RL-OGM-Parking: Lidar OGM-Based Hybrid Reinforcement Learning Planner for Autonomous Parking

TL;DR

This paper introduces a hybrid reinforcement learning and rule-based planning system for autonomous parking that uses LiDAR-based occupancy grid maps to bridge the sim-to-real gap, demonstrating superior performance in both simulation and real-world tests.

Contribution

The paper presents a novel hybrid RL and rule-based parking planner utilizing LiDAR OGM to enable seamless real-world deployment and improved robustness over existing methods.

Findings

Outperforms pure rule-based and learning-based methods in experiments.

Effective in both simulation and real-world scenarios.

LiDAR OGM bridges the sim-to-real gap successfully.

Abstract

Autonomous parking has become a critical application in automatic driving research and development. Parking operations often suffer from limited space and complex environments, requiring accurate perception and precise maneuvering. Traditional rule-based parking algorithms struggle to adapt to diverse and unpredictable conditions, while learning-based algorithms lack consistent and stable performance in various scenarios. Therefore, a hybrid approach is necessary that combines the stability of rule-based methods and the generalizability of learning-based methods. Recently, reinforcement learning (RL) based policy has shown robust capability in planning tasks. However, the simulation-to-reality (sim-to-real) transfer gap seriously blocks the real-world deployment. To address these problems, we employ a hybrid policy, consisting of a rule-based Reeds-Shepp (RS) planner and a learning-based reinforcement learning (RL) planner. A real-time LiDAR-based Occupancy Grid Map (OGM) representation is adopted to bridge the sim-to-real gap, leading the hybrid policy can be applied to real-world systems seamlessly. We conducted extensive experiments both in the simulation environment and real-world scenarios, and the result demonstrates that the proposed method outperforms pure rule-based and learning-based methods. The real-world experiment further validates the feasibility and efficiency of the proposed method.