Monte-Carlo Tree Search with Neural Network Guidance for Lane-Free Autonomous Driving

2026-01-14

AI Summary

This work addresses the challenges of autonomous driving decision-making in lane-free traffic environments, where increased lateral freedom complicates motion planning. The authors propose a neural network-guided Monte Carlo Tree Search (MCTS) framework, leveraging a pretrained neural network to inform the selection phase of MCTS. By integrating a Markov Decision Process with an isotropic vehicle state representation, this study presents the first application of such a framework to lane-free scenarios. The research identifies and characterizes "crowding behavior" induced by isotropic state symmetry and quantifies the trade-off between computational resources and solution quality. Experimental results demonstrate that the proposed method significantly improves vehicle speed while maintaining a low collision rate, effectively accelerating MCTS convergence and achieving a favorable balance between planning performance and computational efficiency.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Planning, Routing, and Scheduling: Learning for Planning and Scheduling
• Multiagent Systems: Multiagent Planning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Lane-free traffic environments allow vehicles to better harness the lateral capacity of the road without being restricted to lane-keeping, thereby increasing the traffic flow rates. As such, we have a distinct and more challenging setting for autonomous driving. In this work, we consider a Monte-Carlo Tree Search (MCTS) planning approach for single-agent autonomous driving in lane-free traffic, where the associated Markov Decision Process we formulate is influenced from existing approaches tied to reinforcement learning frameworks. In addition, MCTS is equipped with a pre-trained neural network (NN) that guides the selection phase. This procedure incorporates the predictive capabilities of NNs for a more informed tree search process under computational constraints. In our experimental evaluation, we consider metrics that address both safety (through collision rates) and efficacy (through measured speed). Then, we examine: (a) the influence of isotropic state information for vehicles in a lane-free environment, resulting in nudging behaviour--vehicles'policy reacts due to the presence of faster tailing ones, (b) the acceleration of performance for the NN-guided variant of MCTS, and (c) the trade-off between computational resources and solution quality.

Problem

• lane-free driving
• autonomous driving
• Monte-Carlo Tree Search
• neural network guidance
• motion planning

Innovation

• Monte-Carlo Tree Search
• Neural Network Guidance
• Lane-Free Driving
• Autonomous Planning
• Markov Decision Process