Qingpei Li | Search arXiv

arXiv2026

Benchmarking Autonomous Driving Planners Across Leaderboards: A Unified CARLA-Based Evaluation

Autonomous driving remains a highly active research domain that seeks to enable vehicles to perceive dynamic environments, predict the future trajectories of traffic agents such as vehicles, pedestrians, and cyclists and plan safe and efficient future motions. To advance the field, several competitive platforms and benchmarks have been established to provide standardized datasets and evaluation protocols. Each offers a unique dataset and challenging planning problems spanning a wide range of driving scenarios and conditions. In this study, we present a comparative case study of representative motion planning methods drawn from major benchmark ecosystems, including CARLA, nuPlan, and the Waymo Open Dataset. To ensure a fair and unified evaluation, we adopt CARLA Leaderboard v2.1 as our common evaluation platform and evaluate eight representative methods: TF++, InterFuser, TCP, PDM-Lite, MTR+MPC, CaRL, PlanT 2.0, Diffusion planner. By highlighting the strengths and weaknesses of current approaches, we identify prevailing trends, common challenges, and potential directions for advancing motion-planning research.

cs.RO↗

arXiv2025

Multi-Agent Path Finding via Offline RL and LLM Collaboration

Multi-Agent Path Finding (MAPF) poses a significant and challenging problem critical for applications in robotics and logistics, particularly due to its combinatorial complexity and the partial observability inherent in realistic environments. Decentralized reinforcement learning methods commonly encounter two substantial difficulties: first, they often yield self-centered behaviors among agents, resulting in frequent collisions, and second, their reliance on complex communication modules leads to prolonged training times, sometimes spanning weeks. To address these challenges, we propose an efficient decentralized planning framework based on the Decision Transformer (DT), uniquely leveraging offline reinforcement learning to substantially reduce training durations from weeks to mere hours. Crucially, our approach effectively handles long-horizon credit assignment and significantly improves performance in scenarios with sparse and delayed rewards. Furthermore, to overcome adaptability limitations inherent in standard RL methods under dynamic environmental changes, we integrate a large language model (GPT-4o) to dynamically guide agent policies. Extensive experiments in both static and dynamically changing environments demonstrate that our DT-based approach, augmented briefly by GPT-4o, significantly enhances adaptability and performance.

cs.MA↗