24 results about "Linear temporal logic" patented technology

The invention provides a safety key scene enhancement generation method fusing traffic rule hard constraints and a dynamic feasible region, and relates to the technical field of automatic driving safety tests.The method comprises the steps that a multi-strategy initial data set is constructed, pre-training an optimal feasible value network of the automatic driving vehicle through offline reinforcement learning by utilizing the multi-strategy initial data set, and generating a dynamic feasible region; a traffic rule is represented in a formalized mode through linear sequential logic, and a rule hard constraint and feasibility guide dual-action mask mechanism is constructed; and controlling the confrontation background vehicle to generate a compliance confrontation scene by maximizing a rule-feasible region dual-guided confrontation objective function, feeding back the generated effective key scene to an initial data set, and realizing data-driven feasible region dynamic updating. According to the method, by combining rule formalization constraint and feasible region reachability analysis, the scene is ensured to be compliant and close to a system capability boundary.

The invention belongs to a specification mining technology of software engineering, and relates to a construction method of an approximate specification mining model and a software behavior verification system. The construction method comprises the following steps: generating a group of linear temporal logic LTL formulas for describing positive example time sequence attributes according to a positive example set; using an LTL formula to generate a potential negative example for evaluation and training; designing and constructing a neural network for analyzing the finite state automaton from the parameter assignment so as to simulate an acceptance behavior of the finite state automaton; and iteratively searching the neural network through a gradient descent algorithm until the maximum number of iterations is reached, and mining to obtain the finite state automaton. The neural network can simulate acceptance of the finite state automaton in the reasoning process, the finite state automaton can be explained at low cost, and the problem of search space explosion is solved.

The invention discloses a path task planning method for a magnetic micro robot in a complex environment, and relates to the technical field of micro-nano control, and the method comprises the steps: carrying out the formalized coding of a multi-target task demand through employing linear sequential logic LTL; a decision module based on a DQN neural network is constructed, a real-time environment state and an action execution result are combined and input to a multi-level reward function coded by LTL to generate a reward and punishment signal, and the reward and punishment signal is fed back to the network to guide a path optimization decision; in the network optimization process, a logic correction state transition model is introduced to increase the probability of compliance action in a weighted manner, so that the state transition process of the magnetic micro robot is shifted towards the direction meeting LTL constraint. According to the method, task logic features are extracted through bidirectional GRU, and the task logic features are embedded into the neural network as priori knowledge of decision making, so that the problem of low efficiency of processing time sequence tasks through traditional DQN is solved, and the interpretability and safety of decision making are improved through explicit logic constraints.

The invention discloses a self-adaptive adjustment method and system for the unstacking height of a stamping robot, and relates to the technical field of intelligent manufacturing, and the method comprises the steps: obtaining multi-modal data, extracting a root cause node of the multi-modal data through a recursive backtracking causal chain, and generating an anti-interference rule library based on the interference condition characteristics of the root cause node and a compensation strategy mapping relation; generating a decision vector through a causal entropy balance target of a neural symbol inference engine; mapping the decision vector into a discrete event model, and verifying the time sequence security through a linear temporal logic protocol; monitoring an actual causal entropy value generated by the decision vector, comparing the actual causal entropy value with a causal entropy balance target, and when the actual causal entropy value deviates from a tolerance value of the causal entropy balance target, marking the actual causal entropy value as a high-risk signal; and triggering root cause backtracking analysis based on the high-risk signal, and if a backtracking result is confirmed as a rule defect, updating a related rule set in the rule base.

The invention discloses a water conservancy flood prevention decision-oriented key element identification and causal modeling method and system, relates to the technical field of water conservancy flood prevention scheduling decisions, and aims to solve the problems of difficult element identification and complex causal relationship in current flood prevention decisions. Comprising the following steps: constructing a flood prevention three-dimensional element system of basic elements-target elements-control elements; performing structured processing on the three-dimensional element data to generate a decision modeling data set in a unified format; identifying credible key elements through a three-stage algorithm of relevance preliminary screening, causal modeling and expert verification; constructing an IMaGES-DBN fusion causal model, and depicting the dynamic change of the causal relationship in flood evolution; introducing bounded linear sequential logic to optimize key element weights; and verifying and iteratively optimizing the model by adopting a statistical model. According to the invention, flood risk rapid identification and early warning are realized, flood prevention command automation, intelligence and high reliability are improved, and the method is suitable for scenes such as drainage basin flood control scheduling and hydraulic engineering safe operation.

This invention belongs to the interdisciplinary field of digital twins and artificial intelligence, specifically disclosing an automatic generation method for manufacturing equipment control logic based on neural-symbolic collaboration and intermediate representation verification. This method utilizes a neural-symbolic collaboration strategy, employing four-element semantic model constraints and thought chain reasoning to transform unstructured natural language process instructions into structured hierarchical state machine (HSM) intermediate representations. Through linear temporal logic (LTL) formal verification and graph theory connectivity analysis, static security verification of the control logic is performed, effectively improving the system's temporal determinism and deadlock resistance. Based on this, the system performs dynamic physical simulation in a digital twin environment, extracting spatial coordinate deviations when mechanical interference occurs, and inversely mapping these deviations into structured error correction prompts, which are then fed back to the large language model for logic reconstruction. This invention constructs a cross-modal "generation-verification-correction" closed-loop mechanism, achieving deep integration of model cognitive intent and underlying physical space constraints, ultimately deterministically compiling the verified intermediate representation into highly reliable industrial standard control code.

The application discloses a symbolic controller design method based on chino polyhedron under linear temporal logic specification, belongs to the technical field of nonlinear system control, and solves the linear temporal logic (LTL) task controller synthesis problem of a nonlinear control system. First, an accepted path is generated for a preset LTL task. Second, a chino polyhedron and a constrained chino polyhedron are used to divide a state space, the divided regions are defined as 'units', adjacent units are allowed to intersect, a unit topology graph is constructed based on the unit intersection relationship, and the realizability of the LTL accepted path is verified. Finally, if the accepted path is realizable, the global LTL task is decomposed into a plurality of local subtasks, a local symbolic model is constructed for each unit, a local symbolic controller is iteratively designed through a 'local to global' control strategy, and combination is completed, so that a symbolic controller satisfying the global LTL specification is obtained. The application supports different units to adopt a differentiated local equivalence relationship, reduces the conservativeness of a single equivalence relationship, reduces the calculation complexity of global approximation, and improves the efficiency and practicability of controller synthesis.

The application is suitable for the field of artificial intelligence and formal verification technology, and provides a conversion system and method from natural language to linear temporal logic based on self-learning, which comprises a text conversion module, an equivalence checking module, a rule induction module and a rule library management module; the text conversion module is used for generating a predicted formula according to a basic rule and a retrieval rule; the equivalence checking module is used for verifying the equivalence of the predicted formula and a target formula and extracting a failure sample; the rule induction module is used for analyzing the failure sample and automatically inducing a new conversion rule; and the rule library management module is used for storing the rules and retrieving based on semantic similarity. The system can automatically learn from conversion errors and continuously optimize the rule library. The application overcomes the dependence on artificial rules or labeled data in the prior art, realizes unsupervised adaptive learning, and significantly improves the accuracy and field adaptability of the conversion from natural language to linear temporal logic.

The application discloses a kind of human-computer collaborative game simulation decision-making methods based on linear temporal logic, comprising: using linear temporal logic expression to describe the task between man and machine, and the expression is converted into automaton;Formalized comprehensive modeling is carried out to unmanned aerial vehicle, and initial global path planning of unmanned aerial vehicle system is carried out using planning automaton;Unmanned aerial vehicle runs according to the initial global path planned, when being disturbed by enemy, dynamic situation is handled using man-machine enemy game algorithm.This method describes the task using linear temporal logic, can describe more complex timing task, effective interaction between man and machine;Linear temporal logic constructs controller by the way of synthesis automaton, does not need human intervention, and is guaranteed by mathematics to construct and correct, so that the system is more reliable;Zero-sum game of man-machine-enemy, consider multi-role arena game model, and construct game tree to obtain dynamic optimal strategy under alternation simulation.

The application discloses a kind of micro-grid cluster cooperative control safety decoupling method and system.The system includes energy management layer, communication layer and distributed power DG individual layer connected in turn, and energy management system of energy management layer is used to give scheduling task instruction, and communication layer is used to transmit scheduling task instruction to DG individual layer, and DG individual layer includes distributed power individual, heterogeneous state safety constraint coupling model set, small gain theory safety gain decomposer, linear temporal logic scheduling module and secondary controller set, and DG individual layer is used to carry out information cooperative processing according to scheduling task instruction, by heterogeneous state safety constraint coupling model set, small gain theory safety gain decomposer, linear temporal logic scheduling module and secondary controller set, and based on secondary controller set, safety decoupling is carried out, high inertia, high damping and strong voltage support are provided, and system strength and stability margin are improved.

The application discloses a kind of robot hierarchical learning method based on linear temporal logic and parallel waypoint planning, including mapping expert demonstration trajectory into action primitive sequence by inverse dynamics model, automatically dividing subtask boundary and determining waypoint quantity benchmark, while converting primitive sequence into linear temporal logic formula and giving text logical constraint;The text semantic features of logical formula are extracted in advance using pre-training encoder;Based on the current observation state, use parallel neural network architecture to synchronously predict multiple target waypoints in the whole process, eliminate time sequence dependence and solve strategy error accumulation;Based on the current state, text semantic features and target waypoints, output hybrid action instruction to drive robot to execute tasks.The application realizes the automatic decomposition from demonstration to structured task, guides policy learning through formal logical constraint, and significantly improves the robustness and sample efficiency of long-time sequence operation through parallel waypoint planning, suitable for application in object stacking, precision assembly and other tasks.

The application provides a vehicle safety control method and device, electronic equipment and a readable storage medium, wherein the method comprises: acquiring perception data of a vehicle laser radar, and generating a safety event according to the perception data; when multiple safety events are triggered concurrently, arbitrating the priority of each safety event and the occupation relationship of each safety event to an actuator resource, and selecting a control instruction matched with the arbitration result from candidate control instructions as an executable control instruction sequence; the candidate control instruction is a linear temporal logic formula converted based on a vehicle safety specification and a formal model constructed in advance, and a control instruction satisfying the linear temporal logic formula is verified in advance; and the executable control instruction sequence is issued to an actuator for execution. In this way, by combining formal verification with an event triggering mechanism and using a priority arbitration mechanism to solve instruction conflicts, the accuracy of vehicle safety control is improved.

This invention relates to the field of robot motion planning and formalization technology, and discloses a method and system for reactive motion planning of robots. The method includes: establishing a set of atomic propositions and a shared-safe linear temporal logic task reduction based on the task to be performed by the robot; converting the task reduction into a deterministic finite automaton, constructing a convex region in the robot configuration space, and establishing a convex set state transition system; constructing a convex set graph by multiplying the convex set state transition system with the deterministic finite automaton, and solving for the initial trajectory; performing structured relaxation on the deterministic finite automaton; and reconstructing the convex set graph based on the relaxed deterministic finite automaton, starting from the current robot configuration, and solving for the replanned trajectory. This invention achieves safe, verifiable, and highly robust execution of long-term sequential tasks of robots in dynamic environments by unifying task semantic hierarchy, automaton logic relaxation, and continuous trajectory optimization of the convex set graph.

The application discloses an industrial robot path planning and execution method based on hierarchical Monte Carlo tree search. By converting the global complex linear temporal logic task into a finite state automaton, the task is simplified and clearly represented, making it easier for the industrial robot to understand and execute. On this basis, a cross product model of finite state automaton and multi-agent Markov decision process is further constructed to more effectively handle the coordination problem between multiple industrial robots. Further, in order to compress the history state space, a hierarchical Monte Carlo tree search (MCTS) algorithm containing task selection and task allocation is proposed, which contains two levels of task selection and task allocation, can significantly reduce the algorithm complexity and improve the search efficiency. In summary, the application provides an efficient, accurate and flexible online path planning and execution solution for industrial robots, especially suitable for various long-range tasks with temporal logic characteristics.

A rail transit interlocking system completeness test case generation method and system, comprising: applying the STPA method to analyze the safety requirements of the rail transit interlocking system, and converting the safety requirements into linear temporal logic properties; modeling the rail transit interlocking system using a symbolic finite state machine to obtain a reference model, calculating all evaluation functions in the rail transit interlocking system, and generating symbolic traces in the reference model according to the evaluation functions; improving the reference model, and combining the linear temporal logic properties to divide the input and output events of the reference model into equivalent classes; generating test cases based on the symbolic traces of the improved reference model, executing the test cases on the system under test, and detecting whether the system under test meets the safety requirements of the rail transit interlocking system. The present application can effectively reduce the number of test cases generated by reasonably dividing the equivalent classes, thereby reducing the test time and improving the test efficiency.

The invention discloses a double-layer control method and system in a dynamic environment based on reinforcement learning, a double-layer reinforcement learning architecture is designed for the path planning problem of multi-task operation in a man-machine coexistence environment, and the method comprises the following steps: S1, according to the multi-task operation to be executed by a robot, determining the path of the multi-task operation to be executed by the robot; multi-task atomic proposition is carried out by using security cooperation linear sequential logic, and a corresponding finite state automaton is constructed; s2, according to the observation state of the manually-driven vehicle in the environment, by constructing a dynamic factor discrete motion model, environment uncertainty measurement is completed; s3, performing risk measurement according to the environmental uncertainty measurement; s4, performing path planning based on a double-layer reinforcement learning algorithm; and S5, if the robot encounters operation interruption in the operation process, returning to the step S4, and carrying out risk calculation and path planning again. According to the method, effective combination of local and global optimal paths can be realized, and finally the global optimal multi-task operation path is generated.

The present invention relates to the field of intelligent manufacturing technology, and discloses an intelligent control method and system for a stamping robot. Among them, an intelligent control method for a stamping robot includes: constructing a knowledge graph containing the multi-dimensional relationship of material process equipment quality; transforming process knowledge into formal logical rules and fusing with a deep neural network to construct a neuro-symbolic reasoning model; modeling the stamping process as a discrete event system and using linear temporal logic specification to verify the correctness of process control rules; using a satisfiability modulo theory solver to detect and resolve parameter constraint conflicts in process control rules; generating and executing an adaptive stamping control strategy based on the verified rule base and production process feedback; The present invention combines symbolic reasoning and deep learning, has technical characteristics such as strong interpretability, high safety, and strong adaptability, and can effectively improve the quality consistency and production efficiency of stamping production.

The invention discloses a formalized verification method and system for a LiteOS-M kernel from a source code to an architecture layer, computer equipment and a medium, and the method comprises the steps: defining a basic model of the LiteOS-M kernel, defining corresponding variables and channels based on the basic model according to a verification demand of a to-be-verified attribute, and establishing a corresponding APA verification model, the attributes to be verified comprise concurrency and scheduling attributes, security and isolation attributes and performance attributes; performing mathematical description on the to-be-verified attribute to form a property protocol, and converting the property protocol into a linear sequential logic formula through deductive reasoning; and performing formalized verification on the to-be-verified attribute based on the linear sequential logic formula. According to the method, the system to be verified can be effectively split and combined according to the relation from top to bottom, the corresponding abstract function model is constructed, and the consistency from the LiteOS-M kernel source code to the security function is verified.

Embodiments of the present disclosure relate to a mobile device, an apparatus, a data carrier, a computer program, and a method for planning a trajectory for a mobile device. The method comprises obtaining a natural language instruction indicating a path for the mobile device, assigning semantic role labels to phrases of the natural language instruction, and obtaining a linear temporal logic (LTL) based on the natural language instruction and the semantic role labels using a large language model.

The application provides a substation relay protection device adaptive control method and system, the method comprises the following steps: constructing a mapping relationship between linear temporal logic sequences and relay protection events; detecting state change events, power grid operation events and manual operation events of each relay protection device in the substation, and assigning each event a globally unique event identifier and a timestamp to construct an unforgeable chain event log in the order of event occurrence, the chain event log stores original data and context information of all events; taking the chain event log as input, verifying through linear temporal logic sequences to correspondingly identify a target event sequence that violates the temporal constraint; analyzing the target event sequence to detect the corresponding target control action, and correspondingly generating a control path and a control object that adapt to the target control action. The application can greatly improve the control efficiency of the relay protection device.

This invention relates to the field of robot motion planning technology, specifically a mobile robot motion planning algorithm based on linear temporal logic, comprising: S1, constructing a grid map and performing dilation processing on the grid map; constructing a robot temporal task and converting it into an automaton; S2, incrementally constructing a prefix sampling tree; S3, obtaining candidate prefix paths; S4, incrementally constructing a suffix sampling tree based on the candidate prefix paths; S5, obtaining the prefix path and suffix path with minimum cost, and constructing a safety corridor based on the obtained paths; S6, constructing an optimization problem based on the safety corridor to solve for the robot's motion trajectory. The trajectory planning algorithm proposed in this invention utilizes a differential flat model of the mobile robot, which can constrain the trajectory based on the kinematics and dynamics of the mobile robot in a lower dimension, resulting in a higher quality generated trajectory.

The invention discloses a DeFi lending protocol formalized modeling and verification method based on a color Petri network, and the method comprises the steps: analyzing a DeFi lending protocol source code through an abstract syntax tree technology, and extracting and recognizing a core function set in a protocol and a constraint rule thereof; based on the extracted core function set and the constraint rule thereof, constructing a lending protocol parameter model, and forming a complete parameter library, a calculation formula and a cross-mechanism parameter synchronization rule; constructing a CPN model according to a lending protocol parameter model by using a color Petri net theory, and designing a state synchronization library and a global shared variable in the model to realize parameter transmission and state updating logic among mechanisms of the protocol; and converting the constructed CPN model, the state synchronization library and the global shared variable into a formalized verification model, defining multi-dimensional attributes based on linear sequential logic, performing automatic verification on the formalized verification model by using a model detection tool, identifying potential vulnerabilities and generating a verification report. According to the invention, comprehensive detection of the security and correctness of the DeFi lending protocol is realized.

The application discloses a mechanical arm task and motion planning method and system based on linear temporal logic, first, a mechanical arm task and motion planning model is built, task information of the mechanical arm, position information of the mechanical arm and a working environment thereof are acquired, and the position information is input into an upper task planning module in the model, after processing and optimization, a feasible network topology graph is obtained, a planning algorithm is used to search on the feasible network topology graph, and a task sequence is obtained; a coordination module in the model receives the task sequence and segments, extracts a motion sequence of the mechanical arm, and makes a planning suggestion; a lower motion planning module in the model receives the planning suggestion, uses a planning algorithm to plan the motion of the mechanical arm, and obtains a motion trajectory of the mechanical arm, and the motion trajectory of the mechanical arm meeting the requirements is output through the coordination module. The method simplifies the interaction mode between man and machine, can prevent steps that cannot be implemented in task planning, and improves the success rate of planning.

The application relates to the technical field of power networks, and provides a security perception method based on a power network and capable of being used for hiding a vulnerability attack path, which comprises the following steps: 1) modeling a Markov decision process (MDP) with security constraints; 2) modeling linear time logic (LTL) specifications; 3) modeling an attacker attack model and initial state opacity; 4) modeling a reinforcement learning problem under security constraints; 5) constructing an initial state estimator (ISE) of the MDP and building a task model; and 6) solving by using Q learning to obtain an optimal strategy, namely completing security perception. The security perception method can comprehensively consider the security requirement of power network routing, system behavior specifications, initial state opacity and potential intruder attacks, so that an effective reinforcement learning scheme is provided to optimize a routing strategy and guarantee the security of the power network when messages are sent.