Adapting Reinforcement Learning for Path Planning in Constrained Parking Scenarios

2026-01-30

AI Summary

This work proposes the first end-to-end deep reinforcement learning (DRL) path planning approach for automatic parking in perception-constrained, spatially narrow environments, where conventional planners often rely on idealized perception assumptions and incur high computational costs. The method formulates parking as a sequential decision-making problem grounded in bicycle-model dynamics, enabling a closed-loop policy to directly map raw sensory inputs to control actions—eliminating the need for structured perception, online search, or auxiliary localization modules. The authors introduce the first open-source simulation benchmark tailored to challenging, confined parking scenarios and demonstrate that their approach achieves a 96% higher success rate and 52% greater efficiency compared to traditional planners, marking a significant performance improvement.

Technology Category

• Planning, Routing, and Scheduling: Learning for Planning and Scheduling
• Intelligent Robots: Motion and Path Planning
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

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

Abstract

Real-time path planning in constrained environments remains a fundamental challenge for autonomous systems. Traditional classical planners, while effective under perfect perception assumptions, are often sensitive to real-world perception constraints and rely on online search procedures that incur high computational costs. In complex surroundings, this renders real-time deployment prohibitive. To overcome these limitations, we introduce a Deep Reinforcement Learning (DRL) framework for real-time path planning in parking scenarios. In particular, we focus on challenging scenes with tight spaces that require a high number of reversal maneuvers and adjustments. Unlike classical planners, our solution does not require ideal and structured perception, and in principle, could avoid the need for additional modules such as localization and tracking, resulting in a simpler and more practical implementation. Also, at test time, the policy generates actions through a single forward pass at each step, which is lightweight enough for real-time deployment. The task is formulated as a sequential decision-making problem grounded in a bicycle model dynamics, enabling the agent to directly learn navigation policies that respect vehicle kinematics and environmental constraints in the closed-loop setting. A new benchmark is developed to support both training and evaluation, capturing diverse and challenging scenarios. Our approach achieves state-of-the-art success rates and efficiency, surpassing classical planner baselines by +96% in success rate and +52% in efficiency. Furthermore, we release our benchmark as an open-source resource for the community to foster future research in autonomous systems. The benchmark and accompanying tools are available at https://github.com/dqm5rtfg9b-collab/Constrained_Parking_Scenarios.

Problem

• real-time path planning
• constrained parking scenarios
• autonomous systems
• perception constraints
• vehicle kinematics

Innovation

• Deep Reinforcement Learning
• Real-time Path Planning
• Constrained Parking
• Bicycle Model Dynamics
• Autonomous Navigation