Timed Plan Verification for Safe Multi-Robot Coordination
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing multi-robot coordination systems face challenges in ensuring safety and efficiency due to uncertainties in robot action times, leading to unsafe states and deadlocks, especially in collaborative environments with human participants, and current methods either fail to adequately handle uncertainties or incur significant computational overhead.
Innovation Solution
A method and system that transforms timed plans into timed game automata (TIGA) for verification and synthesis, using an adaptive controller to handle uncertainties at runtime, ensuring safety and minimizing makespan by intelligently dispatching actions through a dispatcher module that adds delays or reorders plans as needed.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If plans are designed with large tolerances in dispatch times to ensure safety, then safety is improved, but makespan (time to complete the task) greatly increases
Solution Approach 1:
The system performs preliminary verification of timed plans by transforming them into timed game automata models before execution. This advance analysis identifies potential unsafe states and generates corrective strategies in advance, allowing the system to execute plans with tight tolerances without actually entering unsafe states, thus avoiding the need for large safety margins that would increase makespan.
Solution Approach 2:
The patent introduces an intermediary verification and strategy synthesis component that acts between plan generation and execution. This intermediary transforms timed plans into formal models, verifies safety properties, and generates correction strategies without requiring large time tolerances. The intermediary enables safe execution by providing real-time guidance rather than relying on conservative timing margins.
2Reliability
If detailed uncertainty modeling is performed at plan time to generate optimal plans, then plan optimality is improved, but computation time during plan synthesis greatly increases
Solution Approach 1:
The patent segments the uncertainty handling process into two distinct phases: (1) plan generation with standard timing information, and (2) formal verification with uncertainty modeling. By separating these functions, the system avoids the computational burden of modeling all uncertainties during plan synthesis, while still achieving optimality through the subsequent verification and strategy synthesis phase.
Solution Approach 2:
The system performs preliminary plan generation using efficient algorithms without detailed uncertainty modeling, then applies formal verification as a subsequent step. This preliminary action generates candidate plans quickly, and the detailed uncertainty analysis is applied only to verify and refine these candidates, rather than being part of the initial plan synthesis process.
Data Source
AI summary
According to one or more embodiments, a node for temporal plan verification and timed game automata, TIGA, controller strategy synthesis for coordination of a plurality of agents is provided. The node includes processing circuitry that is configured to determine a first model of a plurality of temporal plans for timed operations of the plurality of agents violates at least one predefined safety rule, generate the TIGA controller strategy for controlling the timed operations of at least a subset of the plurality of agents where the TIGA controller strategy meets the at least one predefined safety rule and being based on the first model, and cause transmission of the TIGA controller strategy to a dispatch device for translating the TIGA controller strategy to instructions for the plurality of agents.