19 results about "Autonomous behavior" patented technology

The invention provides a hierarchical autonomous behavior decision and joint control method for expressway and ramp scenes, and belongs to the technical field of auxiliary driving. Comprising the steps of S1, a training stage; s1.1, collecting expert data and training an IL decision maker; s1.2, an RL control module is trained; s1.3, performing combined overall verification and fine adjustment; s2, an execution stage; s2.1, environment perception and state construction are carried out; s2.2, performing upper layer imitation learning decision making; s2.3, calling a lower layer reinforcement learning control module; s2.4, a lower layer MPC control module is called; and S2.5, vehicle execution and environment updating are carried out. According to the invention, control mode switching is more adaptive and learnable, and dependence on artificial experience is reduced; strategy flexibility and control feasibility or safety are considered; complex tasks such as highway main road lane changing, ramp confluence and ramp diversion can be processed under the same framework; according to the method, smooth and comfortable control behaviors can be generated on the premise of ensuring the safety margin.

This invention discloses a method and system for automatically extrapolating dynamic test schemes based on one-click planning rules. In the test planning and design phase, based on preset one-click planning rules, a dynamic test scheme including test scenarios, test factors, and test samples is automatically generated, and automated rules and equipment action modes are configured for the simulation extrapolation process. In the test execution phase, according to the generated dynamic test scheme, simulation resources are automatically scheduled to execute the simulation extrapolation without human intervention. During the extrapolation process, based on the automated rules and equipment action modes, command issuance, autonomous equipment behavior response, data collection, and result evaluation are automatically completed, forming a fully automated simulation extrapolation closed loop. This invention enables a top-down automated process, forming a complete solution for the entire process of automated simulation extrapolation in the "human-in-the-loop" environment, helping users solve various problems encountered in the construction of current "human-in-the-loop" simulation models.

The invention discloses a meta-universe-based user digital cloned behavior pattern generation method, and relates to the technical field of digital cloned learning, and the method comprises the steps: carrying out the processing of collected user social data, meta-universe behavior data and behavior context, and obtaining user behavior event data; performing multi-channel text feature model processing on the user behavior event data to obtain a text feature vector, performing multi-channel task processing to obtain a text classification probability, and constructing a mixed kernel embedded learning model to obtain a text classification result; and mapping the text classification probability and the behavior context to obtain user behavior mapping data, and finally analyzing the user behavior mapping data and the current meta-universe environment to obtain user behavior parameters, so that personalized autonomous behaviors are kept when the user is offline, and deep behavior preferences and decision logic of the user are effectively analyzed in real time.

Provided is an edge-based intelligence support method for performing a complex task of an autonomous behavior robot. Provided is a method for performing a task of an autonomous behavior robot, according to an embodiment of the present invention, in which the autonomous behavior robot performs the task by using an ultra-lightweighted artificial intelligence model, an edge server supports the task performance of the autonomous behavior robot by using a lightweighted artificial intelligence model, and a cloud server supports the task performance of the robot by using a huge artificial intelligence model. Accordingly, in addition to distributing and updating, through edge computing, an artificial intelligence model required when the autonomous behavior robot performs various tasks, the task performance itself is supported through an edge or cloud, thereby increasing the task performance efficiency of the autonomous behavior robot to improve service quality.

The invention discloses a brain-level cross-modal perception autonomous behavior generation method and system for a body-equipped agent, and relates to the technical field of body-equipped agents, and the method comprises the following steps: constructing a dynamic weight distribution chain based on the time continuity of a multi-modal input signal of the body-equipped agent, detecting the time difference of arrival of the language signal and the visual signal and generating a weight adjustment instruction; performing delay compensation on the language signal to form a balanced input frame; setting a semantic suppression window to detect the weight change rate in real time, and triggering reduction suppression when the weight change rate exceeds a threshold; generating a perception enhancement band amplification visual feature according to a suppression result; and establishing a time sequence balance list according to the perception enhancement band output, recording weight change and adaptively correcting weight distribution. According to the method, time sequence synchronization and fusion balance of the language signal and the visual signal are achieved through a dynamic weight distribution and semantic suppression mechanism, long-term weight balance is maintained through self-adaptive correction of a perception enhancement and time sequence balance list, and the fusion precision and behavior stability of the intelligent agent with the body are improved.

This invention provides a robot charging optimization control method and system, relating to the field of robot control technology. The method includes: planning a charging path for the robot to a charging station with the goal of simultaneously satisfying multiple optimization conditions; and controlling the robot to perform a charging operation based on the charging path. The multiple optimization conditions include: the robot's first remaining battery power upon arrival at the charging station is lower than a preset battery power threshold; the time the robot spends charging at the charging station has less impact on its remaining tasks than a preset impact threshold; and when the robot passes any potential non-autonomous behavior execution point, its second remaining battery power is sufficient to support the execution of the corresponding non-autonomous behavior. By comprehensively considering battery management, task execution efficiency, and non-autonomous behavior response requirements, an optimal charging path is planned and the charging operation is controlled, achieving an optimal balance between battery replenishment and task execution.

The invention provides a role control method and device in a game, equipment and a storage medium, and the role control method can support a player to freely and flexibly control the generation opportunity of an NPC role in the game in a mode of controlling a controlled virtual role to execute a specified role behavior in the game; and after the NPC role is generated, according to the distance parameter between the NPC role and the controlled virtual role, the moving mode of the NPC role in the game is enriched, so that the interaction form between the NPC role and the player role in the game is effectively enriched, meanwhile, the autonomous behavior ability of the NPC role in the game is improved, and the game experience is improved. And the man-machine interaction efficiency of players can be improved.

The application discloses an AI dynamic risk grading and layered authorization method and device based on a hardware trust root, which is executed by an independent hardware risk control unit. The unit forcibly takes the AI entity global root identity verified by hardware signature as the unique index of risk control, analyzes multi-dimensional indexes of AI behavior in real time, dynamically quantifies risk scores, automatically executes three-layered authorization from single full-automatic execution to hardware independent channel human confirmation, to full-core physical fuse, and continuously monitors in the process of atomic operation execution. In addition, the application also protects the forward-looking risk prediction based on behavior trend, the whole network dynamic joint defense capability of cross-node real-time sharing of risk information, and the evolution mechanism of identifying new abnormal behavior patterns and incorporating them into the risk assessment system after human confirmation, providing AI autonomous behavior with identity anchoring, dynamic precision, and hardware-level security boundary that cannot be bypassed.

The invention particularly relates to a method for optimizing an intelligent network with a body in a multi-dimensional state space. According to the method, a multi-dimensional state space S and a hierarchical action space A are constructed, a model based on deep reinforcement learning is used as a core scheduler, and autonomous learning and collaborative decision making of the method are realized; building a multi-dimensional space, building a hierarchical action space and a reinforcement learning collaborative optimization model are seamlessly integrated into a control system of the intelligent agent, and autonomous behavior decision-making of network awareness is achieved; the active optimization framework efficiently interacts with a robot operating system (ROS) service of the robot body, and converts an abstract optimization strategy into specific physical and communication instructions. According to the multi-dimensional state space-based intelligent network optimization method, the transformation of the intelligent agent from the traditional passive adaptation network to the active optimization network connection is realized, and the end-to-end task performance and the connection stability are remarkably improved.

The invention provides an expressway multi-expert autonomous behavior decision-making method based on scene perception constraint, and belongs to the technical field of automatic driving. Comprising the steps that a one-way three-lane linear expressway environment is built; describing vehicle kinematics by using a bicycle model; the method comprises the following steps: modeling longitudinal car-following behaviors of surrounding vehicles by adopting an IDM model to form a traffic flow with certain randomness and uncertainty; dividing the driving scene into a plurality of sub-scenes; constructing a unified state space and action space state space; the scene constraint cost with the unified form is designed for all the sub-scenes; introducing scene perception constraint, improving a DRL algorithm used by each sub-scene, and training a corresponding expert model based on a scene perception constraint SAC algorithm; constructing a training set and a test set; and carrying out an actual operation or simulation test stage.

The invention discloses a robot voice interaction and autonomous behavior decision-making method and system based on multi-modal perception, and belongs to the field of autonomous control and intelligent interaction of service robots. The problems that an existing service robot technology cannot meet the natural language interaction requirement in a complex scene, and precise understanding and autonomous decision making of task intentions cannot be achieved are solved. The invention provides a natural language analysis mechanism based on weighted confidence fusion, which performs confidence evaluation and weighted fusion on multi-modal information such as speech recognition, semantic analysis, visual perception, positioning perception and the like to realize intelligent disassembly of composite statements, multi-round instructions and parameter-containing instructions. Accurate understanding and autonomous decision making of task intentions are achieved, and therefore the robot is accurately driven to act. The method is mainly applied to the service robot.

The utility model relates to the field of animal behavioral experiment equipment, in particular to an autonomous jumping training device for a mouse behavioral experiment. Comprising a conveying belt, a plurality of height-adjustable one-way opening units are arranged on the outer side of the conveying belt in the conveying direction of the conveying belt, the two ends of the conveying belt in the conveying direction are located in two shells respectively, a reward device and a punishment device are installed in the two shells respectively, and the one-way opening units can only be opened towards the punishment device. According to the utility model, by arranging the reward water nozzle and the punishment electrode, an autonomous behavior driving mechanism is constructed, and the mice need to actively jump obstacles to avoid punishment or obtain awards, so that the device is more in line with naturalness and scientificity of behavioral research.

The invention relates to the technical field of itinerary planning, and discloses an itinerary planning system based on a large model, and the system comprises a non-autonomous behavior recognition and preference purification module which outputs a purified behavior sequence reflecting the real preference of a user; the dynamic user state characterization module is used for mapping high-dimensional heterogeneous user features to a low-dimensional continuous potential space; the enhanced user portrait construction module is used for integrating regional culture priori knowledge and external ecological behavior signals; the system further comprises a travel generation and multi-constraint feasibility verification module based on a large model and a travel scheme interactive optimization and user feedback closed loop module. According to the scheme, the authenticity and feasibility of itinerary planning are improved, the accuracy of user portraits is enhanced by purifying non-autonomous behavior data, the recommendation adaptability is improved by fusing regional culture and external interest signals, dynamic budget and real-time resource verification are combined to guarantee that the scheme is executable, user interaction optimization and feedback closed loop are supported, and the user experience is improved. And personalized, practical and participatable intelligent travel service is realized.

The invention provides an agent autonomous decision interaction method based on a dynamic personality and bionic memory system, and relates to the technical field of artificial intelligence and cognitive computing. Comprising the following steps: initializing multi-dimensional personality parameters of an intelligent agent, constructing a personality map, establishing a structured memory library containing scene, semantic and emotional memory, and adding a timestamp, an emotional weight and a label to the memory; environment input is received in real time, intention recognition and emotion evaluation are performed in combination with personality states and associated memories to generate a candidate behavior set, target behaviors are selected from the candidate set through a decision-making mechanism for comprehensively evaluating expected emotion benefits, personality consistency and task utility, and an interaction instruction is generated. And finally, according to behavior feedback, dynamically adjusting personality parameters and emotional states, and carrying out enhanced storage and selective forgetting on the memory bank. According to the method, personality consistency maintenance, memory-driven autonomous behavior decision and long-term personality evolution of the intelligent agent in interaction are realized, and the emotional credibility and active adaptability of personification interaction are improved.

The present application relates to pig breeding technology field, disclose a kind of breeding boar breeding device and its using method, comprising: positioning bearing module, comprising: trapezoidal fixed seat, the walking ramp for guiding breeding boar into operating position is arranged in its both sides;Side wing limiting mechanism is composed of first side wing limiting frame and second side wing limiting frame, and both are moved symmetrically on the trapezoidal fixed seat by linear adjustment assembly, to adapt to the breeding boar of different body width, device integrates environmental perception, dynamic adaptation and accurate execution function, completely replace artificial intervention and animal autonomous behavior dependence, by intelligent visual identification and multi-axis collaborative control, automatically complete breeding boar body posture fixation, reproductive organ positioning and semen collection / insemination operation, single operation time is shortened to 1 / 4 (≤5 minutes) of traditional method, and continuous unmanned operation is supported.

The application discloses a user digital avatar behavior mode generation method based on a meta universe, relates to the technical field of digital avatar learning, processes collected user social data, meta universe behavior data and behavior context to obtain user behavior event data; the user behavior event data is processed by a multi-channel text feature model to obtain a text feature vector, a text classification probability is obtained through multi-channel task processing, a mixed kernel embedding learning model is constructed, the text classification probability and the behavior context are mapped to obtain user behavior mapping data, and finally, the user behavior mapping data and the current meta universe environment are analyzed to obtain user behavior parameters, so that personalized autonomous behavior can be maintained when the user is offline, and deep behavior preferences and decision logic of the user can be effectively and timely analyzed.

This invention provides a multi-expert autonomous behavior decision-making method for highways based on scene-aware constraints, belonging to the field of autonomous driving technology. It includes: constructing a one-way three-lane straight highway environment; using a bicycle model to describe vehicle kinematics; employing an IDM model to model the longitudinal following behavior of surrounding vehicles, forming a traffic flow with a certain degree of randomness and uncertainty; dividing the driving scenario into multiple sub-scenarios; constructing a unified state space and action space; designing a unified scene constraint cost for each sub-scenarios; introducing scene-aware constraints, improving the DRL algorithm used for each sub-scenarios, and training a corresponding expert model based on the scene-aware constraint SAC algorithm; constructing training and testing sets; and conducting actual operation or simulation testing.

The application provides a layered autonomous behavior decision and joint control method for highway and ramp scenes, and belongs to the technical field of auxiliary driving. The method comprises the following steps: S1, a training stage; S1.1, collecting expert data and training an IL decision maker; S1.2, training an RL control module; S1.3, joint overall verification and fine tuning; S2, an execution stage; S2.1, environment perception and state construction; S2.2, upper layer imitation learning decision; S2.3, calling a lower layer reinforcement learning control module; S2.4, calling a lower layer MPC control module; S2.5, vehicle execution and environment update. The application makes the control mode switching more adaptive and learnable, reduces the dependence on artificial experience, considers the strategy flexibility and the control feasibility or safety, can process complex tasks such as highway main road lane changing, ramp merging and ramp diverging in the same framework, and can generate smooth and comfortable control behavior under the premise of ensuring safety margin.

A computer-implemented method for preventing loss of function in a local instance when there is a disturbance of a connection to a backend in a communication system that has a local instance having a local agent and a backend acting in part as a global agent, an agent designating a unit that is designed to achieve defined goals through autonomous behavior. The method includes, when there is a connection to the backend, the providing of the function by the global agent, which receives backend information from the backend during the providing of the function, and, if a connection to the backend is disturbed, the providing of the function by the local agent.