Robust Auto-parking: Reinforcement Learning based Real-time Planning Approach with Domain Template

This paper presents an automatic parking for a passenger vehicle, with highlights on a robust real-time planning approach and on experimental results. We propose a framework that leverages the strength of learning-based approaches for robustness to environments noise and capability of dealing with challenging tasks, and rule-based approaches for its versatility of handling normal tasks, by integrating simple rules with RL under a multi-stage architecture, which is inspired by the auto-parking typical template. By taking temporal information into consideration with using Long Short Term Memory (LSTM) network, our approach could facilitate to learn a robust and humanoid parking strategy efficiently. We present preliminary results in a high-fidelity simulator to show our approach can outperform a basic geometric planning baseline in the robustness to environment noise and efficiency of planning.