Skip to content

Learning Reliable Parking Policies via Offline Reinforcement Learning with Quantized Action Representations

Sep 2026 · arXiv.org · Vol abs/2609.19894 · 0 citations · 30 references
Computer Science

TL;DR

This work develops a waypoint-level offline reinforcement learning framework for interaction-aware autonomous parking, which attains the highest parking success rate among all baselines and transfers reliably to unseen parking slots.

Abstract

Parking is a routine yet safety-critical task for autonomous vehicles operating in urban environments. However, cluttered and weakly structured parking spaces, compounded by the interactive uncertainty from surrounding vehicles, hinder reliable maneuver generation. To address these challenges, we develop a waypoint-level offline reinforcement learning framework for interaction-aware autonomous parking. Specifically, a dedicated parking dataset is constructed from hierarchical expert rollouts with rotational waypoint augmentation, covering both non-interactive scenarios and interactive ones. The policy is then conditioned on a compact state representation, in which LiDAR-based obstacle features are adapted to the target pose via feature-wise linear modulation. A state-conditioned tokenizer further quantizes continuous waypoint sequences into discrete action tokens, over which conservative Q-learning is performed to suppress value overestimation on poorly supported actions. Extensive closed-loop experiments are conducted in the high-fidelity CARLA simulator. The proposed framework attains the highest parking success rate among all baselines and transfers reliably to unseen parking slots.

View source

Similar papers

#artificial intelligence Preprint Oct 2026

Beyond Policy Support: Interaction Constrained Offline Reinforcement Learning for Autonomous Driving

Offline reinforcement learning enables reward-driven policy improvement from fixed datasets without requiring online exploration, making it particularly attractive in safety-critical domains. A central challenge, however, is distribution shift: policy optimization may favor actions that are weakly supported by the offl...

Mahmoud Selim, Cristina Cipriani, K. H. Johansson · 0 citations
Sep 2026

Reinforcement Learning-Based Adaptive Path Planning for Autonomous Vehicles in Unpredictable Urban Environments

Autonomous vehicles (AVs) are transforming transportation by enabling intelligent, self-governing mobility. A crucial challenge in AV deployment is real-time path planning under dynamic and unpredictable road conditions. Traditional algorithms such as A* and Dijkstra, while effective in static environments, lack the fl...

K. Priya · 0 citations
#artificial intelligence Preprint Sep 2026

From Semantic Decisions to Feasible Trajectories: Self-Evolving LLM-Guided Optimal Control for Narrow-Space Parking

Autonomous parking in nonconvex and narrow environments remains challenging. Although optimal-control methods can explicitly enforce vehicle dynamics and collision constraints, nonconvexity compromises solver robustness and can cause failures. Large language models (LLMs) exhibit strong semantic reasoning capabilities,...

Zheng-Bao Yao, Yuan-Fu Luo, Ke-Han Xue · 0 citations
Conference Open access Oct 2026

A Mixture of Domain Experts Framework for Autonomous Navigation via Deep Reinforcement Learning

Long-horizon evaluations across in-distribution and held-out CARLA towns show that the proposed architecture outperforms monolithic and end-to-end MoE baselines, especially under multi-scenario and out-of-distribution conditions.

V. Neves, Ana Huamán Reyna, I. P. Gomes et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Imitation Learning for Autonomous Driving in CARLA

This work studies how much closed-loop driving competence a compact multimodal policy can acquire from offline demonstrations in the CARLA simulator, and reports offline metrics and distinguish measured results from qualitative closed-loop observations.

Jordy Kieto · 1 citation
Open access Sep 2026

Learning Scheduling Method for Mixed Traffic at Autonomous Intersections Without Reliable Explicit Turn Information of Human-Driven Vehicles

At autonomous intersections in mixed traffic, where Connected and Autonomous Vehicles (CAVs) coexist with Human-Driven Vehicles (HDVs), scheduling must remain effective even when a reliable explicit HDV turning intention is not available sufficiently early for the scheduling decision. This paper proposes a learning-bas...

Xu-Hao Yue, Feng Peng, Ze-Jian Deng et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.