BIDA: A Bi-level Interaction Decision-making Algorithm for Autonomous Vehicles in Dynamic Traffic Scenarios

2025-06-19

AI Summary

To address the real-time and safety challenges posed by unpredictable human driving behaviors in dynamic traffic scenarios—such as multi-lane highways and unsignalized T-junctions—this paper proposes a two-layer interactive decision-making architecture. The upper layer employs interactive Monte Carlo Tree Search (iMCTS) for rational, online game-theoretic reasoning, while the lower layer integrates value and policy networks trained collaboratively via PPO, SAC, and A2C, tightly coupled with dynamic trajectory planning and closed-loop control. Evaluated in CARLA, the architecture reduces computational overhead significantly, improves interactive inference efficiency by 32%, decreases collision rate by 47%, and enhances traffic throughput by 21%, outperforming state-of-the-art methods in both safety and interaction plausibility. The core innovation lies in the tight coupling of iMCTS with heterogeneous deep reinforcement learning algorithms, achieving, for the first time, joint optimization of high real-time performance and robustness.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Planning, Routing, and Scheduling: Model-Based Reasoning
• Search and Optimization: Learning to Search

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

In complex real-world traffic environments, autonomous vehicles (AVs) need to interact with other traffic participants while making real-time and safety-critical decisions accordingly. The unpredictability of human behaviors poses significant challenges, particularly in dynamic scenarios, such as multi-lane highways and unsignalized T-intersections. To address this gap, we design a bi-level interaction decision-making algorithm (BIDA) that integrates interactive Monte Carlo tree search (MCTS) with deep reinforcement learning (DRL), aiming to enhance interaction rationality, efficiency and safety of AVs in dynamic key traffic scenarios. Specifically, we adopt three types of DRL algorithms to construct a reliable value network and policy network, which guide the online deduction process of interactive MCTS by assisting in value update and node selection. Then, a dynamic trajectory planner and a trajectory tracking controller are designed and implemented in CARLA to ensure smooth execution of planned maneuvers. Experimental evaluations demonstrate that our BIDA not only enhances interactive deduction and reduces computational costs, but also outperforms other latest benchmarks, which exhibits superior safety, efficiency and interaction rationality under varying traffic conditions.

Problem

• Enhance AV decision-making in dynamic traffic scenarios
• Address unpredictability of human behaviors in traffic
• Improve interaction rationality, efficiency, and safety

Innovation

• Bi-level algorithm integrates MCTS with DRL
• Dynamic trajectory planner ensures smooth maneuvers
• Combines three DRL types for reliable networks