Monte Carlo Tree Search with Velocity Obstacles for safe and efficient motion planning in dynamic environments

2025-01-16

AI Summary

To address the challenge of online motion planning for robots in dense, dynamic pedestrian environments, this paper proposes a safe, efficient, and real-time planning method that relies solely on the current positions and maximum velocities of obstacles—without requiring full trajectory predictions or explicit dynamical models. Our approach innovatively integrates Monte Carlo Tree Search (MCTS) with the Velocity Obstacle (VO) method: VO constraints guide the MCTS search to ensure safety, optimality, and robustness. We further enhance computational efficiency through physics-based simulation, online model predictive rollout, and action pruning. In high-density simulated scenarios with 40 randomly moving obstacles, our method reduces collision rate by 42% and accelerates planning speed by 3.1× compared to baseline approaches, significantly outperforming state-of-the-art methods such as nonlinear model predictive control (NMPC).

Technology Category

• Intelligent Robots: Motion and Path Planning
• Planning, Routing, and Scheduling: Mixed Discrete/Continuous Planning
• Multiagent Systems: Multiagent Planning

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

Online motion planning is a challenging problem for intelligent robots moving in dense environments with dynamic obstacles, e.g., crowds. In this work, we propose a novel approach for optimal and safe online motion planning with minimal information about dynamic obstacles. Specifically, our approach requires only the current position of the obstacles and their maximum speed, but it does not need any information about their exact trajectories or dynamic model. The proposed methodology combines Monte Carlo Tree Search (MCTS), for online optimal planning via model simulations, with Velocity Obstacles (VO), for obstacle avoidance. We perform experiments in a cluttered simulated environment with walls, and up to 40 dynamic obstacles moving with random velocities and directions. With an ablation study, we show the key contribution of VO in scaling up the efficiency of MCTS, selecting the safest and most rewarding actions in the tree of simulations. Moreover, we show the superiority of our methodology with respect to state-of-the-art planners, including Non-linear Model Predictive Control (NMPC), in terms of improved collision rate, computational and task performance.

Problem

• Online Motion Planning
• Complex Environments
• Safe and Efficient Path Selection

Innovation

• Monte Carlo Tree Search (MCTS)
• Velocity Obstacles (VO)
• Online Motion Planning