A neuromorphic brain-like decision-making system

Abstract

The present invention discloses a neuromorphic brain-like decision-making system, which relates to the field of artificial intelligence technology. The present invention abstracts object information into symbols and marks them, combines them with position coordinates, takes the initial position of the robot as the starting point, determines the coordinates of the task passing points and the end point, and uses a graph search algorithm to generate an executable path; then calculates the walking distance of the path, and obtains an estimated walking time in combination with the speed range set by the user; at the same time, a relationship between distance and energy consumption is preset, and the estimated energy consumption is determined by matching, and the final energy consumption performance value is calculated on this basis, and the final energy consumption performance value and estimated walking time of the path are extracted. Then, combined with the user's energy consumption preference habits and efficiency preference habits and their weight coefficient sets, a comprehensive evaluation index of each path is calculated, and the path with the highest index is selected as the final walking path, thereby realizing intelligent decision-making based on user preferences and multi-dimensional evaluation, balancing energy consumption and efficiency, and improving the robot's operating efficiency and user experience.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a neuromorphic brain-like decision-making system. Background Art

[0002] In today's era of rapid technological development, robotics technology is increasingly used in many fields.

[0003] However, the existing neuromorphic brain-like decision-making systems used in robots still have the following shortcomings:

[0004] In complex and ever-changing real-world environments, robots need to efficiently process massive amounts of complex information to make accurate decisions. However, traditional systems have limited information processing capabilities, making it difficult to quickly and accurately identify various objects in the environment, analyze their relationships, and their impact on their own tasks. For example, when performing tasks in indoor scenes, faced with numerous obstacles and dynamic elements such as furniture and people, traditional decision-making systems are often unable to quickly plan a reasonable path based on the user's decision-making habits, resulting in inefficient task execution or even failure.

[0005] To this end, a neuromorphic brain-like decision-making system is introduced. Summary of the Invention

[0006] The purpose of the present invention is to propose a neuromorphic brain-like decision-making system in order to solve the problems pointed out in the background technology.

[0007] The purpose of the present invention can be achieved through the following technical solutions: A neuromorphic brain-like decision-making system, comprising:

[0008] Environmental Perception Module: Receives user commands, uses semantic analysis to determine the tasks the user needs to perform, and then comprehensively collects environmental data based on the tasks required by the user commands to obtain feature information of objects. Feature information includes the shape, color, texture, and position coordinates of objects in space. Feature extraction is performed on the collected environmental data to identify different types of objects.

[0009] Inference and decision-making module: This module predefines a symbolic domain and a logical operator group. The symbolic domain represents objects and location information in the environment, while the logical operator group uses a pre-set algorithm to comprehensively analyze the relationships between objects within the symbolic domain and plan the robot's final path to perform the task.

[0010] Reaction execution module: Generates corresponding control instructions based on the final walking path planned by the deduction and decision module, and drives the robot to execute the planned final walking path.

[0011] As a preferred embodiment of the present invention, the logical operator group uses a preset algorithm to perform a comprehensive analysis on the relationship between objects in the symbol domain, specifically:

[0012] Abstract the information elements of each object in the environment into symbols, that is, mark the symbols according to the object type; obtain the coordinates of the position information of each object in the environment;

[0013] Taking the current robot's initial position as the starting point, obtain the waypoints and end point required for the task, and determine the coordinates corresponding to the starting point, waypoints, and end point;

[0014] Starting from the starting point of the robot, a graph-based search algorithm is used to search for paths and generate executable paths corresponding to each current task.

[0015] As a preferred embodiment of the present invention, the final walking path of the robot to perform the task is planned as follows:

[0016] Calculate the required walking distance for each executable path corresponding to the current task, and at the same time obtain the robot's travel speed range set by the user; extract the middle value within the travel speed range and calculate it against the required walking distance for each executable path corresponding to the current task. That is, divide each group of required walking distances by the middle value to obtain the estimated required walking time for each executable path corresponding to the current task;

[0017] Preset each set of distance value ranges corresponding to the required walking distance, and set each set of distance value ranges to correspond to an estimated energy consumption; match the required walking distance of each executable path corresponding to the current task with each set of preset distance value ranges, thereby determining the estimated energy consumption of each executable path corresponding to the current task;

[0018] Analyze the estimated energy consumption of the executable path corresponding to each current task, so as to determine the final energy consumption performance value of the executable path corresponding to each current task;

[0019] The final energy consumption performance value and estimated walking time of each executable path corresponding to the current task are extracted, and a comprehensive evaluation is performed based on the user's preference habits to determine the final walking path.

[0020] As a preferred embodiment of the present invention, the final energy consumption performance value of the executable path corresponding to each current task is determined, specifically:

[0021] Count the number of turns and potential impact adjustments required by the robot when simulating the execution of each executable path corresponding to the current task;

[0022] Extract the symbol of the movable object from the symbol domain, and obtain the specific coordinates corresponding to the movable object symbol, which are recorded as the influence coordinates. Obtain the closest distance between the robot and each set of influence coordinates during the execution of the corresponding path at the current time point, which is recorded as the influence distance.

[0023] Preset reference distances for the impact distances corresponding to different movable objects; compare each group of impact distances in the executable path corresponding to each current task with the corresponding preset reference distances, and count the number of impact distances in the executable path corresponding to each current task that are smaller than the corresponding preset reference distance as the number of potential impact adjustments for the executable path corresponding to each current task;

[0024] Set the weight coefficients corresponding to the required number of turns and the potential impact adjustment number, respectively, multiply the required number of turns and the potential impact adjustment number of each executable path corresponding to the current task by the corresponding set weight coefficients, and then sum them to obtain the energy consumption added value of the executable path corresponding to each current task;

[0025] Preset the value ranges of each group of additional values ​​corresponding to the energy consumption additional value, and set each group of additional value ranges to correspond to an energy consumption additional coefficient;

[0026] Match the energy consumption additional value of the executable path corresponding to each current task with the value range of each group of additional values, so as to obtain the energy consumption additional coefficient of the executable path corresponding to each current task;

[0027] The energy consumption additional coefficient of the executable path corresponding to each current task is multiplied by the estimated energy consumption to obtain the final energy consumption performance value of the executable path corresponding to each current task.

[0028] As a preferred embodiment of the present invention, the final energy consumption performance value and estimated walking time of each executable path corresponding to the current task are extracted, and a comprehensive evaluation is performed in combination with the user's preference habits, specifically:

[0029] Extract the final energy consumption performance value and estimated walking time of each executable path corresponding to the current task, and preset the performance value ranges and duration value ranges corresponding to the final energy consumption performance value and the estimated walking time respectively;

[0030] Set the value range of each performance value and the value range of each duration to correspond to a set of energy consumption scores and efficiency scores respectively;

[0031] The final energy consumption performance value and estimated walking time of the executable path corresponding to each current task are matched with the value range of each group of performance values ​​and the value range of each group of duration, so as to determine the energy consumption score and efficiency score of the executable path corresponding to each current task.

[0032] As a preferred embodiment of the present invention, the final energy consumption performance value and estimated walking time of each executable path corresponding to the current task are extracted, and a comprehensive evaluation is performed based on the user's preference habits, which also includes:

[0033] Preset weight coefficient sets corresponding to energy consumption biased habits and efficiency biased habits, respectively. The weight coefficient sets corresponding to energy consumption biased habits and efficiency biased habits both include weight coefficients corresponding to energy consumption scores and efficiency scores, respectively.

[0034] Extract the weight coefficients corresponding to the energy consumption score and efficiency score in the energy consumption bias habit, multiply the energy consumption score and efficiency score of the executable path corresponding to each current task by the corresponding weight coefficient in the energy consumption bias habit, and then sum them to obtain the comprehensive evaluation index of the executable path corresponding to each current task in the energy consumption bias habit;

[0035] Extract the weight coefficients corresponding to the energy consumption score and efficiency score in the efficiency-biased habit, multiply the energy consumption score and efficiency score of the executable path corresponding to each current task by the corresponding weight coefficient in the efficiency-biased habit, and then sum them to obtain the comprehensive evaluation index of the executable path corresponding to each current task in the efficiency-biased habit;

[0036] Taking the current time point as the starting point, extract the bias habits selected by the user within the set time window before the starting point, and count the number of biases corresponding to energy consumption bias habits and efficiency bias habits within the set time window;

[0037] If the number of energy-biased habits is greater than the number of efficiency-biased habits, then the executable path with the highest comprehensive evaluation index among the executable paths corresponding to the current tasks in the energy-biased habit is selected as the final walking path;

[0038] If the number of energy consumption biased habits is less than the number of efficiency biased habits, then the executable path with the highest comprehensive evaluation index among the executable paths corresponding to the current tasks in the efficiency biased habits is selected as the final walking path.

[0039] Compared with the prior art, the present invention has the following beneficial effects:

[0040] The present invention receives user commands, uses semantic analysis to determine tasks, and uses sensors such as lidar, cameras, and depth cameras to collect environmental data in all directions. It extracts characteristic information such as the shape, color, texture, and position coordinates of objects, identifies different types of objects, and provides basic data for subsequent decision-making.

[0041] The present invention abstracts object information into symbols and marks them, combines them with position coordinates, takes the robot's initial position as the starting point, determines the coordinates of the task's passing points and end point, and uses a graph search algorithm to generate an executable path; then calculates the path walking distance, and derives the estimated walking time in combination with the speed range set by the user; at the same time, the relationship between distance and energy consumption is preset, and the estimated energy consumption is determined by matching. On this basis, the final energy consumption performance value is calculated, and the final energy consumption performance value and estimated walking time of the path are extracted. Then, combined with the user's energy consumption preference habits and efficiency preference habits and their weight coefficient sets, the comprehensive evaluation index of each path is calculated, and the path with the highest index is selected as the final walking path. This realizes intelligent decision-making based on user preferences and multi-dimensional evaluation, balances energy consumption and efficiency, and improves the robot's operating efficiency and user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] To facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0043] Figure 1 This is a principle block diagram of the present invention. DETAILED DESCRIPTION

[0044] The technical solutions of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0045] See also Figure 1 As shown, a neuromorphic brain-like decision-making system includes an environment perception module, a derivation and decision-making module, and a response execution module;

[0046] The environmental perception module is used to receive commands issued by the user, determine the tasks that the user needs to perform through semantic analysis, and collect environmental data in all directions based on the tasks that need to be performed by the user commands to obtain the characteristic information of objects. The characteristic information includes the shape, color, texture and position coordinates of the objects in space. The collected environmental data is then extracted using image recognition technology to identify different types of objects, such as people and objects.

[0047] The environmental perception module is equipped with a variety of high-precision sensors such as lidar, cameras, and depth cameras; these sensors work together to provide the robot with comprehensive environmental perception capabilities;

[0048] Perform semantic analysis and grammatical decomposition of user commands, converting them into machine-understandable task descriptions. For example, for the command "Move the book from the living room table to the study bookshelf," the system can identify key elements such as "book," "living room table," and "study bookshelf," thereby determining the task the user needs to perform.

[0049] The inference and decision module is used to predefine the symbol domain and logical operator group. The symbol domain is used to represent objects and location information elements in the environment. The logical operator group uses a preset algorithm to comprehensively analyze the relationships between objects in the symbol domain and plan the robot's final walking path to perform the task.

[0050] Specifically:

[0051] Abstract the information elements of each object in the environment into symbols, that is, mark the symbols according to the object type; for example, use specific symbols to represent people (P), furniture (V), obstacles (O), etc.; obtain the coordinates of the position information of each object in the environment through spatial perception algorithms combined with sensor data; the coordinates are (x, y, z);

[0052] Taking the current robot's initial position as the starting point, the task requires the waypoints and the end point to be reached, and determine the coordinates corresponding to the starting point, waypoints, and end point;

[0053] Starting from the robot's starting point, a graph-based search algorithm is used to search for paths and generate executable paths corresponding to each current task;

[0054] It should be noted that, for example, for the task of "moving the book on the table in the living room to the bookshelf in the study", the following paths are generated:

[0055] Path 1: Bypass other furniture in the living room and go directly from the table to the bookshelf in the study. The path is relatively short, but you need to change direction frequently to avoid furniture.

[0056] Path 2: Move along the wall of the living room, avoiding most furniture and human activity areas, but the path is relatively long;

[0057] Path 3: First approach the pedestrians in the living room, then use the relatively open area next to them to reach the bookshelves in the study without disturbing them. This path requires consideration of pedestrian movement and behavior, but has an advantage in overall efficiency.

[0058] Calculate the required walking distance for each executable path corresponding to the current task, and simultaneously obtain the robot's permitted walking speed range set by the user; set by the user, that is, the maximum walking speed range allowed for the robot within the current application area; extract the median value within the permitted walking speed range and calculate it against the required walking distance for each executable path corresponding to the current task, that is, divide each group of required walking distances by the median value to obtain the estimated required walking time for each executable path corresponding to the current task;

[0059] Preset each set of distance value ranges corresponding to the required walking distance, and set each set of distance value ranges to correspond to an estimated energy consumption; match the required walking distance of each executable path corresponding to the current task with each set of preset distance value ranges, thereby determining the estimated energy consumption of each executable path corresponding to the current task;

[0060] Count the number of turns and potential impact adjustments required by the robot when simulating the execution of each executable path corresponding to the current task;

[0061] Extract the symbol of the movable object from the symbol domain, and obtain the specific coordinates corresponding to the movable object symbol, which are recorded as the influence coordinates. Obtain the closest distance between the robot and each set of influence coordinates during the execution of the corresponding path at the current time point, which is recorded as the influence distance.

[0062] Preset reference distances for the impact distances corresponding to different movable objects; for example, if the movable object is a pedestrian, who is more mobile, then the reference distance for the impact distance is set to a higher value. If the impact distance is less than the reference distance, it means that the robot is more likely to need to adjust its steering when executing the corresponding path; compare each group of impact distances in the executable path corresponding to each current task with the corresponding preset reference distance, and count the number of impact distances in the executable path corresponding to each current task that are less than the corresponding preset reference distance as the potential number of impact adjustments for the executable path corresponding to each current task;

[0063] Set the weight coefficients corresponding to the required number of turns and the potential impact adjustment number, respectively, multiply the required number of turns and the potential impact adjustment number of each executable path corresponding to the current task by the corresponding set weight coefficients, and then sum them to obtain the energy consumption added value of the executable path corresponding to each current task;

[0064] The preset energy consumption additional value corresponds to each group of additional value value ranges, and each group of additional value value ranges is set to correspond to an energy consumption additional coefficient; the energy consumption additional coefficient range is set to 1.086-1.138, and the higher the energy consumption additional value, the higher the corresponding energy consumption additional coefficient;

[0065] Match the energy consumption additional value of the executable path corresponding to each current task with the value range of each group of additional values, so as to obtain the energy consumption additional coefficient of the executable path corresponding to each current task;

[0066] Multiply the energy consumption additional coefficient of the executable path corresponding to each current task by the estimated energy consumption to obtain the final energy consumption performance value of the executable path corresponding to each current task;

[0067] It should be noted that by presetting the energy consumption corresponding to the required walking distance and then matching the estimated energy consumption with the actual path distance, the robot can more accurately estimate the energy required to complete the task, which helps to rationally plan energy use and avoid task interruptions due to insufficient energy.

[0068] By counting the number of required turns and the number of potential impact adjustments, the impact of environmental factors (such as movable objects) on the robot during path execution is taken into account, and the complexity of path execution is comprehensively evaluated, providing data that is more in line with actual conditions for energy consumption calculations.

[0069] Extract the final energy consumption performance value and estimated walking time of each executable path corresponding to the current task, and preset the performance value ranges and duration value ranges corresponding to the final energy consumption performance value and the estimated walking time respectively;

[0070] Set the performance value range for each group and the duration value range for each group to correspond to a set of energy consumption scores and efficiency scores respectively; the higher the final energy consumption performance value, the lower the corresponding energy consumption score, and the longer the estimated walking time, the lower the corresponding efficiency score; the energy consumption score and efficiency score range are both set to 1-10;

[0071] Match the final energy consumption performance value and estimated walking time of each executable path corresponding to the current task with the performance value range and the duration value range of each group, respectively, to determine the energy consumption score and efficiency score of each executable path corresponding to the current task;

[0072] Preset sets of weight coefficients corresponding to energy consumption biased habits and efficiency biased habits, respectively. The sets of weight coefficients corresponding to energy consumption biased habits and efficiency biased habits both include weight coefficients corresponding to energy consumption scores and efficiency scores, respectively. The weight coefficient of the energy consumption score in the energy consumption biased habit is greater than the weight coefficient of the efficiency score, and the weight coefficient of the energy consumption score in the efficiency biased habit is less than the weight coefficient of the efficiency score.

[0073] Extract the weight coefficients corresponding to the energy consumption score and efficiency score in the energy consumption bias habit, multiply the energy consumption score and efficiency score of the executable path corresponding to each current task by the corresponding weight coefficient in the energy consumption bias habit, and then sum them to obtain the comprehensive evaluation index of the executable path corresponding to each current task in the energy consumption bias habit;

[0074] Extract the weight coefficients corresponding to the energy consumption score and efficiency score in the efficiency-biased habit, multiply the energy consumption score and efficiency score of the executable path corresponding to each current task by the corresponding weight coefficient in the efficiency-biased habit, and then sum them to obtain the comprehensive evaluation index of the executable path corresponding to each current task in the efficiency-biased habit;

[0075] Taking the current time point as the starting point, extract the bias habits selected by the user within the set time window before the starting point, and count the number of biases corresponding to energy consumption bias habits and efficiency bias habits within the set time window;

[0076] If the number of energy-biased habits is greater than the number of efficiency-biased habits, then the executable path with the highest comprehensive evaluation index among the executable paths corresponding to the current tasks in the energy-biased habit is selected as the final walking path;

[0077] If the number of energy consumption biased habits is less than the number of efficiency biased habits, then the executable path with the highest comprehensive evaluation index among the executable paths corresponding to the current task in the efficiency biased habit is selected as the final walking path;

[0078] It should be noted that by presetting the final energy consumption performance value and the estimated walking time range, and matching the energy consumption score and efficiency score respectively, the path is quantitatively evaluated from the two key dimensions of energy consumption and time consumption, providing comprehensive and intuitive data support for the robot's path selection;

[0079] By setting energy consumption bias and efficiency bias habits and their corresponding weight coefficients, the evaluation focus can be flexibly adjusted according to different user scenarios and demand preferences. For example, in scenarios with limited energy, users may be more inclined to energy consumption, and the energy consumption score will be given a greater weight; while in scenarios with high time requirements, efficiency bias habits are more applicable, highlighting the weight of the efficiency score.

[0080] Starting at the current time, the robot counts the user's preferred paths within a set time window before the starting point and selects the final path based on the number of energy consumption and efficiency preferences. This approach automatically adapts to the user's long-standing preferences, eliminating the need for manual selection each time, and improves the robot's decision-making autonomy and intelligence.

[0081] By comprehensively considering energy consumption and efficiency, and combining user preferences, the path with the highest comprehensive evaluation index is finally selected as the final walking path. This allows the robot to no longer be limited to a single factor when selecting a path, but to find a balance among multiple important factors, ensuring that the selected path meets user preferences while achieving the optimal combination of energy consumption and efficiency as much as possible, thereby improving the overall operating efficiency of the robot and user experience.

[0082] The reaction execution module is used to generate corresponding control instructions based on the final walking path planned by the derivation decision module, and drive the robot to execute the planned final walking path;

[0083] It also includes a somatosensory module, a visual processing module, a semantic logic module, a network and positioning module, and a working memory module;

[0084] The somatosensory module is used to help the robot perceive and adapt to changes in the surrounding environment. Through somatosensory sensors, the robot can sense physical characteristics such as temperature, humidity, and pressure;

[0085] The visual processing module is used to use image recognition technology to enable the robot to identify and analyze objects, spatial layout and their positions in the environment in real time;

[0086] The semantic logic module is used to enable the robot to understand and reason about the user's language instructions and perceive human emotions through semantic understanding and natural language processing (NLP) technology, as well as DQN (Deep Q Network);

[0087] The network and positioning module is used to combine network neural networks and topological maps to locate the robot's position in space;

[0088] The working memory module is used to store and adjust the data generated during the execution process and build a database;

[0089] It should be noted that through the mutual cooperation of the above modules, the following effects are achieved:

[0090] Intelligent decision-making: Able to intelligently plan task paths based on user commands and environmental information, optimize decision-making strategies, and balance energy consumption and efficiency;

[0091] Flexible Adaptability: With strong perception and adaptability, it can adjust task execution strategies in real time according to environmental changes, thus improving the stability of task execution;

[0092] Personalized service: Automatically adjust route planning based on user preferences and habits to provide personalized service experience.

[0093] Multi-dimensional evaluation: Combines multiple factors such as walking time, energy consumption, and path optimization to comprehensively evaluate path selection and ensure efficient completion of tasks;

[0094] The preferred embodiments of the present invention disclosed above are intended only to help illustrate the present invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the present invention to specific embodiments. Obviously, many modifications and variations are possible based on the contents of this specification. These embodiments are selected and described in detail in this specification to better explain the principles and practical applications of the present invention, thereby enabling those skilled in the art to better understand and utilize the present invention. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A neuromorphic brain-like decision-making system, characterized in that: include: Environmental Perception Module: Receives user commands, uses semantic analysis to determine the tasks the user needs to perform, and then comprehensively collects environmental data based on the tasks required by the user commands to obtain feature information of objects. Feature information includes the shape, color, texture, and position coordinates of objects in space. Feature extraction is performed on the collected environmental data to identify different types of objects. Inference and decision-making module: This module predefines a symbolic domain and a logical operator group. The symbolic domain represents objects and location information in the environment, while the logical operator group uses a pre-set algorithm to comprehensively analyze the relationships between objects within the symbolic domain and plan the robot's final path to perform the task. Plan the robot's final walking path to perform the task, specifically: Calculate the required walking distance for each executable path corresponding to the current task, and at the same time obtain the robot's travel speed range set by the user; extract the middle value within the travel speed range and calculate it against the required walking distance for each executable path corresponding to the current task. That is, divide each group of required walking distances by the middle value to obtain the estimated required walking time for each executable path corresponding to the current task; Preset each set of distance value ranges corresponding to the required walking distance, and set each set of distance value ranges to correspond to an estimated energy consumption; match the required walking distance of each executable path corresponding to the current task with each set of preset distance value ranges, thereby determining the estimated energy consumption of each executable path corresponding to the current task; Count the number of turns and potential impact adjustments required by the robot when simulating the execution of each executable path corresponding to the current task; Extract the symbol of the movable object from the symbol domain, and obtain the specific coordinates corresponding to the movable object symbol, which are recorded as the influence coordinates. Obtain the closest distance between the robot and each set of influence coordinates during the execution of the corresponding path at the current time point, which is recorded as the influence distance. Preset reference distances for the impact distances corresponding to different movable objects; compare each group of impact distances in the executable path corresponding to each current task with the corresponding preset reference distances, and count the number of impact distances in the executable path corresponding to each current task that are smaller than the corresponding preset reference distance as the number of potential impact adjustments for the executable path corresponding to each current task; Set the weight coefficients corresponding to the required number of turns and the potential impact adjustment number, respectively, multiply the required number of turns and the potential impact adjustment number of each executable path corresponding to the current task by the corresponding set weight coefficients, and then sum them to obtain the energy consumption added value of the executable path corresponding to each current task; Preset the value ranges of each group of additional values ​​corresponding to the energy consumption additional value, and set each group of additional value ranges to correspond to an energy consumption additional coefficient; Match the energy consumption additional value of the executable path corresponding to each current task with the value range of each group of additional values, so as to obtain the energy consumption additional coefficient of the executable path corresponding to each current task; Multiply the energy consumption additional coefficient of the executable path corresponding to each current task by the estimated energy consumption to obtain the final energy consumption performance value of the executable path corresponding to each current task; Extract the final energy consumption performance value and estimated walking time of each executable path corresponding to the current task, and convert them into energy consumption score and efficiency score based on the set conversion rules; Preset weight coefficient sets corresponding to energy consumption biased habits and efficiency biased habits, respectively. The weight coefficient sets corresponding to energy consumption biased habits and efficiency biased habits both include weight coefficients corresponding to energy consumption scores and efficiency scores, respectively. Extract the weight coefficients corresponding to the energy consumption score and efficiency score in the energy consumption bias habit, multiply the energy consumption score and efficiency score of the executable path corresponding to each current task by the corresponding weight coefficient in the energy consumption bias habit, and then sum them to obtain the comprehensive evaluation index of the executable path corresponding to each current task in the energy consumption bias habit; Extract the weight coefficients corresponding to the energy consumption score and efficiency score in the efficiency-biased habit, multiply the energy consumption score and efficiency score of the executable path corresponding to each current task by the corresponding weight coefficient in the efficiency-biased habit, and then sum them to obtain the comprehensive evaluation index of the executable path corresponding to each current task in the efficiency-biased habit; Taking the current time point as the starting point, extract the bias habits selected by the user within the set time window before the starting point, and count the number of biases corresponding to energy consumption bias habits and efficiency bias habits within the set time window; If the number of energy-biased habits is greater than the number of efficiency-biased habits, then the executable path with the highest comprehensive evaluation index among the executable paths corresponding to the current tasks in the energy-biased habit is selected as the final walking path; If the number of energy consumption biased habits is less than the number of efficiency biased habits, then the executable path with the highest comprehensive evaluation index among the executable paths corresponding to the current task in the efficiency biased habit is selected as the final walking path; Reaction execution module: Generates corresponding control instructions based on the final walking path planned by the deduction and decision module, and drives the robot to execute the planned final walking path.

2. A neuromorphic brain-inspired decision-making system according to claim 1, characterized in that: The logical operator group uses a preset algorithm to conduct a comprehensive analysis of the relationships between objects in the symbol domain, specifically: Abstract the information elements of each object in the environment into symbols, that is, mark the symbols according to the object type; obtain the coordinates of the position information of each object in the environment; Taking the current robot's initial position as the starting point, obtain the waypoints and end point required for the task, and determine the coordinates corresponding to the starting point, waypoints, and end point; Starting from the starting point of the robot, a graph-based search algorithm is used to search for paths and generate executable paths corresponding to each current task.

3. A neuromorphic brain-inspired decision-making system according to claim 2, characterized in that: The scores are converted into energy consumption scores and efficiency scores based on the set conversion rules, specifically: Extract the final energy consumption performance value and estimated walking time of each executable path corresponding to the current task, and preset the performance value ranges and duration value ranges corresponding to the final energy consumption performance value and the estimated walking time respectively; Set the value range of each performance value and the value range of each duration to correspond to a set of energy consumption scores and efficiency scores respectively; The final energy consumption performance value and estimated walking time of the executable path corresponding to each current task are matched with the value range of each group of performance values ​​and the value range of each group of duration, so as to determine the energy consumption score and efficiency score of the executable path corresponding to each current task.

Images