This work presents NeuralParker, a reinforcement learning-based hybrid planner for arbitrary-pose parking that encodes full-environment obstacle and boundary geometry in a target-relative vertex representation, allowing the policy to retain route-defining context throughout the approach.
Abstract
Automated parking commonly assumes marked slots and short approach maneuvers. Delivery and service vehicles, however, may need to reach an operator-specified pose in an irregular bounded environment from a distant start. Existing learning-based parking planners often rely on local observations, which can restrict long-range route reasoning. To address this problem, we present NeuralParker, a reinforcement learning-based hybrid planner for arbitrary-pose parking. NeuralParker encodes full-environment obstacle and boundary geometry in a target-relative vertex representation, allowing the policy to retain route-defining context throughout the approach. It further couples a learned curvature--length arc policy with an in-loop terminal ensemble that selects from diverse cubic Hermite connections using a curvature-regularized cost. We also establish factorial and long-range route-choice benchmarks to evaluate planning success and trajectory quality. Experiments on these benchmarks show that NeuralParker achieves higher planning success and better overall trajectory quality than the evaluated baselines, while ablation studies support the benefits of the target-relative global representation and terminal ensemble. Finally, a real-vehicle evaluation confirms that the planner transfers effectively to real delivery-vehicle perception at a working parking site, planning successfully at low computational cost.
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.
Ze-Wei Yang, Zeng-Qi Peng, Jun Ma· arXiv.org· 0 citations
The field of Automated Valet Parking (AVP) has garnered significant academic interest in recent years. However, traditional parking planning methods often struggle with maneuvering in compact spaces and large-scale environments. While effective for short-distance parking, these methods frequently encounter increased co...
Kai Liu, Jian Zhou, Hao-Ran Li et al.· IEEE transactions on intelli...· 0 citations
Planning Diffusion Policy Optimization is proposed, an offline-to-online reinforcement-learning framework that uses a diffusion policy to generate short-horizon action chunks for crowd navigation and obtains an improved success rate over strong baselines and ablations demonstrate that action chunks are especially impor...
Recent advances in generative planning have made trajectory inpainting a promising approach to offline goal-conditioned reinforcement learning. However, these methods typically specify the planning horizon before generating plan content, even though the appropriate horizon depends on the route itself. A horizon that is...
Automated valet-parking trajectory planning has been widely studied in structured environments, whereas its counterpart in unstructured environments remains insufficiently explored. The working face of an open-pit mine is a typical unstructured production environment, where autonomous mining trucks (AMTs) must perform...
Zi-Jie Meng, Rui-Xin Zhang· Italian National Conference...· 0 citations
A straightforward Deep Reinforcement Learning baseline framework that pairs a Double Deep Q-Network (Double DQN) with a deterministic pathfinding module to provide a simulation-based DRL baseline for future comparative studies in intelligent tourism mobility.
Phan Gia Bao Le, S. Moridpour, M. Dinh· International Conference on...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.