17 results about "Behavior Trees" patented technology

The application discloses a kind of based on behavior tree and VLA's dual-arm robot task assembly method, specifically includes: when task starts, behavior tree is executed from root node, signal is sent to child node by fixed frequency;Proposition received by parsing perception module is extracted target object and its spatial relationship by conditional node, and three-dimensional information and attribute are obtained using visual recognition algorithm, to judge whether meet the requirement;Action node generates initial path according to motion planning module, trajectory optimization is carried out according to the dynamics constraint of manipulator, and deviation and disturbance in motion process are monitored in real time, timely adjustment is ensured to complete task, wherein user instruction and scene image information are integrated, joint angle and end effector instruction are generated by means of pre-trained multi-modal VLA model, guide dual-arm efficient cooperation, until successfully complete assembly operation.

This invention relates to the field of quadruped robot navigation technology and discloses an intelligent navigation system for quadruped robots that combines behavior tree and visual recognition. The system includes modules for path processing, turn prediction, behavior tree decision-making, obstruction judgment, visual recognition and language evaluation, and navigation decision-making. The path processing module integrates multi-sensor data to acquire pose and gait state; the turn prediction module calculates safe turning speed and trigger distance based on a gait phase sliding window; the behavior tree decision-making module dynamically adjusts node priorities according to trigger intensity, and the switching timing is controlled by a gait phase arbiter; the obstruction judgment module generates path obstruction flags; the visual recognition module adopts a two-level architecture, calling a visual language model to evaluate the landing area for static traversable obstacles; and the navigation decision-making module integrates landing semantic confidence and outputs commands to cross, detour, wait, or return. This invention enables quadruped robots to achieve proactive predictive navigation and intelligent obstacle avoidance decision-making in complex industrial environments.

The application discloses an intelligent cockpit task control method based on a behavior tree arrangement and multi-source arbitration, and the method comprises the following steps: a task compiler performs behavior tree conversion according to a task configuration file, and completes behavior tree building; a shadow verification module performs simulation verification on the behavior tree, and the behavior tree that passes the verification enters a gray-to-normal process; a trigger arbitrator acquires N trigger signals in a vehicle, when K trigger signals in the N trigger signals all satisfy a trigger condition, the trigger arbitrator generates a trigger proof with a time stamp and an event abstract; a behavior tree engine locks the context of this execution according to the trigger proof, activates action nodes corresponding to the trigger signals, and then injects trigger parameters at the trigger time in each action node to generate CAN signal instructions; and an execution scheduler controls corresponding vehicle-mounted physical hardware to run according to the CAN signal instructions. Effects: the method can solve trigger jitter through multi-source arbitration, solve execution safety through behavior tree injection, and solve online risk through a shadow mode.

The application discloses a simulation deduction data determination method and related products. In the scheme, based on the context prompt information, a plurality of strategy descriptions are determined; based on each strategy description, a corresponding behavior tree file is constructed; a plurality of behavior tree files corresponding to the plurality of strategy descriptions are simulated and deduced, and initial deduction trajectory data is obtained; the initial deduction trajectory data is quantified by using multi-dimensional data quality indicators, and a quantification result is obtained; if the quantification result meets a preset iteration end condition, the initial deduction trajectory data is screened according to a preset data screening condition, and target deduction data is obtained; if the quantification result does not meet the preset iteration end condition, new context prompt information is determined based on the quantification result, and the step of determining a plurality of strategy descriptions based on the context prompt information is returned until the preset iteration end condition is met. Compared with the prior art, the production efficiency and quality of the simulation deduction data can be considered, and the application has obvious advantages.

The present application relates to the technical field of water pollution tracing, and particularly relates to a method and system for tracing water pollution by an unmanned ship, which comprises the following steps: constructing an improved dynamic behavior tree decision model after starting a tracing task, which comprises three parallel behavior sub-trees of tracing, obstacle avoidance and returning; collecting the concentrations of pollutants, the distances of obstacles and the remaining power of the unmanned ship in real time in four directions of front, back, left and right; calculating the behavior weights and normalizing them in each sampling period; judging based on behavior switching logic, which introduces hysteresis constraint and time constraint, and requires that the normalized weight of the behavior to be switched is higher than the sum of the current behavior weight and a threshold increment, and the duration of this state exceeds the anti-shake time, and if the conditions are met, the behavior with the highest weight is switched to; finally, the corresponding algorithm is called to execute the action; the system comprises the modules of main control, concentration detection, obstacle avoidance, positioning, driving, power, wireless communication and host computer control, which is beneficial to solve the problems of inflexible task switching and easy decision shock caused by instantaneous interference or close weights of the traditional behavior tree in complex water areas, and improves the autonomy, task execution efficiency and overall system stability of the unmanned ship tracing.

This application discloses a method, apparatus, device, and storage medium for processing object behavior data, belonging to the field of Internet technology. The method includes: after the background program corresponding to the target application starts, deserializing the behavior tree file corresponding to the background program to obtain memory structure data of the behavior tree, wherein the memory structure data includes node data of multiple nodes, and the node data includes behavior conditions or execution data; loading the memory structure data of the behavior tree into system shared memory; allocating processing memory for the behavior tree in the system shared memory based on the memory structure data; when object behavior data is received, retrieving target execution data corresponding to the behavior conditions matching the object behavior data from the memory structure data based on the processing memory, and executing the target execution data. Using this application, the behavior tree can continue to be executed after the game process restarts based on the processing data stored in the system shared memory, which can reduce the resource consumption on the server.

This application discloses a robot behavior adaptive control system and method, relating to the field of robot behavior control technology. The system includes a behavior library module configured to store multiple pre-built, reusable robot behavior components; a behavior tree engine module configured to connect to the behavior library module for logical orchestration and scheduling calculations of the behavior components; and an artificial intelligence optimization module configured to connect to both the behavior tree engine module and the behavior library module for dynamically optimizing the execution parameters of the behavior components and / or the behavior tree structure of the behavior tree engine module based on real-time sensor data and historical behavior data. This robot behavior adaptive control system and method, by introducing an artificial intelligence optimization module to dynamically optimize pre-built behavior components and behavior tree structures, enhances the robot's mobility in unstructured environments and improves task execution success rate and system robustness.

Method for automatically generating a behavior tree program for controlling a machine. A computer-implemented method for automatically generating a behavior tree program for controlling a machine (24), the method comprising the steps of: - transmitting a sequence of machine commands inputted by a user from a user interface (21) to a controller (23), - receiving supervisory data from the controller (23) in the user interface (21) when the machine commands are executed in the controller (23) controlling the machine (24), - observing and replicating the machine commands and supervisory data transmitted between the controller (23) and the user interface (21), - storing the machine commands and supervisory data in a logging unit (26), - generating a derived behavior tree program from the stored machine commands and supervisory data by statistical inference, and - sending the generated behavior tree program to the controller unit (23) to control the machine.

The application discloses a system for controlling robot task decision based on a semantic network and a knowledge base, comprising a semantic network module for providing a semantic network for constructing a task decision behavior tree, the semantic network being supplemented and expanded through the question and answer results of a large language model and a knowledge base; a large language model module for outputting question and answer results through knowledge question and answer using the large language model; a knowledge base module for providing knowledge for constructing the task decision behavior tree; a task decision module for constructing the task decision behavior tree according to the semantic network module, the large language model module and the knowledge base module, specifically constructing nodes of a decision tree by querying the semantic network, filling node parameters through the question and answer results of the large language model, and filling node parameters through the knowledge base; and a variable storage module for storing temporary variables during the construction of the task decision behavior tree. In this way, the decision behavior tree is more accurate.

The application relates to the technical field of aircraft autonomous decision-making, in particular to an aircraft autonomous decision-making method based on a hybrid architecture of a finite state machine and a behavior tree, which comprises the following steps: acquiring multi-source perception data of an aircraft, and writing the multi-source perception data into a shared data center; monitoring a macro state set in the shared data center by using a finite state machine, determining a current macro state according to the macro state set, and indexing and loading a corresponding behavior tree model from a preset behavior tree library by using the macro state set; taking a current control period as a time step, starting from a root node to traverse and execute the behavior tree model, outputting a leaf node action instruction corresponding to an autonomous decision-making action based on the behavior tree model, and controlling the aircraft to execute the autonomous decision-making action based on the leaf node action instruction. Therefore, the problems of state explosion of a finite state machine and insufficient macro control of a pure behavior tree in the related art are solved.

This application discloses a method and system for collaborative scheduling of unmanned equipment clusters based on behavior trees, relating to the field of equipment scheduling technology. The method includes: collecting equipment categories and basic state parameters of unmanned equipment; randomly selecting one unmanned equipment as the first unmanned equipment and obtaining an initial behavior tree; updating the weights of the root node based on the equipment category and task status of the first unmanned equipment; updating the initial behavior tree of the first unmanned equipment when the task completion degree is greater than a preset completion threshold; obtaining similar unmanned equipment when the task completion degree is less than or equal to the preset completion threshold; selecting collaborative unmanned equipment, updating the parallel node weights of the first unmanned equipment and the collaborative unmanned equipment, and performing collaborative scheduling of the unmanned equipment cluster. This solves the technical problems of insufficient flexibility, low collaborative efficiency, and poor environmental adaptability in existing unmanned equipment scheduling methods, leading to resource conflicts or unreasonable task allocation.

This application discloses a method, apparatus, and electronic device for automatically generating behavior trees based on a large language model, relating to the fields of artificial intelligence and automation control technology. The method includes: acquiring task description information, constructing node variable context objects, injecting structured prompts, and forming a resource-constraint-aware generation context; retrieving high-quality cases that meet a quality threshold based on the semantic vector of the task description, filtering dynamically few-sample examples using a selection algorithm and embedding generation prompts; calling a locally deployed large language model to generate a behavior tree, performing grammar checks and logic defect detection on the generated results through evaluation operators, converting failed detection results into structured feedback information, and driving the model to perform minimization iterative refinement until the checks are passed or the maximum number of iterations is reached. This solves the problems of low usability, poor stability, and high deployment cost of behavior tree generation using large language models, enabling a lightweight large language model to achieve approximately 90% generation success rate on consumer-grade hardware.

The application provides a task implementation structure intelligent design method and device based on an ontology knowledge graph, a medium and a product, relates to the field of intelligent software engineering, and comprises the following steps: extracting a keyword list corresponding to a robot task requirement; inputting the keyword list into an ontology knowledge graph, and outputting actions corresponding to the robot task and an action execution sequence; the ontology knowledge graph is constructed based on a robot ontology knowledge base; constructing a plurality of basic logics for implementing the robot task according to the actions and the action execution sequence; each basic logic corresponds to a group of triple knowledge; generating a behavior tree according to the plurality of triple knowledge; designing a task implementation structure based on the ontology knowledge graph according to the behavior tree; and the task implementation structure based on the ontology knowledge graph is used for executing the robot task. The application improves the intelligent degree and the universality of the designed software architecture.