Robot motion planning method and device inspired by spatial relationship memory

Abstract

The invention relates to the technical field of robot motion planning, in particular to a robot motion planning method and device inspired by spatial relationship memory. The method comprises the steps that according to motion starting position information, motion target position information and map information, a first random geometric graph is constructed through a K-NN algorithm by using a selective sampling strategy in a configuration space of a robot; based on a preset confidence threshold, inputting the first random geometric graph and the obstacle position information into an intelligent edge selector for edge screening to obtain a second random geometric graph; according to the second random geometric graph, heuristic value calculation is carried out through a memory perception predictor, and a node heuristic value is obtained; and according to the node heuristic value and the second random geometric diagram, performing optimal path search by using a micro # imgabs0 # module to obtain a second optimal path. The method is an efficient and accurate robot motion planning method based on human brain space relation memory inspiration.

Description

Technical Field

[0001] The present invention relates to the technical field of robot motion planning, and in particular to a robot motion planning method and device inspired by spatial relationship memory. Background Art

[0002] Motion planning is a key technology in robotics systems and has significant application prospects in various fields such as transportation systems and medical systems. The goal of motion planning is to find a collision-free path connecting the starting point and the target point in the decision space, and ideally minimize the path cost. However, the decision space in the real world usually contains a large number of continuous variables and high-dimensional unstructured space, which greatly increases the complexity of motion planning. Therefore, it is crucial to implement fast and reliable motion planning methods in high-dimensional continuous space to improve its practical application.

[0003] Classic motion planning solutions can be roughly divided into two categories: search-based methods and sampling-based methods. Search-based methods conceptualize the planning problem as a graph search problem. Sampling-based methods, including fast exploration random trees and probabilistic roadmaps, construct exploration trees connecting the starting and target points by randomly sampling in the configuration space. However, classical methods are often inefficient when dealing with high-dimensional planning problems. In high-dimensional continuous environments, learning-based planning methods are a key means to improve motion planning performance. Existing planning methods still face the following challenges when facing high-dimensional continuous environments.

[0004] Traditional planning methods build random geometric graphs based on uniform sampling strategies, which means that they explore the entire space indiscriminately and fail to fully utilize the structural information of the actual problem itself. This may lead to unnecessary node exploration or inappropriate edges and nodes, so it is not effective when dealing with new problems and cannot be effectively generalized. When faced with obstacles that are fast or close, the robot must be able to make decisions quickly and accurately to avoid the obstacles. Traditional planning methods often focus on node location information and handle each task independently, failing to fully utilize past experience and established data models.

[0005] The human brain has a natural advantage in the process of decision-making and reasoning, among which spatial relational memory is crucial in this process. Studies have shown that the human brain can transform decision-making problems into a graph structure corresponding to sensory observations, and relational memory integrates sensory observations with their structural relationships, thereby promoting sensory reasoning. On the one hand, humans can make complex inferences from sparse observations and make quick decisions by integrating previous experience and current environmental information. This ability is related to the hippocampus-entorhinal cortex system. On the other hand, spatial memory is essential for human survival. Humans use "cognitive maps" to structure their understanding of the world, and this process is closely related to the hippocampus. Therefore, in order to meet the above two challenges, the present invention designs a brain-inspired Graph Neural Network (GNN) planner to improve planning efficiency and scalability, called Brainy Motion PlaNNing (BrainyMP).

[0006] In recent years, learning-based planning methods are the most promising methods to improve the performance of high-dimensional continuous motion planning. By leveraging the powerful learning and representation capabilities of neural networks, robots can learn patterns in high-dimensional space and the behavior trajectories of expert planners from data. Therefore, strategies in the planning process (such as sampling mechanisms) can be optimized to achieve excellent performance in high-dimensional continuous spaces. Learning-based methods regard motion planning as a sequential decision problem, which can usually be solved by reinforcement learning. Previous work has proposed various neural network-based motion planners, including planners based on convolutional neural networks, recurrent neural networks, and graph neural networks.

[0007] GNN-based planners have shown remarkable capabilities in handling high-dimensional continuous planning tasks, such as GNN-Explorer and GraphMP. By accessing random geometric graphs formed by uniform sampling, these planners are able to capture the geometric patterns of the environment, thereby achieving more efficient exploration without encoding the entire workspace. Although GNN-based planners perform well in high-dimensional continuous tasks, they still have some limitations: when constructing the initial random geometric graph (RGG), the process of uniformly sampling nodes ignores the topology of the environment, which may lead to unnecessary node exploration; in the process of edge formation of RGG, there may be edges that collide with obstacles, thereby reducing the reliability of planning; when the model extracts key graph patterns, existing methods mainly encode the positional relationship of nodes, but ignore the structural relationship between nodes, which hinders the improvement of the model's expressiveness.

[0008] In the existing technology, there is a lack of an efficient and accurate robot motion planning method inspired by the spatial memory of the human brain. Summary of the invention

[0009] In order to solve the technical problems of low node exploration efficiency and poor reliability of motion route planning in the prior art, the embodiment of the present invention provides a robot motion planning method and device inspired by spatial relationship memory. The technical solution is as follows:

[0010] On the one hand, a robot motion planning method inspired by spatial relationship memory is provided, the method is implemented by a robot motion planning device, and the method includes:

[0011] Obtaining movement starting position information, movement target position information, obstacle position information and map information;

[0012] Based on the selective sampling strategy, according to the movement starting position information, the movement target position information and the map information, a first random geometric graph is constructed in the robot configuration space by using a K-NN algorithm;

[0013] Based on a preset confidence threshold, the first random geometric graph and the obstacle position information are input into the smart edge selector for edge screening to obtain a second random geometric graph;

[0014] According to the second random geometric graph, performing heuristic value calculation by the memory-aware predictor to obtain a node heuristic value;

[0015] Based on differentiable The module searches for an optimal path using a shortcut path exploration method according to the node heuristic value and the second random geometric graph to obtain a second optimal path.

[0016] On the other hand, a robot motion planning device inspired by spatial relationship memory is provided, the device is applied to a robot motion planning method inspired by spatial relationship memory, the device comprising:

[0017] An information acquisition module is used to obtain movement starting position information, movement target position information, obstacle position information and map information;

[0018] A first random geometric graph construction module is used to construct a first random geometric graph in the robot's configuration space by a K-NN algorithm based on a selective sampling strategy and according to the motion starting position information, the motion target position information and the map information;

[0019] A second random geometric graph construction module, used for inputting the first random geometric graph and the obstacle position information into the smart edge selector for edge screening based on a preset confidence threshold to obtain a second random geometric graph;

[0020] a heuristic value calculation module, configured to calculate a heuristic value according to the second random geometric graph by using the memory-aware predictor to obtain a node heuristic value;

[0021] The optimal path acquisition module is used to obtain The module searches for an optimal path using a shortcut path exploration method according to the node heuristic value and the second random geometric graph to obtain a second optimal path.

[0022] On the other hand, a robot motion planning device is provided, which includes: a processor; a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, any one of the above-mentioned robot motion planning methods inspired by spatial relationship memory is implemented.

[0023] On the other hand, a computer-readable storage medium is provided, wherein at least one instruction is stored in the storage medium, and the at least one instruction is loaded and executed by a processor to implement any one of the above-mentioned robot motion planning methods inspired by spatial relationship memory.

[0024] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0025] The present invention proposes a robot motion planning method inspired by spatial relational memory. In the process of decision-making and relational reasoning of the human brain, the brain mechanism related to spatial relational memory shows obvious advantages. Based on this, a new brain-like motion planning based on graph neural network is designed to improve the performance of robot planning in high-dimensional continuous environment. When constructing a random geometric graph, a new random geometric graph generation method is used to make the sampling nodes closer to the optimal solution, thereby improving the search efficiency; through the intelligent edge selector, the edges with the highest confidence in the random geometric graph are retained, thereby avoiding the negative impact of unreasonable edges on motion planning; through the memory perception predictor, the brain mechanism of integrating sensory observation information with relational structure for sensory reasoning is imitated by imitating the brain relational memory, and the subgraph structure is introduced into the node feature to improve the graph representation ability of the graph neural network and enhance the overall learning effect of the model. The present invention is an efficient and accurate robot motion planning method inspired by the spatial relational memory of the human brain. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0027] Figure 1is a flow chart of a robot motion planning method inspired by spatial relationship memory provided by an embodiment of the present invention;

[0028] Figure 2 is a structural diagram of a smart edge selector provided by an embodiment of the present invention;

[0029] Figure 3 is a schematic diagram of the structure of a memory perception predictor provided by an embodiment of the present invention;

[0030] Figure 4 It is a block diagram of a robot motion planning device inspired by spatial relationship memory provided by an embodiment of the present invention;

[0031] Figure 5 It is a structural schematic diagram of a robot motion planning device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0032] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0033] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0034] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.

[0035] In the embodiments of the present invention, sometimes a subscript such as W1 may be written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0036] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0037] The embodiment of the present invention provides a robot motion planning method inspired by spatial relationship memory, which can be implemented by a robot motion planning device, which can be a terminal or a server. Figure 1The flowchart of the robot motion planning method inspired by spatial relationship memory is shown in the figure. The processing flow of the method may include the following steps:

[0038] S1. Obtain movement starting position information, movement target position information, obstacle position information and map information.

[0039] In a feasible implementation, in a high-dimensional continuous motion scene of a robot, the location information of the starting point and the target is obtained from the information released by the robot's ROS system. The laser sensor carried by the robot is used to scan the site to obtain the obstacle location information and the current map information.

[0040] S2. Based on the selective sampling strategy, according to the motion starting position information, motion target position information and map information, a first random geometric graph is constructed in the robot's configuration space by using the K-NN algorithm.

[0041] Optionally, based on the selective sampling strategy, according to the motion starting position information, the motion target position information and the map information, in the configuration space of the robot, a first random geometric graph is constructed by a K-NN algorithm, including:

[0042] Map the robot position according to the motion starting position information, motion target position information and map information to obtain the robot positioning information;

[0043] Based on the robot's configuration space, a node set is constructed using a selective sampling strategy according to the movement starting position information, map information and robot positioning information;

[0044] According to the node set, use the K-NN algorithm to search for neighboring nodes and obtain the neighboring node set;

[0045] Edge connections are performed based on the node set and the neighboring node set to obtain a first random geometric graph.

[0046] In a feasible implementation manner, the robot positioning information of the robot is determined based on the accurate spatial position description of obstacles in the robot's environment and matching it with a preset map.

[0047] In the planning process, the present invention aims to solve the problem of ignoring environmental information in random sampling when constructing RGG. The robot generates a batch of nodes by sampling in the area between the starting point and the target with a probability of α, and uniformly samples in the entire configuration space with a probability of (1-α). This method can flexibly switch between biased sampling and uniform sampling by adjusting the hyperparameter α, balance efficiency and exploration, while maintaining probability completeness and reducing the exploration of redundant nodes.

[0048] The present invention uses the K-Nearest Neighbors algorithm (K-NN) to search for neighboring nodes and construct a first random geometric graph. The first random geometric graph gives a feasible path for the robot in the configuration space. Through this graph, a collision-free path from the initial configuration to the target configuration can be effectively planned.

[0049] S3. Based on a preset confidence threshold, the first random geometric graph and obstacle position information are input into the intelligent edge selector for edge screening to obtain a second random geometric graph.

[0050] Among them, the smart edge selector includes an encoding layer, a transformer layer, and a hidden layer;

[0051] The encoding layer is built based on the attention mechanism;

[0052] The hidden layers are constructed according to the multi-layer perceptron model structure.

[0053] In a feasible implementation manner, the present invention adopts the architecture of the intelligent edge selector as follows Figure 2 As shown, the encoding layer includes three encoders for extracting features of the nodes and edges of the first random geometric graph and the positions of obstacles respectively; the transformer layer includes two transformer modules; and the hidden layer is composed of three multi-layer perceptrons.

[0054] In the training and learning phase, the smart edge selector uses training data for each planning problem consisting of obstacles, starting vertices, and the target vertex The k-NN graph is constructed by uniformly sampling nodes in the configuration space. ,in . Through the binary cross entropy (BCE) loss To train, we minimize the confidence difference between the estimated value and the true label. Dijkstra algorithm is used as an expert planner to provide the true label for the training problem. .

[0055] Optionally, based on a preset confidence threshold, the first random geometric graph and the obstacle position information are input into a smart edge selector for edge screening to obtain a second random geometric graph, including:

[0056] According to the first random geometric graph, node information and edge information are obtained;

[0057] Input the node information, edge information and obstacle position information into the encoding layer for feature extraction to obtain the first node feature, the first edge feature and the obstacle position feature;

[0058] According to the first node feature, the first edge feature and the obstacle position feature, encoding processing is performed through the transformer layer to obtain the node-obstacle feature and the edge-obstacle feature;

[0059] The node-obstacle features and edge-obstacle features are input into the hidden layer for confidence calculation to obtain edge confidence;

[0060] According to the edge confidence and a preset confidence threshold, the edges of the first random geometric graph are screened to obtain a second random geometric graph.

[0061] In a feasible implementation, the first random geometric graph RGG As the input of the encoder, vertices and edges are encoded into the latent space. Each vertex and each edge The embedding representation of and ,in and are two different two-layer MLPs. In iterative obstacle encoding The obstacle encoding process in the tth iteration can be expressed as follows (1):

[0062] (1)

[0063] in, and are the outputs of the vertices and edges after t-1 iterations of obstacle encoding, The representation layer is normalized, B is the output of the obstacle after passing through the encoder, is the MLP layer. are the outputs of the vertices and edges after t iterations of obstacle encoding, respectively. , for , The intermediate result output by the transformer layer during the iterative update process. is a typical attention function, where Represents key, query, and value respectively.

[0064] RGG Each edge The confidence of can be evaluated using obstacle information. Specifically, through T iterations of the obstacle encoder , the information of RGG and obstacles is encoded into each edge The concatenated embedding vector of .side The confidence of Calculate, expressed as . Retain the edges whose confidence is higher than the preset threshold and obtain the second random geometric graph .

[0065] S4. According to the second random geometric graph, heuristic value calculation is performed by a memory-aware predictor to obtain a node heuristic value.

[0066] The memory-aware predictor includes a subgraph extraction layer, a graph encoding layer, a linear layer, a pooling layer, and an output layer.

[0067] In a feasible implementation manner, the memory-aware predictor proposed in the present invention is constructed based on a graph neural network, such as Figure 3 As shown in the figure. The subgraph extraction layer includes the extraction of Ego subgraph and Cut subgraph and the feature extraction of vertices and edges of the second random geometric graph. The graph encoding layer includes three encoders corresponding to the encoding of Ego subgraph, Cut subgraph, and the vertex and edge features of the second most taboo geometric graph. The output layer is constructed by three multi-layer perceptrons.

[0068] Memory perceptron uses differentiable The memory-aware predictor can be jointly trained in an end-to-end manner. During the learning phase, the training data consists of graph search problem instances. Composition, of which are all nodes and edges in the input RGG, and are the starting vertex and the target vertex respectively, is a binary vector that marks the vertices in the optimal path as 1. The training loss is defined as follows (2):

[0069] (2)

[0070] in, It is micro A vector of closed lists of module estimates, is the binary vector provided by the expert planner for the i-th training problem.

[0071] The training loss guides the path closer to the optimal path by penalizing over-explored vertices in the path. Therefore, by minimizing the training function, the differentiable The optimal path can be searched efficiently.

[0072] Optionally, performing heuristic value calculation by a memory-aware predictor according to the second random geometric graph to obtain a node heuristic value includes:

[0073] Input the subgraph extraction layer to extract subgraphs according to the second random geometric graph, and obtain the Ego subgraph and the Cut subgraph;

[0074] Based on the preset random walk process, the probability distribution is calculated according to the Ego subgraph and the Cut subgraph to obtain the random walk probability of the Ego subgraph and the random walk probability of the Cut subgraph;

[0075] Inputting the second random geometric graph into the graph encoding layer for feature extraction to obtain second node features and second edge features;

[0076] Input the random walk probability of the Ego subgraph and the random walk probability of the Cut subgraph into the graph encoding layer for encoding processing to obtain a first hidden representation vector feature and a second hidden representation vector feature;

[0077] Splicing the first hidden representation vector feature and the second hidden representation vector feature to the vertex vector through a linear layer to obtain a first spliced ​​vertex vector;

[0078] Input the first spliced ​​vertex vector into the pooling layer for aggregation iteration to obtain a second spliced ​​vertex vector;

[0079] The second concatenated vertex vector and the second edge feature vector are input into the output layer to calculate the heuristic value, so as to obtain the node heuristic value of the second random geometric graph.

[0080] In a feasible implementation, the present invention adopts two subgraph extraction strategies: Ego subgraph and Cut subgraph. Defines a k-hop EgoNetwork with node v as the root, including the neighbor nodes within k-hop of node v ,in, Represents the set of nodes within k-hop from the root node v. Cut subgraphs are obtained from the original graph by continuously and selectively removing edges.

[0081] Extracted subgraph The i-th vertex in The random walk return probability encoding of is defined as follows:

[0082] (3)

[0083] in, Represents the subgraph middle root vertex The return probability of the random walk of s steps is expressed as and Subsequently, two linear layers are applied to encode the random walk return probabilities of the Ego subgraph and the Cut subgraph into hidden representation vectors, which are and .

[0084] Given and the target vertex , then the vertex Features And edge Features The definition of is as follows:

[0085] (4)

[0086] in, and are two different two-layer MLPs.

[0087] The Ego subgraph and the Cut subgraph are mapped to the same Then, the hidden representations of the two types of subgraphs are concatenated with the vertex features to obtain the subgraph information injection features, which are and , defined as follows (5):

[0088] (5)

[0089] Graph neural networks are constructed by learning from the neighbors of each vertex Aggregate local information, iteratively update Ego subgraph and Cut subgraph information to update node features. The update method of Ego message transmission channel is as follows (6):

[0090] (6)

[0091] in, and There are three different two-layer MLPs. The Cut messaging channel is the same as the Ego channel.

[0092] After L iterations, the information injection features of the Ego subgraph and the Cut subgraph are expressed as and Finally, the complete graph representation is obtained through the pooling operation as follows (7)

[0093] (7)

[0094] Among them, the POOL operation is a global pooling function used to aggregate the information of all vertices.

[0095] vertex The perceptual prediction H can be expressed as , It is a three-layer MLP.

[0096] S5, based on differentiability The module uses a shortcut path exploration method to search for the optimal path based on the node heuristic value and the second random geometric graph to obtain the second optimal path.

[0097] Optionally, based on differentiable Module, based on the node heuristic value and the second random geometric graph, uses the shortcut path exploration method to search for the optimal path and obtain the second optimal path, including

[0098] Input the node heuristic value into the differentiable A module performs an optimal path search in a second random geometric graph to obtain a first optimal path;

[0099] According to the first optimal path, redundant nodes are deleted through a shortcut path exploration method to obtain a second optimal path.

[0100] In one possible implementation, the heuristic value is used as a differentiable The input of the module is used to search for the optimal path in the second random geometric graph RGG'.

[0101] Differentiable The module's expansion process for new nodes is as follows (8):

[0102] (8)

[0103] in Indicates the selected node, the initial open list represents all nodes of a random geometric graph, represents the total accumulated path cost from the starting point to the current node, and Indicates the estimated cost of the current node from the end point, which is replaced by the heuristic value H. As the search progresses, the selected nodes are gradually moved from Delete and Stored in the closed list C.

[0104] In the micro After the module completes the path search, the path quality still needs to be improved because there may be some detours. Therefore, the present invention designs a shortcut path exploration to identify potential shorter edges. Once these shortcuts are identified, they will be added to the exploration tree to eliminate unnecessary detours.

[0105] The search window length is preset to 2. Assume that the current window contains nodes v i-1 , v i , vi+1 , determine node v i-1 and v i+1 Is there a shortcut between v i-1 and v i+1 The edges between them do not intersect with obstacles, that is, there are shortcuts in the search window. Once these shortcuts are identified, they will be added to the exploration tree to eliminate unnecessary detours. By moving the search window, iteratively checking whether there are shortcuts in the window to improve the path quality.

[0106] In a feasible implementation, the present invention uses five key indicators to evaluate performance, namely, the success rate of collision-free path finding (SR), the number of collision checks (CK), the planning time (PT), the path cost (CO), and the penalized path cost (PO).

[0107] The performance comparison of the model proposed in this invention and the most advanced method on the above 6 data sets is shown in Table 1 (Planning performance comparison table on maze planning data set) and Table 2 (Planning performance comparison on robotic arm operation data set).

[0108] Table 1

[0109]

[0110] Table 2

[0111]

[0112] The present invention has shown remarkable performance in all tested simulation environments, achieving a success rate of nearly 100%. Especially in high-dimensional environments, the present invention significantly reduces the number of collision checks and path costs. For some methods with lower success rates, they can only successfully find paths in simpler example problems with lower path costs. For this reason, the present invention introduces penalty terms in failed paths to balance the fairness of path cost comparisons. For this indicator, the present invention achieves the best results in all simulation environments. Experimental results show that the present invention is robust and stable for decision-making tasks in various complex environments.

[0113] The present invention proposes a robot motion planning method inspired by spatial relational memory. In the process of decision-making and relational reasoning of the human brain, the brain mechanism related to spatial relational memory shows obvious advantages. Based on this, a new brain-like motion planning based on graph neural network is designed to improve the performance of robot planning in high-dimensional continuous environment. When constructing a random geometric graph, a new random geometric graph generation method is used to make the sampling nodes closer to the optimal solution, thereby improving the search efficiency; through the intelligent edge selector, the edges with the highest confidence in the random geometric graph are retained, thereby avoiding the negative impact of unreasonable edges on motion planning; through the memory perception predictor, the brain mechanism of integrating sensory observation information with relational structure for sensory reasoning is imitated by imitating the brain relational memory, and the subgraph structure is introduced into the node feature to improve the graph representation ability of the graph neural network and enhance the overall learning effect of the model. The present invention is an efficient and accurate robot motion planning method inspired by the spatial relational memory of the human brain.

[0114] Figure 4 1 is a block diagram of a robot motion planning device inspired by spatial relationship memory according to an exemplary embodiment, wherein the device is used in a robot motion planning method inspired by spatial relationship memory. Figure 4 The device includes an information acquisition module 410, a first random geometric graph construction module 420, a second random geometric graph construction module 430, a heuristic value calculation module 440 and an optimal path acquisition module 450. Among them:

[0115] The information acquisition module 410 is used to acquire the movement starting position information, obstacle position information and map information;

[0116] A first random geometric graph construction module 420 is used to construct a first random geometric graph in the robot's configuration space by using a K-NN algorithm based on a selective sampling strategy and according to the motion start position information, the motion target position information and the map information;

[0117] A second random geometric graph construction module 430 is used to input the first random geometric graph and obstacle position information into a smart edge selector for edge screening based on a preset confidence threshold to obtain a second random geometric graph;

[0118] A heuristic value calculation module 440 is used to calculate the heuristic value according to the second random geometric graph through a memory-aware predictor to obtain a node heuristic value;

[0119] The optimal path acquisition module 450 is used to obtain the optimal path based on the differentiable The module uses a shortcut path exploration method to search for the optimal path based on the graph node heuristic values ​​and the second random geometric graph to obtain the second optimal path.

[0120] Optionally, the first random geometric graph construction module 420 is further used to:

[0121] Map the robot position according to the motion starting position information, motion target position information and map information to obtain the robot positioning information;

[0122] Based on the robot's configuration space, a node set is constructed using a selective sampling strategy according to the movement starting position information, map information and robot positioning information;

[0123] According to the node set, use the K-NN algorithm to search for neighboring nodes and obtain the neighboring node set;

[0124] Edge connections are performed based on the node set and the neighboring node set to obtain a first random geometric graph.

[0125] Among them, the smart edge selector includes an encoding layer, a transformer layer, and a hidden layer;

[0126] The encoding layer is built based on the attention mechanism;

[0127] The hidden layers are constructed according to the multi-layer perceptron model structure.

[0128] Optionally, the second random geometric graph construction module 430 is further used to:

[0129] According to the first random geometric graph, node information and edge information are obtained;

[0130] Input the node information, edge information and obstacle position information into the encoding layer for feature extraction to obtain the first node feature, the first edge feature and the obstacle position feature;

[0131] According to the first node feature, the first edge feature and the obstacle position feature, encoding processing is performed through the transformer layer to obtain the node-obstacle feature and the edge-obstacle feature;

[0132] The node-obstacle features and edge-obstacle features are input into the hidden layer for confidence calculation to obtain edge confidence;

[0133] According to the edge confidence and a preset confidence threshold, the edges of the first random geometric graph are screened to obtain a second random geometric graph.

[0134] The memory-aware predictor includes a subgraph extraction layer, a graph encoding layer, a linear layer, a pooling layer, and an output layer.

[0135] Optionally, the heuristic value calculation module 440 is further used to:

[0136] Input the subgraph extraction layer to extract subgraphs according to the second random geometric graph, and obtain the Ego subgraph and the Cut subgraph;

[0137] Based on the preset random walk process, the probability distribution is calculated according to the Ego subgraph and the Cut subgraph to obtain the random walk probability of the Ego subgraph and the random walk probability of the Cut subgraph;

[0138] Inputting the second random geometric graph into the graph encoding layer for feature extraction to obtain second node features and second edge features;

[0139] Input the random walk probability of the Ego subgraph and the random walk probability of the Cut subgraph into the graph encoding layer for encoding processing to obtain a first hidden representation vector feature and a second hidden representation vector feature;

[0140] Splicing the first hidden representation vector feature and the second hidden representation vector feature to the vertex vector through a linear layer to obtain a first spliced ​​vertex vector;

[0141] Input the first spliced ​​vertex vector into the pooling layer for aggregation iteration to obtain a second spliced ​​vertex vector;

[0142] The second concatenated vertex vector and the second edge feature vector are input into the output layer to calculate the heuristic value, so as to obtain the node heuristic value of the second random geometric graph.

[0143] Optionally, the optimal path acquisition module 450 is further used to

[0144] Input graph node heuristic values ​​into differentiable A module performs an optimal path search in a second random geometric graph to obtain a first optimal path;

[0145] According to the first optimal path, redundant nodes are deleted through a shortcut path exploration method to obtain a second optimal path.

[0146] The present invention proposes a robot motion planning method inspired by spatial relational memory. In the process of decision-making and relational reasoning of the human brain, the brain mechanism related to spatial relational memory shows obvious advantages. Based on this, a new brain-like motion planning based on graph neural network is designed to improve the performance of robot planning in high-dimensional continuous environment. When constructing a random geometric graph, a new random geometric graph generation method is used to make the sampling nodes closer to the optimal solution, thereby improving the search efficiency; through the intelligent edge selector, the edges with the highest confidence in the random geometric graph are retained, thereby avoiding the negative impact of unreasonable edges on motion planning; through the memory perception predictor, the brain mechanism of integrating sensory observation information with relational structure for sensory reasoning is imitated by imitating the brain relational memory, and the subgraph structure is introduced into the node feature to improve the graph representation ability of the graph neural network and enhance the overall learning effect of the model. The present invention is an efficient and accurate robot motion planning method inspired by the spatial relational memory of the human brain.

[0147] Figure 5 is a schematic diagram of the structure of a robot motion planning device provided by an embodiment of the present invention, such as Figure 5 As shown, the robot motion planning device may include the above Figure 4 The robot motion planning device inspired by spatial relationship memory is shown. Optionally, the robot motion planning device 510 may include a first processor 2001.

[0148] Optionally, the robot motion planning device 510 may further include a memory 2002 and a transceiver 2003 .

[0149] The first processor 2001, the memory 2002 and the transceiver 2003 may be connected via a communication bus.

[0150] Combine the following Figure 5 The components of the robot motion planning device 510 are specifically introduced as follows:

[0151] The first processor 2001 is the control center of the robot motion planning device 510, and can be a processor or a general term for multiple processing elements. For example, the first processor 2001 is one or more central processing units (CPUs), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention, such as one or more microprocessors (digital signal processors, DSPs), or one or more field programmable gate arrays (field programmable gate arrays, FPGAs).

[0152] Optionally, the first processor 2001 can perform various functions of the robot motion planning device 510 by running or executing a software program stored in the memory 2002 and calling data stored in the memory 2002.

[0153] In a specific implementation, as an embodiment, the first processor 2001 may include one or more CPUs, such as Figure 5 CPU0 and CPU1 are shown in FIG.

[0154] In a specific implementation, as an embodiment, the robot motion planning device 510 may also include multiple processors, such as Figure 5 The first processor 2001 and the second processor 2004 are shown in FIG. Each of these processors may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0155] The memory 2002 is used to store the software program for executing the solution of the present invention, and is controlled to be executed by the first processor 2001. The specific implementation method can refer to the above method embodiment, which will not be repeated here.

[0156] Optionally, the memory 2002 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 2002 may be integrated with the first processor 2001, or may exist independently and access the first processor 2001 through the interface circuit ( Figure 5 (not shown) is coupled to the first processor 2001, which is not specifically limited in this embodiment of the present invention.

[0157] The transceiver 2003 is used to communicate with a network device or a terminal device.

[0158] Optionally, the transceiver 2003 may include a receiver and a transmitter ( Figure 5 The receiver is used to implement a receiving function, and the transmitter is used to implement a sending function.

[0159] Optionally, the transceiver 2003 may be integrated with the first processor 2001, or may exist independently and communicate with the first processor 2001 through the interface circuit ( Figure 5 (not shown) is coupled to the first processor 2001, which is not specifically limited in this embodiment of the present invention.

[0160] It should be noted that Figure 5 The structure of the robot motion planning device 510 shown in the figure does not constitute a limitation on the router, and the actual knowledge structure recognition device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0161] In addition, the technical effects of the robot motion planning device 510 can refer to the technical effects of the robot motion planning method inspired by spatial relationship memory described in the above method embodiment, and will not be repeated here.

[0162] It should be understood that the first processor 2001 in the embodiment of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0163] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0164] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0165] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0166] In the present invention, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0167] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0168] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0169] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0170] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0171] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0172] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0173] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0174] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A robot motion planning method inspired by spatial relation memory, characterized in that: The method comprises: Obtaining movement starting position information, movement target position information, obstacle position information and map information; Based on the selective sampling strategy, according to the movement starting position information, the movement target position information and the map information, a first random geometric graph is constructed in the robot configuration space by using a K-NN algorithm; Based on a preset confidence threshold, the first random geometric graph and the obstacle position information are input into the smart edge selector for edge screening to obtain a second random geometric graph; According to the second random geometric graph, performing heuristic value calculation by the memory-aware predictor to obtain a node heuristic value; Based on differentiable The module searches for an optimal path using a shortcut path exploration method according to the node heuristic value and the second random geometric graph to obtain a second optimal path.

2. The robot motion planning method inspired by spatial relation memory according to claim 1, characterized in that: The method based on the selective sampling strategy, according to the motion starting position information, the motion target position information and the map information, constructs a first random geometric graph in the robot configuration space by using the K-NN algorithm, including: Perform robot position mapping according to the movement starting position information, movement target position information and map information to obtain robot positioning information; Based on the configuration space of the robot, a node set is constructed using a selective sampling strategy according to the movement starting position information, the map information and the robot positioning information; According to the node set, a K-NN algorithm is used to search for neighboring nodes to obtain a neighboring node set; Perform edge connections based on the node set and the neighboring node set to obtain a first random geometric graph.

3. The robot motion planning method inspired by spatial relation memory according to claim 1, characterized in that: The intelligent edge selector includes an encoding layer, a transformer layer and a hidden layer; The encoding layer is constructed based on the attention mechanism; The hidden layer is constructed according to the multi-layer perceptron model structure.

4. The robot motion planning method inspired by spatial relation memory according to claim 3, characterized in that: The step of inputting the first random geometric graph and the obstacle position information into the smart edge selector for edge screening based on a preset confidence threshold to obtain a second random geometric graph includes: According to the first random geometric graph, obtaining node information and edge information; Inputting the node information, the edge information and the obstacle position information into the coding layer for feature extraction to obtain a first node feature, a first edge feature and an obstacle position feature; According to the first node feature, the first edge feature and the obstacle position feature, encoding processing is performed through the transformer layer to obtain a node-obstacle feature and an edge-obstacle feature; Inputting the node-obstacle feature and the edge-obstacle feature into the hidden layer to perform confidence calculation to obtain edge confidence; According to the edge confidence and a preset confidence threshold, the edges of the first random geometric graph are screened to obtain a second random geometric graph.

5. The robot motion planning method inspired by spatial relation memory according to claim 1, characterized in that: The memory-aware predictor includes a subgraph extraction layer, a graph encoding layer, a linear layer, a pooling layer and an output layer.

6. The robot motion planning method inspired by spatial relation memory according to claim 5, characterized in that: The step of calculating the heuristic value according to the second random geometric graph by the memory-aware predictor to obtain the node heuristic value includes: Inputting the second random geometric graph into the subgraph extraction layer to extract subgraphs, and obtaining an Ego subgraph and a Cut subgraph; Based on the preset random walk process, probability distribution calculation is performed according to the Ego subgraph and the Cut subgraph to obtain the random walk probability of the Ego subgraph and the random walk probability of the Cut subgraph; Inputting the second random geometric graph into the graph encoding layer for feature extraction to obtain second node features and second edge features; Inputting the random walk probability of the Ego subgraph and the random walk probability of the Cut subgraph into the graph coding layer for coding processing to obtain a first hidden representation vector feature and a second hidden representation vector feature; splicing the first hidden representation vector feature and the second hidden representation vector feature to the vertex vector through the linear layer to obtain a first spliced ​​vertex vector; Inputting the first spliced ​​vertex vector into the pooling layer for aggregation iteration to obtain a second spliced ​​vertex vector; The second concatenated vertex vector and the second edge feature vector are input into the output layer to calculate the heuristic value, so as to obtain the node heuristic value of the second random geometric graph.

7. The robot motion planning method inspired by spatial relation memory according to claim 1, characterized in that: The differentiable The module uses a shortcut path exploration method to search for an optimal path according to the node heuristic value and the second random geometric graph to obtain a second optimal path, including: Input the node heuristic value into the differentiable A module performs an optimal path search in a second random geometric graph to obtain a first optimal path; According to the first optimal path, redundant nodes are deleted by using a shortcut path exploration method to obtain a second optimal path.

8. A robot motion planning device inspired by spatial relationship memory, the robot motion planning device inspired by spatial relationship memory is used to implement the robot motion planning method inspired by spatial relationship memory as claimed in any one of claims 1 to 7, characterized in that: The device comprises: An information acquisition module is used to obtain movement starting position information, movement target position information, obstacle position information and map information; A first random geometric graph construction module is used to construct a first random geometric graph in the robot's configuration space by a K-NN algorithm based on a selective sampling strategy and according to the motion starting position information, the motion target position information and the map information; A second random geometric graph construction module, used for inputting the first random geometric graph and the obstacle position information into the smart edge selector for edge screening based on a preset confidence threshold to obtain a second random geometric graph; a heuristic value calculation module, configured to calculate a heuristic value according to the second random geometric graph by using the memory-aware predictor to obtain a node heuristic value; The optimal path acquisition module is used to obtain The module searches for an optimal path using a shortcut path exploration method according to the node heuristic value and the second random geometric graph to obtain a second optimal path.

9. A robot motion planning device, characterized in that: The robot motion planning device comprises: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program codes, which can be called by a processor to execute the method according to any one of claims 1 to 7.

Images