Unmanned system navigation method and device, unmanned system, equipment and storage medium

Abstract

The invention provides an unmanned system navigation method and device, an unmanned system, equipment and a storage medium, and relates to the technical field of unmanned systems. Neurons included in the cognitive map construction module in the unmanned system navigation model are differential equation neurons with adjustable time constants, the operation speed in the neurons can be increased, in addition, cognitive map codes are constructed through the cognitive map construction module, the map construction speed is shortened, and the navigation efficiency is improved. Therefore, the navigation speed and precision of the unmanned system can be remarkably improved in a large-scale real scene.

Description

Technical Field

[0001] This application relates to the technical field of unmanned systems, and in particular to a navigation method, device, unmanned system, equipment and storage medium for unmanned systems. Background Art

[0002] In recent years, the autonomous navigation technology of unmanned systems has developed rapidly and has been widely used in fields such as intelligent transportation, robots, and drones. Existing navigation methods mainly include path planning navigation based on high-precision environmental maps and end-to-end navigation based on deep learning. The former relies on high-precision sensors (such as lidar and high-definition cameras) to perceive the environment, and constructs a refined geometric map through technologies such as SLAM, and performs global and local path planning on this basis to achieve precise navigation. However, the construction and maintenance costs of high-precision maps are relatively high, the difficulty of real-time update is large, and the requirements for computing resources are relatively high, making it difficult to respond quickly in dynamic environments. The latter directly generates navigation control instructions from the input of camera images through a convolutional neural network, omitting the traditional navigation process, and has a certain environmental adaptability. However, due to the "black box" nature of its decision-making process and lack of interpretability, it is difficult to effectively handle complex tasks and changing scenarios, especially in long-distance navigation or repetitive environments, there may be problems of insufficient adaptability.

[0003] Therefore, in view of the limitations of existing navigation technologies, it is urgent to propose a new autonomous navigation method. Summary of the Invention

[0004] In view of the above problems, embodiments of the present application provide a navigation method, device, unmanned system, equipment and storage medium for unmanned systems, so as to overcome the above problems or at least partially solve the above problems.

[0005] In the first aspect of the embodiments of the present application, a navigation method for an unmanned system based on a cognitive map is provided, and the method includes: Collect an environmental image sequence through a camera carried by the unmanned system, where the environmental image sequence includes multiple environmental images collected within a time period starting from an initial moment, and the unmanned system is located at an initial position at the initial moment; Extract features from the environmental image sequence through the visual perception module of the unmanned system navigation model, and generate a landmark code, an obstacle code, a motion parameter value code, and a location code according to the extracted image features; Encode the target position in the target instruction relative to the initial position through the instruction encoding module of the unmanned system navigation model to generate a target position code; Through the cognitive map construction module of the unmanned system navigation model, the landmark encoding, the obstacle encoding, the motion parameter value encoding, the location encoding, and the target location encoding are processed to generate a cognitive map encoding, where the cognitive map encoding represents the environmental map from the initial location to the target location, and the neurons included in the cognitive map construction module are differential equation neurons with adjustable time constants; Through the decision-making action module of the unmanned system navigation model, the cognitive map encoding is processed to generate control parameter values for controlling the drive motors of the unmanned system, and the control parameter values include: motion direction and motion speed.

[0006] Optionally, the processing of the landmark encoding, the obstacle encoding, the motion parameter value encoding, the location encoding, and the target location encoding by the cognitive map construction module of the unmanned system navigation model to generate a cognitive map encoding includes: Inputting the landmark encoding, the obstacle encoding, the motion parameter value encoding, the location encoding, and the target location encoding into the differential equation neurons in the cognitive map construction module to obtain the cognitive map neuron state; Processing the cognitive map neuron state through a first fully connected layer to obtain the cognitive map encoding.

[0007] Optionally, the neurons included in the visual perception module are differential equation neurons with adjustable time constants; Through the visual perception module of the unmanned system navigation model, feature extraction is performed on the environmental image sequence, and landmark encoding, obstacle encoding, motion parameter value encoding, and location encoding are generated according to the extracted image features, including: Preprocessing each of the environmental images in the environmental image sequence to obtain a feature vector; Inputting the feature vector into the differential equation neurons in the visual perception module to obtain the visual neuron state; Processing the visual neuron state through a second fully connected layer to obtain the landmark encoding, the obstacle encoding, the motion parameter value encoding, and the location encoding.

[0008] Optionally, the neurons included in the instruction encoding module and the decision-making action module are both differential equation neurons with adjustable time constants; where the output of the i-th differential equation neuron is the neuron state , and the input of the i-th differential equation neuron includes: an input feature vector , and the states of other differential equation neurons connected to the i-th differential equation neuron; Any of the differential equation neurons conforms to the following expression:

[0009] where, represents the state of the th differential equation neuron; represents the state of the th differential equation neuron; represents the input feature vector; represents the time constant that controls the dynamic change of the differential equation neuron; represents the set of units connected to the th differential equation neuron; represents the th differential equation neuron transmitting information to the th differential equation neuron's connection weight; represents the perception weight from the input feature vector to the th differential equation neuron; represents the activation function.

[0010] Optionally, the decision-making action module of the unmanned system navigation model processes the cognitive map encoding to generate control parameter values for controlling the drive motor of the unmanned system, including: Processing the cognitive map encoding through the decision-making action module to obtain the action neuron state; Determining the movement direction of the unmanned system during obstacle avoidance according to the positive or negative of the action neuron state, where the movement direction includes left and right directions; Determining the movement speed of the unmanned system during obstacle avoidance according to the value of the action neuron state.

[0011] Optionally, the method further includes: Collecting a sample environmental image sequence through a camera carried by the unmanned system, and obtaining the actual values of the control parameters of the drive motor of the unmanned system during the collection of the sample environmental image sequence; Marking the initial sample position according to the position of the unmanned system when collecting the first sample environmental image in the sample environmental image sequence, and marking the sample target position according to the position of the unmanned system when collecting the last sample environmental image in the sample environmental image sequence; Inputting the sample environmental image sequence and the sample target position into the to-be-trained unmanned system navigation model to obtain the predicted values of the control parameters of the drive motor of the unmanned system; Based on the predicted control parameter values of the drive motor of the unmanned system and the actual control parameter values of the drive motor of the unmanned system, update the perception weights and connection weights of each differential equation neuron in the unmanned system navigation model to be trained, and obtain the trained unmanned system navigation model.

[0012] In a second aspect of the present application, a navigation device for an unmanned system based on a cognitive map is provided, and the device includes: An acquisition unit, configured to acquire an environmental image sequence through a camera carried by the unmanned system, where the environmental image sequence includes multiple environmental images acquired within a time period starting from an initial moment, and the unmanned system is located at an initial position at the initial moment; A feature extraction unit, configured to extract features from the environmental image sequence through a visual perception module of the unmanned system navigation model, and generate a landmark code, an obstacle code, a motion parameter value code, and a location code according to the extracted image features; An encoding unit, configured to encode a target position relative to the initial position in a target instruction through an instruction encoding module of the unmanned system navigation model to generate a target position code; A first processing unit, configured to process the landmark code, the obstacle code, the motion parameter value code, the location code, and the target position code through a cognitive map construction module of the unmanned system navigation model to generate a cognitive map code, where the cognitive map code represents an environmental map from the initial position to the target position, and the neurons included in the cognitive map construction module are differential equation neurons with adjustable time constants; A second processing unit, configured to process the cognitive map code through a decision-making action module of the unmanned system navigation model to generate control parameter values for controlling the drive motor of the unmanned system, where the control parameter values include: a motion direction and a motion speed.

[0013] Optionally, the processing of the landmark code, the obstacle code, the motion parameter value code, the location code, and the target position code through the cognitive map construction module of the unmanned system navigation model to generate a cognitive map code, and the first processing unit includes: A first input sub-unit, configured to input the landmark code, the obstacle code, the motion parameter value code, the location code, and the target position code into a differential equation neuron in the cognitive map construction module to obtain a cognitive map neuron state; A first processing sub-unit, configured to process the cognitive map neuron state through a first fully connected layer to obtain a cognitive map code.

[0014] Optionally, the neurons included in the visual perception module are differential equation neurons with adjustable time constants. Through the visual perception module of the unmanned system navigation model, feature extraction is performed on the environmental image sequence. According to the extracted image features, landmark coding, obstacle coding, motion parameter value coding, and position coding where it is located are generated. The feature extraction unit includes: A second processing subunit for preprocessing each of the environmental images in the environmental image sequence to obtain feature vectors. A second input subunit for inputting the feature vectors into the differential equation neurons in the visual perception module to obtain visual neuron states. A third processing subunit for processing the visual neuron states through a second fully connected layer to obtain the landmark coding, the obstacle coding, the motion parameter value coding, and the position coding where it is located.

[0015] Optionally, through the decision-making action module of the unmanned system navigation model, the cognitive map coding is processed to generate control parameter values for controlling the drive motor of the unmanned system. The second processing unit includes: A fourth processing subunit for processing the cognitive map coding through the decision-making action module to obtain action neuron states. A first determination subunit for determining the movement direction of the unmanned system during obstacle avoidance according to the positive or negative of the action neuron states. The movement direction includes left and right directions. A second determination subunit for determining the movement speed of the unmanned system during obstacle avoidance according to the value of the action neuron states.

[0016] Optionally, the device further includes: An acquisition subunit for collecting a sample environmental image sequence through a camera carried by the unmanned system and obtaining the actual control parameter values of the drive motor of the unmanned system during the collection of the sample environmental image sequence. A marking subunit for marking the initial sample position according to the position of the unmanned system when collecting the first sample environmental image in the collected sample environmental image sequence, and marking the sample target position according to the position of the unmanned system when collecting the last sample environmental image in the collected sample environmental image sequence. A third input subunit for inputting the sample environmental image sequence and the sample target position into the to-be-trained unmanned system navigation model to obtain the predicted control parameter values of the drive motor of the unmanned system. An update subunit, configured to update the perception weights and connection weights of each differential equation neuron in the to-be-trained unmanned system navigation model according to the predicted control parameter value of the drive motor of the unmanned system and the actual control parameter value of the drive motor of the unmanned system, so as to obtain the trained unmanned system navigation model.

[0017] In a third aspect of the present application, a unmanned system based on a cognitive map is provided. The system includes the unmanned system navigation device as described in the second aspect of the present application, and / or the unmanned system is configured to execute the steps of the unmanned system navigation method as described in the first aspect of the present application.

[0018] In a fourth aspect of the present application, an electronic device is provided, including a processor, a memory, and a program or instruction stored on the memory and executable on the processor. When the program or instruction is executed by the processor, the steps of the unmanned system navigation method as described in the first aspect of the present application are implemented.

[0019] In a fifth aspect of the present application, a readable storage medium is provided. A program or instruction is stored on the readable storage medium. When the program or instruction is executed by a processor, the steps of the unmanned system navigation method as described in the first aspect of the present application are implemented.

[0020] Advantages of the present application: The present application proposes a unmanned system navigation method based on a cognitive map. The method includes: first, collecting an environmental image sequence through a camera carried by the unmanned system; then, extracting features from the environmental image sequence through a visual perception module of the unmanned system navigation model, and generating a landmark code, an obstacle code, a motion parameter value code, and a location code according to the extracted image features; further, encoding a target position relative to the initial position in a target instruction through an instruction encoding module of the unmanned system navigation model to generate a target position code; then, processing the landmark code, the obstacle code, the motion parameter value code, the location code, and the target position code through a cognitive map construction module of the unmanned system navigation model to generate a cognitive map code. The neurons included in the cognitive map construction module are differential equation neurons with adjustable time constants; finally, processing the cognitive map code through a decision-making action module of the unmanned system navigation model to generate a control parameter value for controlling the drive motor of the unmanned system. The control parameter value includes: a motion direction and a motion speed.

[0021] This application uses a navigation model for unmanned systems based on a cognitive map completed through pre-training. The neurons included in the cognitive map construction module in this navigation model for unmanned systems are differential equation neurons with adjustable time constants, which can accelerate the computing speed within the neurons. In addition, by constructing a cognitive map encoding through the cognitive map construction module, the map construction speed is shortened, thereby significantly improving the navigation speed and accuracy of unmanned systems in large-scale real scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] To more clearly illustrate the technical solutions of the embodiments of this application, the following will briefly introduce the drawings required for the description of the embodiments of this application. Obviously, the drawings in the following description are only some embodiments of this application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0023] Figure 1 is a schematic flowchart of the steps of a method for navigating an unmanned system based on a cognitive map provided by an embodiment of this application; Figure 2 is a schematic flowchart of the steps of a method for training a navigation model for an unmanned system provided by an embodiment of this application; Figure 3 is a schematic diagram of the overall architecture of a navigation model for an unmanned system based on a cognitive map provided by an embodiment of this application; Figure 4 is a schematic diagram of a device for navigating an unmanned system based on a cognitive map provided by an embodiment of this application; Figure 5 is a schematic diagram of an electronic device provided by an embodiment of this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] The following will describe the exemplary embodiments of this application in more detail with reference to the drawings in the embodiments of this application. Although the exemplary embodiments of this application are shown in the drawings, it should be understood that this application can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that this application can be more thoroughly understood and the scope of this application can be fully communicated to those skilled in the art.

[0025] In the first aspect of the embodiments of this application, a method for navigating an unmanned system based on a cognitive map is provided, as Figure 1 shown, the method includes: Step S101, collecting an environmental image sequence through a camera carried by the unmanned system. The environmental image sequence includes multiple environmental images collected within a time period starting from the initial moment. The unmanned system is located at the initial position at the initial moment.

[0026] In this step, an unmanned system - mounted camera continuously captures an environmental image sequence from the initial moment. During this process, the unmanned system is at a known position at the initial moment, which serves as a benchmark for state update and path integration to ensure the accuracy of positioning and timely correction of errors. In some cases, pre - processing such as denoising, enhancement, distortion correction, and color calibration can also be performed on the captured image sequence to ensure data quality.

[0027] In addition, in some embodiments, the image sequence contains rich scene geometric features, obstacle information, visual landmarks, etc. Moreover, the high - frame - rate and high - resolution acquisition requirements and rapid data transmission ensure that the system can timely capture subtle environmental changes and meet the real - time response requirements, thus providing key guarantees for the efficient and accurate operation of the entire end - to - end navigation system.

[0028] Step S102: Through the visual perception module of the unmanned system navigation model, extract features from the environmental image sequence, and generate landmark encoding, obstacle encoding, motion parameter value encoding, and position encoding based on the extracted image features.

[0029] In this step, the visual perception module of the unmanned system navigation model performs deep feature extraction on the captured environmental image sequence. In some cases, by comprehensively analyzing information such as texture, edge, shape, and color in the image, key elements and feature regions in the environment can be automatically identified, and multi - level encoding can be generated based on this, including landmark encoding for identifying significant landmarks, obstacle encoding for quantitatively describing the position and shape of potential obstacles, motion parameter value encoding reflecting the current motion state, and position encoding providing precise spatial positioning. These encodings provide rich and accurate information support for subsequent cognitive map construction, path planning, and navigation decision - making.

[0030] Step S103: Through the instruction encoding module of the unmanned system navigation model, encode the target position in the target instruction relative to the initial position to generate a target position encoding.

[0031] In this step, the instruction encoding module of the unmanned system navigation model processes the target position information contained in the target instruction relative to the initial position, and uses a preset encoding algorithm to convert this information into a target position encoding, so as to provide a clear and accurate target indication. Through this encoding process, the relative position relationship of the target in the initial coordinate system can be captured, realizing a quantitative description and highly robust expression from the initial position to the target position.

[0032] Step S104: Through the cognitive map construction module of the unmanned system navigation model, process the landmark encoding, the obstacle encoding, the motion parameter value encoding, the location encoding, and the target location encoding to generate a cognitive map encoding, where the cognitive map encoding represents the environmental map from the initial location to the target location. The neurons included in the cognitive map construction module are differential equation neurons with adjustable time constants.

[0033] In this step, the cognitive map construction module of the unmanned system navigation model utilizes the landmark encoding, obstacle encoding, motion parameter value encoding, location encoding, and target location encoding generated in the previous steps to comprehensively process and fuse this multi-modal information. By using differential equation neurons with adjustable time constants to dynamically model and iteratively update the input data, a cognitive map encoding reflecting the complete environmental structure from the initial location to the target location is generated. In this application, the neurons included in the cognitive map construction module are differential equation neurons with adjustable time constants, which compress the traditional multiplication and addition operations within a single neuron and use the Euler method as the differential solver. This not only significantly improves the operation speed and makes it run faster than existing artificial neural networks, but also its bio-inspired feature, that is, using differential equation neurons with adjustable time constants to simulate the place cells and grid cells in the hippocampus and entorhinal cortex of organisms, enables the unmanned system navigation model to capture and continuously evolve spatio-temporal information more precisely, thus ensuring that the system can construct and update the internal environmental model in real time in complex or dynamic scenarios, providing solid and accurate data support for subsequent path planning, navigation decision-making, and action execution.

[0034] Step S105: Through the decision-making action module of the unmanned system navigation model, process the cognitive map encoding to generate control parameter values for controlling the drive motors of the unmanned system, where the control parameter values include: motion direction and motion speed.

[0035] In this step, the decision-making action module of the unmanned system navigation model utilizes the cognitive map encoding generated in the previous step. This cognitive map encoding integrates the landmark encoding, obstacle encoding, motion parameter value encoding, location encoding, and target location encoding extracted from the continuous environmental image sequence collected by the camera starting from the initial location, and after dynamic modeling and iterative update by the differential equation neurons, comprehensively reflects the environmental structure and spatio-temporal information between the initial location and the target location. Based on this cognitive map encoding, the decision-making action module further analyzes the relative position information of the obstacle distribution, motion state, and target instruction in the environment, and finally generates control parameter values including motion direction and motion speed. These parameters can accurately guide the drive motors of the unmanned system to achieve real-time and accurate path planning and navigation decision-making, ensuring that the system can always move smoothly towards the predetermined target in complex or dynamic environments.

[0036] In this application, an unmanned system equipped with a camera continuously acquires an environmental image sequence from the initial moment, providing continuous, high-resolution raw data with accurate timestamps for the entire system. Then, the visual perception module preprocesses these image sequences and extracts depth features, generating landmark encodings, obstacle encodings, motion parameter value encodings, and position encodings, fully capturing the geometric, obstacle, and dynamic information of the environment. Next, the instruction encoding module further encodes the target position information relative to the initial position to generate a target position encoding, thus clarifying the target direction. Then, the cognitive map construction module fuses the above-mentioned various encodings, dynamically models and iteratively updates the input data by using differential equation neurons with adjustable time constants, and compresses the traditional multiplication and addition operations into a single neuron by using an Euler method differential solver, thereby significantly improving the operation speed and generating a cognitive map encoding that comprehensively represents the environmental structure from the initial position to the target position. Finally, the decision-making action module analyzes the obstacle, motion state, and target information in the environment based on this cognitive map encoding, generates control parameter values including the motion direction and motion speed, and guides the drive motor to achieve precise motion control. By efficiently integrating multi-modal information and accelerating operations by using bio-inspired differential equation neurons, this application not only significantly improves the real-time response ability and operation efficiency of the system, but also can dynamically and accurately construct an environmental model and perform path planning, realizing high-precision, autonomous, and robust navigation decisions in complex dynamic environments.

[0037] In one embodiment, the cognitive map construction module of the unmanned system navigation model processes the landmark encoding, the obstacle encoding, the motion parameter value encoding, the position encoding, and the target position encoding to generate a cognitive map encoding, including: Inputting the landmark encoding, the obstacle encoding, the motion parameter value encoding, the position encoding, and the target position encoding into the differential equation neurons in the cognitive map construction module to obtain the cognitive map neuron state; Processing the cognitive map neuron state through a first fully connected layer to obtain the cognitive map encoding.

[0038] In this embodiment, the landmark encoding, obstacle encoding, motion parameter value encoding, location encoding, and target location encoding are input into the differential equation neurons in the cognitive map construction module. By utilizing the adjustable time constant characteristic of the neurons, dynamic modeling of environmental information is performed to obtain the cognitive map neuron state. Subsequently, the cognitive map neuron state is further processed through the first fully connected layer to extract effective features and generate the cognitive map encoding, thereby achieving an efficient representation of the environmental information from the initial location to the target location. In addition, in this embodiment, by adopting the cognitive map construction module, only the key information related to the navigation task is recorded, rather than storing the complete high-precision map details, thus significantly reducing the memory occupancy and improving the computational efficiency.

[0039] In some embodiments, the cognitive map functional area can use 24 differential equation neurons as recording nodes to simulate the place cells and grid cells in the hippocampus and entorhinal cortex of organisms, thereby completing the precise location representation and path integration tasks. This functional area can learn and predict the map representation of the current location by processing continuous motion inputs (such as linear velocity and angular velocity). Specifically, this model receives, at each time step, the sine and cosine value encodings of the linear velocity and angular velocity extracted by the perception layer as inputs, and uses the cognitive map network composed of differential equation neurons to deeply capture the dynamic information in the time series. Combining with the Euler method differential solver to accelerate the calculation, so as to enhance the computational efficiency and real-time performance. Finally, the location representation is generated through the subsequent linear output layer to achieve its own precise positioning and environmental map construction, providing efficient and stable environmental perception and decision-making support for the autonomous navigation of the unmanned system.

[0040] In one embodiment, the neurons included in the visual perception module are differential equation neurons with adjustable time constants. Through the visual perception module of the unmanned system navigation model, feature extraction is performed on the environmental image sequence, and based on the extracted image features, landmark encoding, obstacle encoding, motion parameter value encoding, and location encoding are generated, including: Preprocess each of the environmental images in the environmental image sequence to obtain feature vectors. Input the feature vectors into the differential equation neurons in the visual perception module to obtain the visual neuron state. Process the visual neuron state through the second fully connected layer to obtain the landmark encoding, the obstacle encoding, the motion parameter value encoding, and the location encoding.

[0041] In this embodiment, the visual perception module includes differential equation neurons with adjustable time constants to enhance the ability to extract dynamic features from environmental image sequences and improve the efficiency and accuracy of information processing. Specifically, this process first preprocesses each environmental image in the environmental image sequence received by the visual perception module of the unmanned system navigation model to remove noise, enhance key features, and convert them into feature vectors suitable for neural network processing. Subsequently, the feature vectors are input into the differential equation neurons in the visual perception module. Through time constant regulation, this neuron realizes the temporal dynamic modeling of image features, captures environmental changes and motion information, and obtains the visual neuron state. Then, through the second fully connected layer, non-linear transformation and feature extraction are performed on the visual neuron state to generate key coding information for characterizing the environment where the unmanned system is located, including landmark coding, obstacle coding, motion parameter value coding, and location coding. These codings not only accurately describe the environmental features around the unmanned system but also provide efficient and stable input data for subsequent cognitive map construction and path planning, ensuring the real-time performance and robustness of the navigation system in complex environments.

[0042] Exemplarily, the visual perception module includes 20 differential equation neurons. These 20 differential equation neurons are used for image feature extraction to improve the calculation efficiency and information processing ability. Specifically, this process first preprocesses the environmental image sequence collected by the camera carried by the unmanned system, downsamples the image pixels to 256×144, and evenly divides it into 8×8 image blocks, a total of 32×18. Subsequently, each image block is sequentially expanded into a vector with a length of 64, and the vectors of all blocks are sequentially concatenated to form a 576×64 vector matrix. Then, this vector matrix is used as the input and enters the visual perception module, where 20 differential equation neurons are used to extract visual information from the 576×64 input matrix. Specifically, this vector matrix first passes through a 64×1 visual layer neuron fully connected input layer and is converted into a 576×1 feature vector, and then is input into 20 differential equation neurons through neuron perception weights to obtain 20 visual neuron states. Subsequently, these neuron states are further processed through the fully connected layer to generate landmark coding, obstacle coding, motion parameter value coding, and location coding. By projecting image information onto differential equation neurons for feature extraction, this application avoids large-scale scanning calculations, can thus more quickly extract the structural information in the image, improves the extraction efficiency and calculation speed of image features, and enables the unmanned system to achieve more efficient perception and navigation in complex environments.

[0043] In this embodiment, the environmental images collected by the unmanned system are first downsampled and segmented, converted into a feature vector matrix, and feature extraction is performed through the differential equation neurons in the visual perception module. For example, 20 differential equation neurons are used in the visual area to process the input feature vector matrix, and the encoded information representing landmarks, obstacles, motion parameter values, and the current position is mapped through a fully connected layer. Compared with the traditional feature extraction method based on convolutional neural networks, this method utilizes the time dynamic characteristics of differential equation neurons to capture the spatial structure and motion information of images in a shorter calculation time, thereby improving the real-time performance and computational efficiency of visual perception, enabling the unmanned system to perceive the environment more quickly and complete path planning and navigation decisions.

[0044] In one embodiment, processing the cognitive map encoding through the decision-making action module of the unmanned system navigation model to generate control parameter values for controlling the drive motor of the unmanned system includes: Processing the cognitive map encoding through the decision-making action module to obtain the action neuron state; Determining the movement direction of the unmanned system during obstacle avoidance according to the positive or negative of the action neuron state, where the movement direction includes left and right directions; Determining the movement speed of the unmanned system during obstacle avoidance according to the value of the action neuron state.

[0045] In this embodiment, the decision-making action module generates control parameter values for controlling the drive motor of the unmanned system based on the processing of the cognitive map encoding to achieve precise obstacle avoidance and path planning. First, the cognitive map encoding is transmitted as input to the decision-making action module and the action neuron state is obtained through calculation. In practical applications, this action neuron state can be the last component of the neuron state vector after iteration by the Euler method. Subsequently, according to the positive or negative value of the action neuron state, the movement direction of the unmanned system during obstacle avoidance is determined, that is, the driving trajectory is adjusted left or right to avoid obstacles and maintain a stable navigation path. At the same time, according to the numerical value of the action neuron state, the movement speed of the unmanned system is calculated to ensure that it can flexibly adjust the direction and reasonably control the speed during obstacle avoidance, avoiding instability caused by drastic speed changes. In practical applications, the state of the action area neuron is a number between -1 and 1, representing the action degree of the unmanned system. For example, the speeds of the unmanned system moving left and right during obstacle avoidance, -1 represents moving left at 1 m / s, and 0.5 represents moving right at 0.5 m / s.

[0046] In this embodiment, the differential equation neurons are used to analyze the environmental information, enabling the unmanned system to adaptively adjust the motion parameters, improve the navigation efficiency, and enhance the motion stability and safety in complex environments.

[0047] In one embodiment, the neurons included in the instruction encoding module and the decision-making action module are both differential equation neurons with adjustable time constants; among them, the output of the th differential equation neuron is the neuron state , and the input of the th differential equation neuron includes: the input feature vector , and the states of other differential equation neurons connected to the th differential equation neuron. Any of the differential equation neurons conforms to the following expression (1): (1) where represents the state of the th differential equation neuron; represents the state of the th differential equation neuron; represents the input feature vector; represents the time constant that controls the dynamic change of the differential equation neuron; represents the set of units connected to the th differential equation neuron; represents the connection weight for the th differential equation neuron to transmit information to the th differential equation neuron; represents the perception weight from the input feature vector to the th differential equation neuron; represents the activation function.

[0048] In this application, the neurons included in the instruction encoding module and the decision-making action module are also both differential equation neurons with adjustable time constants. Among them, the output of the th differential equation neuron is the neuron state , and the input of the th differential equation neuron includes: the input feature vector , and the states of other differential equation neurons connected to the th differential equation neuron.

[0049] It should be noted that in the unmanned system navigation model, for different modules, the input feature vector is different. For example, in the visual perception module, the input feature vector is the visual feature vector, and in the cognitive map construction module, the input feature vector To characterize the feature vectors of landmark coding, obstacle coding, motion parameter value coding, location coding, and target location coding, in the instruction coding module, input the feature vectors To be the feature vector of the target location relative to the initial location in the target instruction, in the decision-making action module, input the feature vector To be the feature vector representing the cognitive map coding.

[0050] Among them, any differential equation neuron conforms to the following expression (1): (1) Among them, represents the state of the th differential equation neuron; represents the state of the th differential equation neuron; represents the input feature vector; represents the time constant that controls the dynamic change of the differential equation neuron; represents the set of units connected to the th differential equation neuron; represents the connection weight for the th differential equation neuron to transmit information to the th differential equation neuron; represents the perception weight from the input feature vector to the th differential equation neuron, represents the activation function.

[0051] In some embodiments, the present application also provides a training method for the unmanned system navigation model, and the method is as Figure 2 shown, including: Step S201, through the camera carried by the unmanned system, collect a sequence of sample environment images, and obtain the actual values of the control parameters of the driving motor of the unmanned system during the collection of the sequence of sample environment images.

[0052] In this step, through the camera carried by the unmanned system, collect a sequence of sample environment images, and synchronously record the actual values of the control parameters of the driving motor of the unmanned system during the collection process for subsequent model training and optimization. Specifically, during the sample data collection stage, the unmanned system travels along a preset path, and obtains a sequence of environment images in the form of continuous frames through the carried camera, while simultaneously obtaining the actual values of the control parameters of the driving motor in real time, including the motion direction, motion speed, etc., to accurately reflect the driving state of the unmanned system in different environments.

[0053] Step S202: Mark the initial sample position according to the position of the unmanned system when the first sample environment image in the acquired sample environment image sequence is collected, and mark the sample target position according to the position of the unmanned system when the last sample environment image in the acquired sample environment image sequence is collected.

[0054] In this step, mark the initial sample position according to the position of the unmanned system when the first sample environment image in the acquired sample environment image sequence is collected. At the same time, mark the sample target position according to the position of the unmanned system when the last sample environment image in the acquired sample environment image sequence is collected. Specifically, during the sample data collection process, the position information of the unmanned system is recorded synchronously with the environment image to ensure the spatio-temporal consistency of the data. By determining the start and end positions of the sample environment image sequence, the movement trajectory of the unmanned system during this data collection process can be clarified, thus providing a reference for the path planning and behavior decision-making of the subsequent navigation model. In addition, this step helps to establish a mapping of position information based on environmental features, enabling the training model to better understand the spatial relationship from the initial position to the target position, and improving the learning effect and path inference ability of the navigation system.

[0055] Step S203: Input the sample environment image sequence and the sample target position into the unmanned system navigation model to be trained, and obtain the predicted value of the control parameter of the drive motor of the unmanned system.

[0056] In this step, input the sample environment image sequence and the sample target position into the unmanned system navigation model to be trained, and obtain the predicted value of the control parameter of the drive motor of the unmanned system. Specifically, the unmanned system navigation model to be trained receives the acquired sample environment image sequence, extracts environmental features using the visual perception module, generates landmark encoding, obstacle encoding, motion parameter value encoding, and position encoding, and at the same time combines the marked sample target position to construct a cognitive map encoding to represent the environmental information of the unmanned system from the initial sample position to the sample target position. On this basis, the decision-making action module infers the traveling strategy of the unmanned system according to the cognitive map encoding, and outputs the predicted value of the control parameter for drive motor control, including the movement direction and movement speed. This step realizes the construction of the training input for the unmanned system navigation model, enabling the model to learn the mapping relationship from environmental perception to motion decision-making in the subsequent training process, and improving the autonomous navigation ability of the unmanned system in complex environments.

[0057] Step S204: Update the perception weights and connection weights of each differential equation neuron in the unmanned system navigation model to be trained according to the predicted value of the control parameter of the drive motor of the unmanned system and the actual value of the control parameter of the drive motor of the unmanned system, and obtain the trained unmanned system navigation model.

[0058] In one embodiment, there is provided an overall architecture schematic diagram of an unmanned system navigation model based on a cognitive map as shown in Figure 3 and shown as follows: Figure 3 as follows: This framework diagram shows the process of image acquisition, preprocessing, the architecture of the unmanned system navigation model, and driving the unmanned system. Among them, the unmanned system navigation model is divided into multiple modules, including: a visual perception module, an instruction encoding module, a cognitive map construction module, and a decision-making action module.

[0059] Among them, the visual perception module is divided into a visual function area and an integration function area. The instruction encoding module includes a target instruction function area. The cognitive map construction module includes a cognitive map function area. The decision-making action module is divided into a decision-making function area and an action function area.

[0060] As shown in Figure 3 , the input end of this architecture, i.e., the dashed box A in Figure 3 , represents that the camera carried by the unmanned system performs visual acquisition on the external environment to obtain an environmental image sequence. The example in the figure is a forest scene, indicating that this model can perform navigation tasks in a natural and complex environment. The input end of this architecture, i.e., the dashed box in Figure 3 , also includes the relative position information of the target position.

[0061] An intermediate processing end of this architecture, i.e., the dashed box B in Figure 3 , is the visual perception module. The left side is the visual function area, representing the visual perception network used to extract image features. This module inputs the original image obtained by the camera into differential equation neurons to complete the preliminary extraction and encoding of landmarks, obstacles, motion parameter values, and the location. The right side is the integration function area, which is used to further extract features from the landmark encoding, obstacle encoding, motion parameter value encoding, and location encoding extracted by the visual function area.

[0062] An intermediate processing end of this architecture, i.e., the dashed box C in Figure 3 , is the instruction encoding module, which includes a target instruction function area and is used to encode according to the input relative position information of the target to obtain the target position encoding.

[0063] An intermediate processing end of this architecture, i.e., the dashed box in Figure 3The dashed box D in [description] is the cognitive map construction module, which includes a cognitive map functional area. It appears in the figure in a form similar to a SLAM map or a grayscale environmental map, representing the core concept of the "cognitive map". Here, the key encodings obtained from the visual perception module (such as landmarks, obstacles, motion parameter values, current position, etc.) and the target position encoding obtained from the instruction encoding module are jointly input into a network constructed by differential equation neurons, thereby generating or updating the "cognitive map encoding". Among them, the network structure constructed by differential equation neurons is also shown in the dashed box D.

[0064] An intermediate processing end of this architecture is Figure 3 The dashed box E in [description] is the decision-making action module, which is divided into a decision-making functional area and an action functional area. Among them, the left side is the decision-making functional area, which is connected to the output of the cognitive map module and is used to make navigation decisions based on environmental encoding and target position information. This network will output control parameters such as the movement direction and movement speed. The right side is the action functional area, which is connected to the unmanned system in the dashed box F in [description]. It means that the control parameters such as the movement direction and movement speed output by the decision-making functional area are converted into control instructions for the drive motor (such as motor speed or servo angle) and output by the action functional area to the unmanned system, so that the unmanned system can perform actual actions. The waveform diagram therein reflects the timing characteristics of the control signal. Figure 3 The dashed box F in [description] is connected to the unmanned system. It means that the control parameters such as the movement direction and movement speed output by the decision-making functional area are converted into control instructions for the drive motor (such as motor speed or servo angle) and output by the action functional area to the unmanned system, so that the unmanned system can perform actual actions. The waveform diagram therein reflects the timing characteristics of the control signal.

[0065] In this step, according to the predicted value of the control parameter of the drive motor of the unmanned system and the actual value of the control parameter of the drive motor of the unmanned system, the perception weights and connection weights of each differential equation neuron in the unmanned system navigation model to be trained are updated to obtain the trained unmanned system navigation model. Specifically, this process uses an error backpropagation mechanism, takes the deviation between the predicted value and the actual value of the control parameter as the loss signal, and adjusts the weights of the differential equation neurons in the visual perception module, the cognitive map construction module, and the decision-making action module to optimize the feature extraction, environmental modeling, and path decision-making capabilities. Since the differential equation neuron can complete multiplication and addition operations within a single neuron and uses an Euler method differential solver, it has a faster optimization speed compared to traditional neural networks, making the training process more efficient. In addition, the differential equation neurons in the cognitive map construction module learn the dynamic information in the time series, improve the accuracy of the unmanned system's self-positioning and path reasoning, thereby enhancing the autonomous navigation performance of the unmanned system in complex environments and achieving precise obstacle avoidance and stable motion control.

[0066] The present application proposes a navigation method for an unmanned system based on a cognitive map. The method includes: First, an environmental image sequence is collected through a camera carried by the unmanned system; Then, through the visual perception module of the unmanned system navigation model, feature extraction is performed on the environmental image sequence, and according to the extracted image features, landmark coding, obstacle coding, motion parameter value coding, and position coding where it is located are generated; Also, through the instruction coding module of the unmanned system navigation model, the target position relative to the initial position in the target instruction is coded to generate a target position coding; After that, through the cognitive map construction module of the unmanned system navigation model, the landmark coding, the obstacle coding, the motion parameter value coding, the position coding where it is located, and the target position coding are processed to generate a cognitive map coding. The neurons included in the cognitive map construction module are differential equation neurons with adjustable time constants; Finally, through the decision-making action module of the unmanned system navigation model, the cognitive map coding is processed to generate control parameter values for controlling the drive motor of the unmanned system. The control parameter values include: motion direction and motion speed.

[0067] The present application uses a pre-trained unmanned system navigation model based on a cognitive map. The neurons included in the cognitive map construction module of the unmanned system navigation model are differential equation neurons with adjustable time constants, which can accelerate the operation speed within the neurons. In addition, by constructing the cognitive map coding through the cognitive map construction module, the map construction speed is shortened, so that the navigation speed and accuracy of the unmanned system can be significantly improved in a large-scale real scenario.

[0068] Based on the same inventive concept, in the second aspect of the present application, a navigation device for an unmanned system based on a cognitive map is provided, as Figure 4 shown. The device includes: An acquisition unit 201, configured to collect an environmental image sequence through a camera carried by the unmanned system. The environmental image sequence includes multiple environmental images collected during a time period starting from an initial moment. The unmanned system is located at an initial position at the initial moment; A feature extraction unit 202, configured to perform feature extraction on the environmental image sequence through the visual perception module of the unmanned system navigation model, and generate landmark coding, obstacle coding, motion parameter value coding, and position coding where it is located according to the extracted image features; An encoding unit 203, configured to encode the target position relative to the initial position in the target instruction through the instruction coding module of the unmanned system navigation model to generate a target position coding; The first processing unit 204 is configured to process the landmark encoding, the obstacle encoding, the motion parameter value encoding, the location encoding, and the target location encoding through the cognitive map construction module of the unmanned system navigation model to generate a cognitive map encoding, where the cognitive map encoding represents the environmental map from the initial location to the target location, and the neurons included in the cognitive map construction module are differential equation neurons with adjustable time constants; The second processing unit 205 is configured to process the cognitive map encoding through the decision-making action module of the unmanned system navigation model to generate a control parameter value for controlling the drive motor of the unmanned system, where the control parameter value includes: a motion direction and a motion speed.

[0069] Optionally, the processing of the landmark encoding, the obstacle encoding, the motion parameter value encoding, the location encoding, and the target location encoding through the cognitive map construction module of the unmanned system navigation model to generate a cognitive map encoding, the first processing unit 204 includes: A first input subunit, configured to input the landmark encoding, the obstacle encoding, the motion parameter value encoding, the location encoding, and the target location encoding into the differential equation neurons in the cognitive map construction module to obtain cognitive map neuron states; A first processing subunit, configured to process the cognitive map neuron states through a first fully connected layer to obtain a cognitive map encoding.

[0070] Optionally, the neurons included in the visual perception module are differential equation neurons with adjustable time constants; Feature extraction is performed on the environmental image sequence through the visual perception module of the unmanned system navigation model, and according to the extracted image features, a landmark encoding, an obstacle encoding, a motion parameter value encoding, and a location encoding are generated. The feature extraction unit 202 includes: A second processing subunit, configured to preprocess each of the environmental images in the environmental image sequence to obtain feature vectors; A second input subunit, configured to input the feature vectors into the differential equation neurons in the visual perception module to obtain visual neuron states; A third processing subunit, configured to process the visual neuron states through a second fully connected layer to obtain the landmark encoding, the obstacle encoding, the motion parameter value encoding, and the location encoding.

[0071] Optionally, the decision-making action module of the unmanned system navigation model processes the cognitive map encoding to generate a control parameter value for controlling the drive motor of the unmanned system. The second processing unit 205 includes: A fourth processing subunit, configured to process the cognitive map encoding through the decision-making action module to obtain the action neuron state; A first determination subunit, configured to determine the movement direction of the unmanned system during obstacle avoidance according to the positive or negative of the action neuron state, where the movement direction includes left and right directions; A second determination subunit, configured to determine the movement speed of the unmanned system during obstacle avoidance according to the value of the action neuron state.

[0072] Optionally, the device further includes: An acquisition subunit, configured to collect a sample environment image sequence through a camera carried by the unmanned system, and obtain the actual value of the control parameter of the drive motor of the unmanned system during the collection of the sample environment image sequence; A marking subunit, configured to mark the initial sample position according to the position of the unmanned system when the first sample environment image in the collected sample environment image sequence is acquired, and mark the sample target position according to the position of the unmanned system when the last sample environment image in the collected sample environment image sequence is acquired; A third input subunit, configured to input the sample environment image sequence and the sample target position into the to-be-trained unmanned system navigation model to obtain a predicted value of the control parameter of the drive motor of the unmanned system; An update subunit, configured to update the perception weight and connection weight of each differential equation neuron in the to-be-trained unmanned system navigation model according to the predicted value of the control parameter of the drive motor of the unmanned system and the actual value of the control parameter of the drive motor of the unmanned system, so as to obtain the trained unmanned system navigation model.

[0073] Based on the same inventive concept, in the third aspect of the present application, a cognitive map-based unmanned system is provided. The system includes the unmanned system navigation device as described in the second aspect of the present application, and / or the unmanned system is configured to execute the steps of the unmanned system navigation method as described in the first aspect of the present application.

[0074] Based on the same inventive concept, in the fourth aspect of the present application, a kind of Figure 5 shown electronic device 100 includes a processor 120, a memory 110, and a program or instruction stored on the memory 110 and executable on the processor 120. When the program or instruction is executed by the processor 120, the steps of the unmanned system navigation method as described in the first aspect of the present application are implemented.

[0075] In the fifth aspect of the present application, a readable storage medium is provided. Programs or instructions are stored on the readable storage medium, and when the programs or instructions are executed by a processor, the steps of the unmanned system navigation method described in the first aspect of the present application are implemented.

[0076] In each embodiment described in this specification, the key points are the differences from other embodiments. For the same or similar parts among the various embodiments, reference can be made to each other.

[0077] Those skilled in the art should understand that the embodiments of the present application can be provided as methods, devices, or computer program products. Therefore, the embodiments of the present application can take the form of completely hardware embodiments, completely software embodiments, or embodiments combining software and hardware aspects. Moreover, the embodiments of the present application can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program codes.

[0078] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of methods, terminal devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of processes and / or blocks in the flowchart and / or block diagram can also be implemented. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal devices generate a device for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0079] These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing terminal device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured product including an instruction device, and the instruction device implements the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0080] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device, so that a series of operation steps are executed on the computer or other programmable terminal device to generate a computer-implemented process. Therefore, the instructions executed on the computer or other programmable terminal device provide for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1Steps of the functions specified in one or more boxes.

[0081] Although the preferred embodiments of the embodiments of the present application have been described, those skilled in the art can make additional changes and modifications to these embodiments once they know the basic creative concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications that fall within the scope of the embodiments of the present application.

[0082] Finally, it should also be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or terminal device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or terminal device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or terminal device comprising the element.

[0083] The above has introduced in detail a method, device, unmanned system, equipment and storage medium for unmanned system navigation. Specific examples are used in this text to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, there will be changes in the specific implementation manner and application scope according to the idea of the present application. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A navigation method for an unmanned system based on a cognitive map, characterized in that: The method comprises: Collecting an environment image sequence by a camera carried by the unmanned system, the environment image sequence comprising a plurality of environment images collected within a time period starting from an initial moment, the unmanned system being located at an initial position at the initial moment; Extracting features of the environment image sequence through the visual perception module of the unmanned system navigation model, and generating landmark codes, obstacle codes, motion parameter value codes, and location codes according to the extracted image features; By means of the instruction encoding module of the unmanned system navigation model, the target position relative to the initial position in the target instruction is encoded to generate a target position code; The landmark code, the obstacle code, the motion parameter value code, the location code and the target location code are processed by the cognitive map construction module of the unmanned system navigation model to generate a cognitive map code, wherein the cognitive map code represents an environment map from the initial location to the target location, and the neurons included in the cognitive map construction module are differential equation neurons with adjustable time constants; The cognitive map code is processed by the decision-making action module of the unmanned system navigation model to generate control parameter values ​​for controlling the driving motor of the unmanned system, wherein the control parameter values ​​include: movement direction and movement speed.

2. The unmanned system navigation method based on cognitive map according to claim 1, characterized in that: The cognitive map construction module of the unmanned system navigation model processes the landmark code, the obstacle code, the motion parameter value code, the location code, and the target location code to generate a cognitive map code, including: Inputting the landmark code, the obstacle code, the motion parameter value code, the position code, and the target position code into the differential equation neuron in the cognitive map construction module to obtain the cognitive map neuron state; The cognitive map neuron states are processed through the first fully connected layer to obtain the cognitive map encoding.

3. The unmanned system navigation method based on cognitive map according to claim 1, characterized in that: The neurons included in the visual perception module are differential equation neurons with adjustable time constants; The visual perception module of the unmanned system navigation model extracts features from the environment image sequence, and generates landmark codes, obstacle codes, motion parameter value codes, and location codes according to the extracted image features, including: Preprocessing each of the environmental images in the environmental image sequence to obtain a feature vector; Inputting the feature vector into the differential equation neuron in the visual perception module to obtain the state of the visual neuron; The visual neuron state is processed by a second fully connected layer to obtain the landmark code, the obstacle code, the motion parameter value code, and the position code.

4. The unmanned system navigation method based on cognitive map according to claim 3 is characterized in that: The neurons included in the instruction encoding module and the decision action module are differential equation neurons with adjustable time constants; The output of a differential equation neuron is the neuron state , No. The input of the differential equation neuron includes: the input feature vector , and The states of other differential equation neurons that a differential equation neuron is connected to; Any of the differential equations of neurons meets the following expression: in, Indicates The state of the neuron in a differential equation; Indicates The state of the neuron in a differential equation; represents the input feature vector; represents the time constant of the neuron dynamics governing the differential equation; Indicates A collection of units connected by differential equation neurons; Indicates The differential equation neuron transmits information to the The connection weights of the differential equation neurons; Represents the input feature vector to the The perceptual weights of the differential equation neurons; Represents the activation function.

5. The unmanned system navigation method based on cognitive map according to claim 4 is characterized in that: The cognitive map code is processed by the decision action module of the unmanned system navigation model to generate a control parameter value for controlling a drive motor of the unmanned system, including: Processing the cognitive map encoding through the decision action module to obtain the action neuron state; Determining the movement direction of the unmanned system when avoiding obstacles according to the positive or negative state of the action neuron, wherein the movement direction includes left and right directions; The movement speed of the unmanned system when avoiding obstacles is determined according to the value of the action neuron state.

6. The unmanned system navigation method based on cognitive map according to any one of claims 1 to 5, characterized in that: The method further comprises: Collecting a sample environment image sequence through a camera carried by the unmanned system, and obtaining actual values ​​of control parameters of a driving motor of the unmanned system during the period of collecting the sample environment image sequence; Marking an initial sample position according to the position of the unmanned system when the first sample environment image in the sample environment image sequence is collected, and marking a sample target position according to the position of the unmanned system when the last sample environment image in the sample environment image sequence is collected; Inputting the sample environment image sequence and the sample target position into the unmanned system navigation model to be trained to obtain the control parameter prediction value of the driving motor of the unmanned system; According to the predicted value of the control parameter of the driving motor of the unmanned system and the actual value of the control parameter of the driving motor of the unmanned system, the perception weight and connection weight of each differential equation neuron in the unmanned system navigation model to be trained are updated to obtain the trained unmanned system navigation model.

7. An unmanned system navigation device based on cognitive map, characterized in that: The device comprises: A collection unit, configured to collect an environment image sequence through a camera carried by the unmanned system, wherein the environment image sequence includes a plurality of environment images collected within a time period starting from an initial moment, and the unmanned system is located at an initial position at the initial moment; A feature extraction unit is used to extract features from the environment image sequence through a visual perception module of the unmanned system navigation model, and generate landmark codes, obstacle codes, motion parameter value codes, and location codes according to the extracted image features; An encoding unit, configured to encode a target position relative to the initial position in a target instruction through an instruction encoding module of the unmanned system navigation model, and generate a target position code; A first processing unit is used to process the landmark code, the obstacle code, the motion parameter value code, the location code and the target location code through a cognitive map construction module of the unmanned system navigation model to generate a cognitive map code, wherein the cognitive map code represents an environment map from the initial location to the target location, and the neurons included in the cognitive map construction module are differential equation neurons with adjustable time constants; The second processing unit is used to process the cognitive map code through the decision-making action module of the unmanned system navigation model to generate control parameter values ​​for controlling the drive motor of the unmanned system, and the control parameter values ​​include: movement direction and movement speed.

8. An unmanned system based on cognitive maps, characterized in that: The system includes the unmanned system navigation device according to claim 7, and / or the unmanned system is used to execute the steps of the unmanned system navigation method according to any one of claims 1-6.

9. An electronic device, characterized in that: It includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the unmanned system navigation method as described in any one of claims 1 to 6.

10. A readable storage medium, characterized in that: The readable storage medium stores programs or instructions, and when the programs or instructions are executed by the processor, the steps of the unmanned system navigation method as described in any one of claims 1-6 are implemented.

Images