SMART: Scalable Multi-Agent Reasoning and Trajectory Planning in Dense Environments

2025-09-19

AI Summary

In dense traffic scenarios, multi-vehicle trajectory planning suffers from severe non-convexity due to a surge in collision-avoidance constraints. Method: This paper proposes a hierarchical cooperative planning framework: (i) an upper layer employs reinforcement learning for behavior priority inference and large-step search to explore interaction patterns; (ii) a lower layer decomposes the joint optimization via spatial partitioning and navigable corridor construction, enabling parallel convex optimization for trajectory refinement. The framework integrates hybrid A*, V2X-enabled cooperative perception, and distributed optimization for real-time collaborative planning. Contribution/Results: Experiments demonstrate 90% and 95% success rates within 1 second for 25-vehicle (50 m × 50 m) and 50-vehicle (100 m × 100 m) scenarios, respectively; it scales up to 90 vehicles with a minimum planning latency of 0.014 seconds—over 10× faster than pure optimization-based approaches.

Technology Category

• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Multiagent Systems: Multiagent Planning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Multi-vehicle trajectory planning is a non-convex problem that becomes increasingly difficult in dense environments due to the rapid growth of collision constraints. Efficient exploration of feasible behaviors and resolution of tight interactions are essential for real-time, large-scale coordination. This paper introduces SMART, Scalable Multi-Agent Reasoning and Trajectory Planning, a hierarchical framework that combines priority-based search with distributed optimization to achieve efficient and feasible multi-vehicle planning. The upper layer explores diverse interaction modes using reinforcement learning-based priority estimation and large-step hybrid A* search, while the lower layer refines solutions via parallelizable convex optimization. By partitioning space among neighboring vehicles and constructing robust feasible corridors, the method decouples the joint non-convex problem into convex subproblems solved efficiently in parallel. This design alleviates the step-size trade-off while ensuring kinematic feasibility and collision avoidance. Experiments show that SMART consistently outperforms baselines. On 50 m x 50 m maps, it sustains over 90% success within 1 s up to 25 vehicles, while baselines often drop below 50%. On 100 m x 100 m maps, SMART achieves above 95% success up to 50 vehicles and remains feasible up to 90 vehicles, with runtimes more than an order of magnitude faster than optimization-only approaches. Built on vehicle-to-everything communication, SMART incorporates vehicle-infrastructure cooperation through roadside sensing and agent coordination, improving scalability and safety. Real-world experiments further validate this design, achieving planning times as low as 0.014 s while preserving cooperative behaviors.

Problem

• Solving non-convex multi-vehicle trajectory planning in dense environments
• Efficiently resolving tight interactions for real-time large-scale coordination
• Ensuring kinematic feasibility and collision avoidance through hierarchical optimization

Innovation

• Hierarchical framework combining priority search and optimization
• Reinforcement learning for priority estimation and A* search
• Parallel convex optimization with robust feasible corridors