Towards Safe Maneuvering of Double-Ackermann-Steering Robots with a Soft Actor-Critic Framework

2025-10-11

AI Summary

Conventional motion planning methods fail for Dual-Ackermann Steering Mobile Robots (DASMRs) in narrow, cluttered environments due to stringent nonholonomic kinematic constraints. To address this, this paper proposes a deep reinforcement learning framework based on Soft Actor-Critic (SAC), enhanced with Hindsight Experience Replay (HER) and the CrossQ mechanism, significantly improving sample efficiency and obstacle-avoidance robustness. The approach learns safe, precise autonomous parking and dynamic obstacle avoidance policies end-to-end—without requiring hand-crafted trajectories or expert demonstrations. Evaluated on a high-fidelity simulation platform of a heavy-duty four-wheel-steering rover, the method achieves a 97% goal-reaching success rate and reduces path-tracking error by 32% compared to baseline methods. These results demonstrate strong generalization capability under complex nonholonomic constraints and confirm practical engineering applicability.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Planning, Routing, and Scheduling: Learning for Planning and Scheduling
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

We present a deep reinforcement learning framework based on Soft Actor-Critic (SAC) for safe and precise maneuvering of double-Ackermann-steering mobile robots (DASMRs). Unlike holonomic or simpler non-holonomic robots such as differential-drive robots, DASMRs face strong kinematic constraints that make classical planners brittle in cluttered environments. Our framework leverages the Hindsight Experience Replay (HER) and the CrossQ overlay to encourage maneuvering efficiency while avoiding obstacles. Simulation results with a heavy four-wheel-steering rover show that the learned policy can robustly reach up to 97% of target positions while avoiding obstacles. Our framework does not rely on handcrafted trajectories or expert demonstrations.

Problem

• Safe maneuvering of double-Ackermann-steering robots in cluttered environments
• Overcoming strong kinematic constraints with deep reinforcement learning
• Achieving obstacle avoidance and precise positioning without expert demonstrations

Innovation

• Soft Actor-Critic framework for robot maneuvering
• Hindsight Experience Replay for obstacle avoidance
• CrossQ overlay for efficient kinematic control