trajectory corresponding to the planned trajectory information corresponding to the reachable state.

[0134] In the process of determining the evaluation index value corresponding to the planned trajectory information corresponding to the reachable state, it can be represented by n LCNeed ∈ {0, 1} whether the execution label corresponding to the reachable state is a mandatory execution label. Among them, it can be that when n LCNeed is 1, it means that the execution label corresponding to the reachable state is a mandatory execution label, and when n LCNeed is 0, it means that the execution label corresponding to the reachable state is not a mandatory execution label. Whether to add the preset execution penalty term J LCNeed corresponding to the trajectory is determined according to whether the execution label corresponding to the reachable state is a mandatory execution label.

[0135] S105: 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.

[0136] After the electronic device determines the target state, it can control the preset hierarchical state machine to jump from the current state to the target state and output the planned trajectory information corresponding to the target state, so that the target object travels based on the planned trajectory information corresponding to the target state.

[0137] Applying the embodiments of the present invention, based on the current state of the preset hierarchical state machine, the jump relationships between states, the current decision-making planning related information, and the preset driving limit conditions, the reachable state set that can be jumped to from the next state of the preset hierarchical state machine is determined, that is, the reachable state set of the target object corresponding to the preset hierarchical state machine at the next moment is determined. Furthermore, using the rationality of the planned trajectory information corresponding to each reachable state, the reachable state with the most reasonable corresponding planned trajectory information in the reachable state set is determined, that is, the target state, to realize the rational and accurate determination of the state of the target object at the next moment, improve the rationality of path planning, and, during the planning process, first determine the reachable states, and then obtain the planned trajectory information corresponding to the reachable states, so as to determine the target state from the reachable states through the evaluation of the planning information. This planning framework is more generalizable, extensible, and interpretable, and can quickly define and embed new scenarios and action modes for newly emerging practical problems and scenarios, and adapt to new path planning algorithms.

[0138] In another embodiment of the present invention, S102 may include the following steps 011 - 012:

[0139] 011: Preprocess the specified information in the current decision-making planning related information and determine whether each piece of information in the current decision-making planning related information is valid.

[0140] 012: When it is determined that all the currently obtained decision-making planning related information is valid, based on the current state of the preset hierarchical state machine, the jump relationships between states, the current decision-making planning related information, and the preset driving limit conditions, determine the reachable state set corresponding to the target object.

[0141] In this implementation manner, in order to ensure the accuracy of subsequent decision-making results and path planning, after the electronic device obtains the current decision-making planning related information, it preprocesses the specified information in the current decision-making planning related information. For example, use the current pose information and its previous historical pose information to determine the driving trajectory of the target object; use the current surrounding perception information and historical surrounding perception information to determine the driving trajectories of each perception target in the current surrounding perception information, etc.

[0142] Furthermore, based on the specific data of each piece of information in the preprocessing result and the current decision-making and planning-related information, it is determined whether each piece of information in the current decision-making and planning-related information is valid. For example: based on the specific value of the current pose information in the current decision-making and planning-related information and the determined driving trajectory of the target object, it is determined whether the current pose information is accurate; based on the position information and type of each perceived target and the driving trajectory of each perceived target in the current surrounding perception information, it is determined whether the current surrounding perception information is accurate, and it is determined whether there are missed detections and false detections of the perceived targets, and whether the position information of the perceived targets is accurate, etc. Based on the specific value of the prediction information of the obstacle, it is determined whether the prediction information of the obstacle is accurate.

[0143] In the case where it is determined that all pieces of information in the current decision-making and planning-related information are valid, the subsequent path planning process is executed. To ensure the accuracy of the subsequent decision-making results and the path planning.

[0144] In another implementation, in the case where it is determined that not all pieces of information in the current decision-making and planning-related information are valid, the electronic device can determine the deceleration trajectory information based on the valid information in the current decision-making and planning-related information, so as to control the target object to decelerate based on the deceleration trajectory information. And reset the state of the preset hierarchical state machine. For example: the state of the preset hierarchical state machine can be reset to its specified state to ensure the safety of the target object and other objects that have an interaction relationship with it.

[0145] In one case, when the target object is an autonomous vehicle, after the autonomous driving system of the target object is started, the electronic device can operate at a fixed frequency. After obtaining a frame of current decision-making and planning-related information, it can preprocess the specified information in the current decision-making and planning-related information and determine whether each piece of information in the current decision-making and planning-related information is valid.

[0146] In another embodiment of the present invention, S104 may include the following steps 021-024:

[0147] 021: Determine whether there is a reachable state in the reachable state set whose corresponding execution label is the must-execute label.

[0148] Wherein, the jump label is: the label determined based on the current surrounding perception information and / or the current map information in the current decision-making and planning-related information.

[0149] 022: If it is determined that there is a reachable state in the reachable state set whose corresponding execution label is the mandatory execution label, based on the current priorities corresponding to the top-level hierarchical states corresponding to each reachable state, determine the reachable state with the highest current priority as the state to be evaluated; based on the planned trajectory information corresponding to the state to be evaluated and the evaluation factors corresponding to the state to be evaluated, determine the evaluation result of whether the planned trajectory information corresponding to the state to be evaluated is feasible.

[0150] Among them, the reachable state corresponding to the mandatory execution label has the highest priority.

[0151] 023: If the evaluation result indicates that the planned trajectory information corresponding to the state to be evaluated is feasible, then based on the feasible planned trajectory information, determine the target state of the target object from the states to be evaluated.

[0152] 024: If the evaluation result indicates that the planned trajectory information corresponding to the state to be evaluated is not feasible, then return to execute 022.

[0153] When determining the next state of the target object, that is, determining the planned trajectory of the target object, it is necessary to give priority to the safety of the target object and other objects that have an interaction relationship with it. Based on the current surrounding perception information, current pose information, and the surrounding situation represented by the current map information in the current decision-making and planning related information, there will inevitably be situations where the target object needs to perform certain actions to avoid danger to the target object and / or other objects that have an interaction relationship with the target object. Correspondingly, there will inevitably be a distinction between mandatory execution and non-mandatory execution among the determined reachable states. To ensure the safety of the target object and other objects that have an interaction relationship with it, there are differences in the evaluation and arbitration process of the planned trajectory information corresponding to the reachable states with mandatory execution and those without mandatory execution.

[0154] Among them, whether a reachable state is mandatory can be determined by the execution label corresponding to the reachable state. Among them, the execution label corresponding to the reachable state is: the label determined based on the current surrounding perception information and / or current map information in the current decision-making and planning related information. For example: in the case where it is determined through the current surrounding perception information that there is a faulty object or a suddenly appearing fast-moving object in the lane in front of the target object when it is driving, the target object needs to change lanes; in the case where it is determined through the current surrounding perception information and the current map information that there is no road or no lane in front of the target object when it is driving, the target object needs to change lanes or turn; in the case where it is determined through the current surrounding perception information and the current map information that the front of the target object is at an intersection and the task performed by the target object requires the target object to turn left, correspondingly, the target object needs to turn, etc.

[0155] In this implementation manner, during the process of the electronic device evaluating and arbitrating the planned trajectory information corresponding to each reachable state, it first determines whether there is a reachable state in the reachable state set whose corresponding execution label is the must-execute label. If it is determined that there is a reachable state in the reachable state set whose corresponding execution label is the must-execute label, it is necessary to prioritize the evaluation and arbitration. And when the planned trajectory information corresponding to the reachable state corresponding to the must-execute label is safe and feasible, it is preferred to consider jumping to the reachable state with the must-execute label.

[0156] The reachable states in the reachable state set can include states at the top level or states at non-top levels. When it is determined that there is a reachable state in the reachable state set whose corresponding execution label is the must-execute label, based on the priority of the current priority corresponding to the state at the top level corresponding to the reachable state, the planned trajectory information corresponding to the reachable state is evaluated and arbitrated in sequence. It can be understood that the current priority of the reachable state with the must-execute label is the highest.

[0157] Specifically, based on the current priority corresponding to the top-level state corresponding to each reachable state, the reachable state with the highest current priority is determined as the state to be evaluated; based on the planned trajectory information corresponding to the state to be evaluated and the evaluation factors corresponding to the state to be evaluated, the evaluation index value corresponding to the state to be evaluated is determined. Based on the evaluation index value corresponding to the state to be evaluated, the evaluation result of whether the planned trajectory information corresponding to the state to be evaluated is feasible is determined; if the evaluation result indicates that the planned trajectory information corresponding to the state to be evaluated is feasible, then the current reachable state is directly determined as the target state corresponding to the target object; there is no need to perform the evaluation and arbitration process on the planned trajectory information corresponding to other reachable states with lower current priorities.

[0158] If the evaluation result indicates that the planned trajectory information corresponding to the state to be evaluated is not feasible, then continue to evaluate and arbitrate the planned trajectory information corresponding to other reachable states with lower current priorities, that is, return to execute the step of determining the reachable state with the highest current priority as the state to be evaluated based on the current priority corresponding to the top-level state corresponding to each reachable state.

[0159] In one case, if there is at least one piece of planned trajectory information corresponding to the state to be evaluated that is feasible among the planned trajectory information corresponding to the state to be evaluated, it can be determined that the planned trajectory information corresponding to the state to be evaluated is feasible.

[0160] Among them, the top-level state corresponding to the reachable state is: the state at the top level in the preset hierarchical state machine to which the reachable state belongs. For example, the states at the top level of the preset hierarchical state machine include lane keeping, lane changing, and borrowing a lane; among them, the top-level state of lane changing includes three sub-states: lane change preparation, lane change execution, and lane change return. In one case, based on the current state of the preset hierarchical state machine, the transition relationship between states, the current decision-making and planning related information, and the preset driving limit conditions, the electronic device determines that the reachable state set corresponding to the target object includes three reachable states: lane keeping, lane change preparation, and lane change execution. Among them, lane keeping is at the top level, and its corresponding top-level state is itself; lane change preparation and lane change execution are sub-states of lane change. Correspondingly, the top-level states corresponding to lane change preparation and lane change execution are lane change.

[0161] In another embodiment of the present invention, the state to be evaluated may be one or more. For example, continuing with the above example, the top-level states corresponding to both lane change preparation and lane change execution are the top-level state of lane change. Correspondingly, the current priorities corresponding to lane change preparation and lane change execution are the same. Lane change preparation and lane change execution correspond to the same parent state and are at the same level. Then, it can be considered that lane change preparation and lane change execution are reachable states with a common parent state and at the same level.

[0162] During driving, when the target object performs a series of execution actions, theoretically, there is a corresponding execution order between this series of execution actions. For example, when the target object needs to perform a lane change, if there are multiple objects on the target road to which it changes lanes, when the target object performs a lane change, it needs to first determine the position to be inserted for the lane change, that is, the gap between which two objects or in front of or behind which object on the target road, and then drive on its own road to near the position it determines to be inserted, and then perform the lane change, that is, enter the target road.

[0163] To ensure the coherence and comfort of the execution actions of the target object, if the states to be evaluated include reachable states with a common parent state and at the same level, there is a timing stage transition relationship between such states, and this timing stage transition relationship is used to limit the execution order between states.

[0164] Correspondingly, in one embodiment of the present invention, after the electronic device determines the state to be evaluated and determines that there are multiple states to be evaluated, if the states to be evaluated include reachable states with a common parent state and at the same level; there is a timing stage transition relationship between the reachable states with a common parent state and at the same level.

[0165] The 022 may include the following steps 0221-0225:

[0166] 0221: For the to-be-evaluated states that have a common parent state and are at the same level, based on the order of the time-sequence stage transition relationships corresponding to each to-be-evaluated state, sequentially determine the reachable state that is currently unevaluated and has the earliest corresponding time-sequence stage transition relationship as the current to-be-evaluated state.

[0167] 0222: Determine the evaluation index value corresponding to the current to-be-evaluated state based on the planned trajectory information corresponding to the current to-be-evaluated state and the evaluation factors corresponding to the current to-be-evaluated state.

[0168] 0223: If the rating index value corresponding to the current to-be-evaluated state indicates that the planned trajectory information corresponding to the current to-be-evaluated state is feasible, determine whether there is an unevaluated state among the to-be-evaluated states.

[0169] 0224: If it is determined that there is one, return to 0221.

[0170] 0225: If it is determined that there is none, or it is determined that the planned trajectory information corresponding to the current to-be-evaluated state is infeasible, obtain the evaluation result of whether the planned trajectory information corresponding to the to-be-evaluated state is feasible.

[0171] In this implementation, the electronic device traverses the to-be-evaluated states that have a common parent state and are at the same level among the to-be-evaluated states. Based on the order of the time-sequence stage transition relationships corresponding to each to-be-evaluated state, sequentially determine the reachable state that is currently unevaluated and has the earliest corresponding time-sequence stage transition relationship as the current to-be-evaluated state; determine the evaluation index value corresponding to the current to-be-evaluated state based on the planned trajectory information corresponding to the current to-be-evaluated state and the evaluation factors corresponding to the current to-be-evaluated state. Furthermore, based on the evaluation index value corresponding to the current to-be-evaluated state, determine whether the planned trajectory information corresponding to the current to-be-evaluated state is feasible. If the rating index value corresponding to the current to-be-evaluated state indicates that the planned trajectory information corresponding to the current to-be-evaluated state is feasible, determine whether there is an unevaluated state among the to-be-evaluated states. If there is, then continue to execute 0224; if it is determined that there is none, or it is determined that the planned trajectory information corresponding to the current to-be-evaluated state is infeasible, obtain the evaluation result of whether the planned trajectory information corresponding to the to-be-evaluated state is feasible.

[0172] Among them, if it is determined that there is at least one state among the to-be-evaluated states whose planned trajectory information is feasible, the evaluation result of whether the planned trajectory information corresponding to the to-be-evaluated state is feasible includes: information indicating that the planned trajectory information corresponding to the to-be-evaluated state is feasible, and carrying the identifier of the state with feasible planned trajectory information. If it is determined that the planned trajectory information of all states among the to-be-evaluated states is infeasible, the evaluation result of whether the planned trajectory information corresponding to the to-be-evaluated state is feasible includes: information indicating that the planned trajectory information corresponding to the to-be-evaluated state is infeasible.

[0173] Among them, the planned trajectory information corresponding to the sub-states of the top-level state is the sub-information of the planned trajectory information corresponding to the top-level state, that is, the planned trajectory information corresponding to the sub-states of the top-level state can be combined to form the planned trajectory information corresponding to the top-level state. If there are still states at the next level for the sub-states corresponding to the top-level state, the planned trajectory information corresponding to each state at the next level of the sub-state can be combined to form the planned trajectory information corresponding to the sub-state. And so on. The planned trajectory information corresponding to each state that has a common parent state and is at the same level can be combined to form the planned trajectory information corresponding to its parent state.

[0174] For example, the states at the top level of the preset hierarchical state machine include lane keeping, lane change, and borrowing a lane; among them, the state of lane change at the top level includes three sub-states: lane change preparation, lane change execution, and lane change return. The current state of the target object is lane keeping or lane change preparation. Based on the current priorities corresponding to the top-level states of each reachable state, determine the reachable state with the highest current priority as the state to be evaluated. Among them, the states to be evaluated include lane change preparation, lane change execution, and lane change return; among them, as Figure 2B shown, the sequential phase transition relationship among lane change preparation, lane change execution, and lane change return indicates that lane change preparation can transition to lane change execution, lane change execution can transition to lane change return, lane change return can transition to lane change execution, and when lane change execution is completed, the lane change is completed.

[0175] When the current state of the target object is lane keeping or lane change preparation, based on the order of the sequential phase transition relationships corresponding to each state to be evaluated, the feasibility of the planned trajectory information corresponding to lane change preparation, the feasibility of the planned trajectory information corresponding to lane change execution, and the feasibility of the planned trajectory information corresponding to lane change return can be evaluated and arbitrated in sequence until the planned trajectory information corresponding to the state being evaluated and arbitrated is infeasible, and then determine the evaluation result of whether the planned trajectory information corresponding to the state to be evaluated is feasible.

[0176] When the current state of the target object is lane change execution, based on the order of the sequential phase transition relationships corresponding to each state to be evaluated, the feasibility of the planned trajectory information corresponding to lane change execution and the feasibility of the planned trajectory information corresponding to lane change return can be evaluated and arbitrated in sequence until the planned trajectory information corresponding to the state being evaluated and arbitrated is infeasible, and then determine the evaluation result of whether the planned trajectory information corresponding to the state to be evaluated is feasible.

[0177] When the current state of the target object is a lane change return, based on the order of the sequential stage transition relationships corresponding to each state to be evaluated, the feasibility of arbitration for lane change execution and lane change return can be evaluated in sequence until the planned trajectory information corresponding to the state of the evaluated arbitration is infeasible, and the evaluation result of whether the planned trajectory information corresponding to the state to be evaluated is feasible is determined.

[0178] As Figure 2A shown, 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 the reachable state set corresponding to the target object based on the current state of the preset hierarchical state machine, the jump relationships between states, the current decision-making plan related information, and the preset driving limit conditions. As Figure 2A shown in, the "feasible target state set" includes: lane keeping, lane change preparation, and lane change execution. That is, the state of the preset hierarchical state machine can jump from representing lane keeping to lane keeping, or from lane keeping to lane change preparation, or from lane keeping to lane change execution. The electronic device can obtain the planned trajectory information corresponding to each reachable state in the reachable state set; based on the planned trajectory information corresponding to each reachable state, the level and evaluation factors corresponding to each reachable state, determine the evaluation index value corresponding to the reachable state, and based on the evaluation index value corresponding to the reachable state, determine the target state corresponding to the target object from the reachable states, that is, construct an arbitration tree.

[0179] The electronic device can construct an arbitration tree from bottom to top, that is, determine the evaluation index value corresponding to each reachable state. Correspondingly, since lane change preparation and lane change execution have a common parent state and are states at the same level, as Figure 2AAs shown, first, based on the planned trajectory information corresponding to lane change preparation, the level and evaluation factors corresponding to lane change preparation, determine the evaluation index value corresponding to lane change preparation; evaluate and arbitrate the planned trajectory information corresponding to lane change preparation based on the evaluation index value corresponding to lane change preparation. If the evaluation index value corresponding to lane change preparation indicates that the planned trajectory information corresponding to lane change preparation is feasible, then based on the planned trajectory information corresponding to lane change execution, the level and evaluation factors corresponding to lane change execution, determine the evaluation index value corresponding to lane change execution, and evaluate and arbitrate the planned trajectory information corresponding to lane change execution based on the evaluation index value corresponding to lane change execution. If the evaluation index value corresponding to lane change execution indicates that the planned trajectory information corresponding to lane change execution is not feasible, in one case, if the execution label corresponding to lane change is a must-execute label, then the corresponding electronic device can directly determine lane change preparation as the target state. In another case, if there is no state in the reachable state set whose corresponding execution label is a must-execute label, then based on the planned trajectory information corresponding to lane keeping, the level and evaluation factors corresponding to lane keeping, determine the evaluation index value corresponding to lane keeping; based on the evaluation index value corresponding to lane keeping and the evaluation index value corresponding to lane change preparation, determine the optimal planned trajectory information among the planned trajectory information corresponding to lane keeping and the planned trajectory information corresponding to lane change preparation, and determine the reachable state corresponding to the optimal planned trajectory information as the target state.

[0180] Correspondingly, in another embodiment of the present invention, the 023 includes the following steps:

[0181] Determine the reachable state with the last transition relationship of the corresponding time sequence stage among the reachable states corresponding to the feasible planned trajectory information as the target state of the target object.

[0182] In this implementation manner, if the evaluation result corresponding to the state to be evaluated indicates that the planned trajectory information corresponding to the state to be evaluated is feasible, then based on the evaluation result corresponding to the state to be evaluated, determine the identifier of the reachable state corresponding to the feasible planned trajectory information, and determine the reachable state with the last transition relationship of the corresponding time sequence stage among the reachable states corresponding to the feasible planned trajectory information as the target state of the target object. For example: Continuing with the above example, if the feasibility of the planned trajectory information corresponding to lane change preparation, the feasibility of the planned trajectory information corresponding to lane change execution, and the feasibility of the planned trajectory information corresponding to lane change return are evaluated and arbitrated in sequence, where it is determined that the planned trajectory information corresponding to lane change preparation is feasible, but the planned trajectory information corresponding to lane change execution is not feasible, then determine lane change preparation as the target state of the target object. After determining the target state, the electronic device can control the preset hierarchical state machine to jump from the current state of lane keeping to the target state, such as lane change preparation, based on the state transition function.

[0183] Such as Figure 2AAs shown, the preset hierarchical state machine can support the scenario configuration of the staff, so that the preset hierarchical state machine can expand and / or modify the state according to the actual usage scenario.

[0184] In another embodiment of the present invention, S104 may include the following steps 025-026:

[0185] 025: If it is determined that there is no reachable state in the reachable state set whose corresponding execution label is the must-execute label, for each reachable state, based on the planned trajectory information corresponding to the reachable state and the evaluation factors corresponding to the reachable state, determine the evaluation index value corresponding to the reachable state.

[0186] 026: Based on the evaluation index values corresponding to each reachable state, determine the target state corresponding to the target object from all reachable states.

[0187] In this implementation manner, if the electronic device determines that there is no reachable state in the reachable state set whose corresponding execution label is the must-execute label, and if each reachable state belongs to the same level, it can be considered that the selection levels among the reachable states are equal. Correspondingly, the electronic device can, for each reachable state, based on the planned trajectory information corresponding to the reachable state and the evaluation factors corresponding to the reachable state, determine the evaluation index value corresponding to the reachable state; furthermore, based on the evaluation index values corresponding to each reachable state, determine a relatively safe, comfortable and reasonable reachable state from all reachable states as the target state corresponding to the target object.

[0188] In another implementation manner of the present invention, if the electronic device determines that there is no reachable state in the reachable state set whose corresponding execution label is the must-execute label, and there are states belonging to different levels among the reachable states. Among them, there will inevitably be states that have a common parent state and are in the same level. When determining the feasibility of the planned trajectory information corresponding to the states that have a common parent state and are in the same level, that is, during the evaluation arbitration process, it is necessary to consider the transition relationship of the timing stages between the states that have a common parent state and are in the same level.

[0189] If feasible planned trajectory information is determined from the planned trajectory information corresponding to states that are in a mutually parent - child relationship and at the same level, return the evaluation index value corresponding to the state where the corresponding planned trajectory information is feasible and the last state of the corresponding time - sequence stage transition relationship as the first evaluation index value. Compare this first evaluation index value with the evaluation index value corresponding to the parent state of the states that are in a mutually parent - child relationship and at the same level to determine the state with the optimal corresponding planned trajectory information as the target state. Among them, if the evaluation index value exists in the form of a penalty term, the larger the evaluation index value corresponding to the reachable state, the more unreasonable the corresponding planned trajectory information. Correspondingly, the state with the optimal corresponding planned trajectory information can be the state with the smallest corresponding evaluation index value.

[0190] In another embodiment of the present invention, the method may further include:

[0191] Based on the target state, determine the visualization signal and visualization information corresponding to the target state, and output them so that the target object makes corresponding displays based on the visualization signal and visualization information.

[0192] In this implementation, considering that the target object needs to display the state it is about to be in and the actions it is about to perform to its corresponding user and other objects with which it has an interaction relationship during the driving process and when performing the execution actions corresponding to each state. Correspondingly, after the electronic device determines the target state, it can determine the visualization signal and visualization information corresponding to the target state and output them so that the target object makes corresponding displays based on the visualization signal and visualization information.

[0193] The visualization signal can be information determined based on the target state for controlling the specified display device of the target object to make corresponding displays. For example, when the target state is lane - changing, the visualization signal is a signal for controlling the left - turn or right - turn indicator of the target object to flash or continuously light up, where specifically whether the left - turn indicator lights up or the right - turn indicator lights up is determined based on the planned trajectory information corresponding to the target state. The visualization information is information to be displayed to the user of the target object. For example, it can be information describing the state that the target object is about to jump to, that is, the decision result, and / or information describing the actions that the target object is about to perform, etc.

[0194] Corresponding to the above - mentioned method embodiment, an embodiment of the present invention provides a path planning device, as Figure 3 shown, the device may include:

[0195] A first acquisition module 310, configured to acquire the current decision - making and planning - related information corresponding to the target object;

[0196] The first determination module 320 is configured to determine a reachable state set corresponding to the target object based on the current state of a preset hierarchical state machine, the transition relationships between states, the current decision-making planning related information, and preset driving limit conditions. The preset hierarchical state machine includes: the transition relationships and hierarchical relationships between the states corresponding to the target object;

[0197] The second acquisition module 330 is configured to acquire the planned trajectory information corresponding to each reachable state in the reachable state set;

[0198] The second determination module 340 is configured to determine a target state corresponding to the target object from all reachable states based on the planned trajectory information corresponding to each reachable state, the level and evaluation factors corresponding to each reachable state, where the level corresponding to a reachable state is its level in the preset hierarchical state machine;

[0199] The control module 350 is 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.

[0200] Applying the embodiments of the present invention, based on the current state of a preset hierarchical state machine, the transition relationships between states, the current decision-making planning related information, and preset driving limit conditions, a reachable state set that can be jumped to from the next state of the preset hierarchical state machine is determined, that is, the reachable state set of the target object corresponding to the preset hierarchical state machine at the next moment is determined. Furthermore, by using the rationality of the planned trajectory information corresponding to each reachable state, the reachable state with the most reasonable planned trajectory information corresponding thereto, that is, the target state, is determined from the reachable state set, realizing the rational and accurate determination of the state of the target object at the next moment, improving the rationality of path planning. And during the planning process, the reachable states are first determined, and then the planned trajectory information corresponding to the reachable states is obtained, so as to determine the target state from the reachable states through the evaluation of the planning information. This planning framework is more generalizable, extensible, and interpretable, and can quickly define and embed new scenarios and action modes for newly emerging practical problems and scenarios, and adapt to new path planning algorithms.

[0201] In another embodiment of the present invention, the current decision-making planning related information includes: the current surrounding perception information of the target object, the current pose information, the current map information, and the prediction information of obstacles.

[0202] In another embodiment of the present invention, the first determination module 320 is specifically configured to preprocess the specified information in the current decision-making planning related information and determine whether each piece of information in the current decision-making planning related information is valid;

[0203] When it is determined that all the currently obtained decision-making planning-related information is valid, based on the current state of the preset hierarchical state machine, the transition relationships between states, the currently obtained decision-making planning-related information, and the preset driving limit conditions, determine the reachable state set corresponding to the target object.

[0204] In another embodiment of the present invention, the second determination module 340 includes:

[0205] A judgment unit (not shown in the figure), configured to judge whether there is a reachable state in the reachable state set whose corresponding execution label is a must-execute label, where the jump label is: a label determined based on the current surrounding perception information and / or the current map information in the currently obtained decision-making planning-related information;

[0206] A first determination unit (not shown in the figure), configured to, if it is determined that there is a reachable state in the reachable state set whose corresponding execution label is a must-execute label, based on the current priority corresponding to the top-level state corresponding to each reachable state, determine the reachable state with the highest current priority as the state to be evaluated; based on the planned trajectory information corresponding to the state to be evaluated and the evaluation factors corresponding to the state to be evaluated, determine the evaluation result of whether the planned trajectory information corresponding to the state to be evaluated is feasible, where the reachable state corresponding to the must-execute label has the highest priority;

[0207] A second determination unit (not shown in the figure), configured to, if the evaluation result indicates that the planned trajectory information corresponding to the state to be evaluated is feasible, based on the feasible planned trajectory information, determine the target state corresponding to the target object from the states to be evaluated;

[0208] If the evaluation result indicates that the planned trajectory information corresponding to the state to be evaluated is not feasible, then return to trigger the first determination unit.

[0209] In another embodiment of the present invention, if the states to be evaluated include reachable states that have a common parent state and are at the same level; there is a time-sequence stage transition relationship between the reachable states that have a common parent state and are at the same level;

[0210] The first determination unit (not shown in the figure) is specifically configured to, for the states to be evaluated that have a common parent state and are at the same level, based on the sequence of the time-sequence stage transition relationships corresponding to each state to be evaluated, sequentially determine the reachable state that has not been evaluated currently and whose corresponding time-sequence stage transition relationship is the earliest as the current state to be evaluated;

[0211] Based on the planned trajectory information corresponding to the current state to be evaluated and the evaluation factors corresponding to the current state to be evaluated, determine the evaluation index value corresponding to the current state to be evaluated;

[0212] If the rating index value corresponding to the current state to be evaluated indicates that the planned trajectory information corresponding to the current state to be evaluated is feasible, determine whether there is an unevaluated state in the state to be evaluated;

[0213] If it is determined that there is one, return the reachable state that is unevaluated and has the earliest corresponding time sequence stage transition relationship among the states to be evaluated as the current state to be evaluated;

[0214] If it is determined that there is none, or it is determined that the planned trajectory information corresponding to the current state to be evaluated is infeasible, obtain the evaluation result of whether the planned trajectory information corresponding to the state to be evaluated is feasible.

[0215] In another embodiment of the present invention, the second determination unit (not shown in the figure) is specifically configured to determine the reachable state with the last corresponding time sequence stage transition relationship among the reachable states corresponding to the feasible planned trajectory information as the target state corresponding to the target object.

[0216] In another embodiment of the present invention, the second determination module 340 further includes:

[0217] A third determination unit, configured to, if it is determined that there is no reachable state in the reachable state set whose corresponding execution label is the must-execute label, for each reachable state, determine the evaluation index value corresponding to the reachable state based on the planned trajectory information corresponding to the reachable state and the evaluation factors corresponding to the reachable state;

[0218] Based on the evaluation index values corresponding to each reachable state, determine the target state corresponding to the target object from all reachable states.

[0219] In another embodiment of the present invention, the second acquisition module 330 is specifically configured to determine the planned trajectory information corresponding to each reachable state in the reachable state set based on the path planning algorithm corresponding to each reachable state in the reachable state set and the current surrounding perception information, current pose information, current map information, and predicted information of obstacles of the target object in the current decision-making plan related information.

[0220] In another embodiment of the present invention, the device further includes:

[0221] A determination output module (not shown in the figure), configured to determine the visualization signal and visualization information corresponding to the target state based on the target state and output them, so that the target object performs corresponding display based on the visualization signal and visualization information.

[0222] The above system and apparatus embodiments correspond to the system embodiments and have the same technical effects as the method embodiments. For specific descriptions, please refer to the method embodiments. The apparatus embodiments are obtained based on the method embodiments. For specific descriptions, please refer to the method embodiment section and will not be elaborated here. Those of ordinary skill in the art can understand that the drawings are only schematic diagrams of an embodiment, and the modules or processes in the drawings are not necessarily essential for implementing the present invention.

[0223] Those of ordinary skill in the art can understand that the modules in the apparatus in the embodiments can be distributed in the apparatus of the embodiments according to the descriptions in the embodiments, or can be correspondingly changed to be located in one or more apparatuses different from the present embodiment. The modules in the above embodiments can be combined into one module, or further split into multiple sub-modules.

[0224] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. However, such modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A path planning method, characterized in that, the method includes: obtaining current decision-making planning related information corresponding to the target object; determining a reachable state set corresponding to the target object based on the current state of a preset hierarchical state machine, the transition relationships between states, the current decision-making planning related information, and preset driving limit conditions, where the preset hierarchical state machine includes: the transition relationships and hierarchical relationships between the states corresponding to the target object; obtaining planning trajectory 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 the planning trajectory information corresponding to each reachable state, the level corresponding to each reachable state, and evaluation factors, where the level corresponding to a reachable state is its level in the preset hierarchical state machine; controlling the preset hierarchical state machine to jump from the current state to the target state, so that the target object travels based on the planning trajectory information corresponding to the target state; the step of determining a target state corresponding to the target object from all reachable states based on the planning trajectory information corresponding to each reachable state, the level corresponding to each reachable state, and evaluation factors includes: judging whether there is a reachable state in the reachable state set whose corresponding execution label is a must-execute label, where the execution label is: a label determined based on the current surrounding perception information and / or current map information in the current decision-making planning related information; if it is determined that there is a reachable state in the reachable state set whose corresponding execution label is a must-execute label, determining the reachable state with the highest current priority corresponding to the top-level hierarchical state of each reachable state as the state to be evaluated; determining an evaluation result of whether the planning trajectory information corresponding to the state to be evaluated is feasible based on the planning trajectory information corresponding to the state to be evaluated and the evaluation factors corresponding to the state to be evaluated, where the reachable state corresponding to the must-execute label has the highest priority; if the evaluation result indicates that the planning trajectory information corresponding to the state to be evaluated is feasible, determining a target state corresponding to the target object from the states to be evaluated based on the feasible planning trajectory information; if the evaluation result indicates that the planning trajectory information corresponding to the state to be evaluated is infeasible, returning to execute the step of determining the reachable state with the highest current priority corresponding to the top-level hierarchical state of each reachable state as the state to be evaluated.

2. The method according to claim 1, characterized in that, the current decision-making planning related information includes: the current surrounding perception information of the target object, the current pose information, the current map information, and the prediction information of obstacles.

3. The method according to claim 1, characterized in that, the step of determining a reachable state set corresponding to the target object based on the current state of a preset hierarchical state machine, the transition relationships between states, the current decision-making planning related information, and preset driving limit conditions includes: Preprocess the specified information in the current decision-making planning related information, and determine whether each piece of information in the current decision-making planning related information is valid; When it is determined that all the currently obtained decision-making planning related information is valid, based on the current state of the preset hierarchical state machine, the jump relationships between states, the current decision-making planning related information, and the preset driving limit conditions, determine the reachable state set corresponding to the target object.

4. The method according to claim 1, characterized in that, if the reachable states in the state to be evaluated include reachable states that have a common parent state and are at the same level; there is a time-sequence stage transition relationship between reachable states that have a common parent state and are at the same level; The step of determining whether the planned trajectory information corresponding to the state to be evaluated is feasible based on the planned trajectory information corresponding to the state to be evaluated and the evaluation factors corresponding to the state to be evaluated includes: For the states to be evaluated that have a common parent state and are at the same level, based on the order of the time-sequence stage transition relationships corresponding to each state to be evaluated, sequentially determine the reachable state that has not been evaluated yet and whose corresponding time-sequence stage transition relationship is the earliest as the current state to be evaluated; Based on the planned trajectory information corresponding to the current state to be evaluated and the evaluation factors corresponding to the current state to be evaluated, determine the evaluation index value corresponding to the current state to be evaluated; If the evaluation index value corresponding to the current state to be evaluated indicates that the planned trajectory information corresponding to the current state to be evaluated is feasible, determine whether there is an unevaluated state in the states to be evaluated; If it is determined that there is, return to the step of determining the reachable state that has not been evaluated yet and whose corresponding time-sequence stage transition relationship is the earliest from the states to be evaluated as the current state to be evaluated; If it is determined that there is no, or it is determined that the planned trajectory information corresponding to the current state to be evaluated is not feasible, obtain the evaluation result of whether the planned trajectory information corresponding to the state to be evaluated is feasible.

5. The method according to claim 4, characterized in that, The step of determining the target state corresponding to the target object from the states to be evaluated based on the feasible planned trajectory information includes: Determine the reachable state with the last corresponding time-sequence stage transition relationship among the reachable states corresponding to the feasible planned trajectory information as the target state corresponding to the target object.

6. The method according to claim 1, characterized in that, The method further includes: If it is determined that there is no reachable state in the reachable state set whose corresponding execution label is the mandatory execution label, for each reachable state, based on the planned trajectory information corresponding to the reachable state and the evaluation factors corresponding to the reachable state, determine the evaluation index value corresponding to the reachable state; Based on the evaluation index values corresponding to each reachable state, determine the target state corresponding to the target object from all reachable states.

7. The method according to claim 1, characterized in that, The step of obtaining the planned trajectory information corresponding to each reachable state in the reachable state set includes: Based on the path planning algorithms corresponding to each reachable state in the reachable state set, and the current surrounding perception information, current pose information, current map information, and predicted information of obstacles in the current decision-making planning related information, determine the planning trajectory information corresponding to each reachable state in the reachable state set.

8. The method according to any one of claims 1-7, wherein, the method further includes: Based on the target state, determine the visualization signal and visualization information corresponding to the target state, and output them, so that the target object performs corresponding display based on the visualization signal and visualization information.

9. A path planning device, wherein, the device includes: A first acquisition module configured to acquire the current decision-making planning related information corresponding to the target object; A first determination module configured to determine the reachable state set corresponding to the target object based on the current state of the preset hierarchical state machine, the jump relationships between states, the current decision-making planning related information, and the preset driving limit conditions, where the preset hierarchical state machine includes: the jump relationships and hierarchical relationships between the states corresponding to the target object; A second acquisition module configured to acquire the planning trajectory information corresponding to each reachable state in the reachable state set; A second determination module configured to determine the target state corresponding to the target object from all reachable states based on the planning trajectory information corresponding to each reachable state, the level and evaluation factors corresponding to each reachable state, where the level corresponding to a reachable state is its level in the preset hierarchical state machine; A control module 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 planning trajectory information corresponding to the target state; The second determination module includes: A judgment unit configured to judge whether there is a reachable state in the reachable state set whose corresponding execution label is the must-execute label, where the execution label is: the label determined based on the current surrounding perception information and / or current map information in the current decision-making planning related information; A first determination unit configured to, if it is determined that there is a reachable state in the reachable state set whose corresponding execution label is the must-execute label, determine the reachable state with the highest current priority corresponding to the top-level state of each reachable state as the to-be-evaluated state; based on the planning trajectory information corresponding to the to-be-evaluated state and the evaluation factors corresponding to the to-be-evaluated state, determine the evaluation result of whether the planning trajectory information corresponding to the to-be-evaluated state is feasible, where the reachable state corresponding to the must-execute label has the highest priority; A second determination unit configured to, if the evaluation result indicates that the planning trajectory information corresponding to the to-be-evaluated state is feasible, determine the target state corresponding to the target object from the to-be-evaluated states based on the feasible planning trajectory information; If the evaluation result indicates that the planning trajectory information corresponding to the to-be-evaluated state is not feasible, return to trigger the first determination unit.

Images