Multi-Robot Trajectory Planning via Constrained Bayesian Optimization and Local Cost Map Learning with STL-Based Conflict Resolution

2026-03-06

AI Summary

This work addresses the challenges of trajectory planning for multi-robot systems under signal temporal logic (STL) specifications and dynamic constraints, which often suffer from poor scalability, limited adaptability, and low sampling efficiency. The authors propose a two-stage planning framework: at the single-robot level, a constrained Bayesian optimization tree search (cBOT) learns local cost maps and feasibility constraints; at the multi-robot level, an STL-monitored enhanced kinodynamic conflict-based search (STL-KCBS) embeds STL semantics into conflict detection and resolution mechanisms. By integrating Bayesian optimization with formal STL reasoning, the approach ensures probabilistic completeness while significantly improving trajectory efficiency, safety, and compliance with STL specifications. Extensive simulations and real-world experiments with autonomous surface vessels demonstrate the method’s robustness and practicality in uncertain environments.

Technology Category

• Multiagent Systems: Multiagent Planning
• Intelligent Robots: Motion and Path Planning
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

We address multi-robot motion planning under Signal Temporal Logic (STL) specifications with kinodynamic constraints. Exact approaches face scalability bottlenecks and limited adaptability, while conventional sampling-based methods require excessive samples to construct optimal trajectories. We propose a two-stage framework integrating sampling-based online learning with formal STL reasoning. At the single-robot level, our constrained Bayesian Optimization-based Tree search (cBOT) planner uses a Gaussian process as a surrogate model to learn local cost maps and feasibility constraints, generating shorter collision-free trajectories with fewer samples. At the multi-robot level, our STL-enhanced Kinodynamic Conflict-Based Search (STL-KCBS) algorithm incorporates STL monitoring into conflict detection and resolution, ensuring specification satisfaction while maintaining scalability and probabilistic completeness. Benchmarking demonstrates improved trajectory efficiency and safety over existing methods. Real-world experiments with autonomous surface vehicles validate robustness and practical applicability in uncertain environments. The STLcBOT Planner will be released as an open-source package, and videos of real-world and simulated experiments are available at https://stlbot.github.io/.

Problem

• multi-robot trajectory planning
• Signal Temporal Logic
• kinodynamic constraints
• scalability
• collision avoidance

Innovation

• Constrained Bayesian Optimization
• Signal Temporal Logic (STL)
• Multi-Robot Trajectory Planning
• Local Cost Map Learning
• Conflict-Based Search