Towards Safe Maneuvering of Double-Ackermann-Steering Robots with a Soft Actor-Critic Framework
This addresses the challenge of robust navigation for complex non-holonomic robots in cluttered environments, representing an incremental improvement over existing methods.
The paper tackled the problem of safe and precise maneuvering for double-Ackermann-steering robots, which face strong kinematic constraints, by developing a deep reinforcement learning framework based on Soft Actor-Critic, achieving up to 97% success in reaching target positions while avoiding obstacles in simulations.
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.