# NeuralParker: A Reinforcement Learning Planner for Irregular Parking Environments

arXiv: https://arxiv.org/abs/2608.24485 · HTML: https://mlsanity.com/paper/2608.24485/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL for autonomous driving and traffic, one of 15 directions in Deep reinforcement learning methods.
- Builds on 19 of its 45 references that are in the map.
- First posted on arXiv 25 Aug 2026.

## Placed in

- Deep reinforcement learning methods / [RL for autonomous driving and traffic](https://mlsanity.com/deeprl/rl-for-autonomous-driving-and-traffic/)

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [VAD: Vectorized Scene Representation for Efficient Autonomous Driving](https://mlsanity.com/paper/2303.12077/) (2023)
- [VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation](https://mlsanity.com/paper/2005.04259/) (2020)
- [A Survey of Motion Planning and Control Techniques for Self-driving Urban Vehicles](https://mlsanity.com/paper/1604.07446/) (2016)
- [Reverse Curriculum Generation for Reinforcement Learning](https://mlsanity.com/paper/1707.05300/) (2017)
- [Integrated Decision and Control: Towards Interpretable and Computationally Efficient Driving Intelligence](https://mlsanity.com/paper/2103.10290/) (2021)
- [BaRC: Backward Reachability Curriculum for Robotic Reinforcement Learning](https://mlsanity.com/paper/1806.06161/) (2018)
- [ParkingE2E: Camera-based End-to-end Parking Network, from Images to Planning](https://mlsanity.com/paper/2408.02061/) (2024)
- [Direct and indirect reinforcement learning](https://mlsanity.com/paper/1912.10600/) (2019)
- [HOPE: A Reinforcement Learning-based Hybrid Policy Path Planner for Diverse Parking Scenarios](https://mlsanity.com/paper/2405.20579/) (2024)
- [RL-OGM-Parking: Lidar OGM-Based Hybrid Reinforcement Learning Planner for Autonomous Parking](https://mlsanity.com/paper/2502.18846/) (2025)
- [TransParking: A Dual-Decoder Transformer Framework with Soft Localization for End-to-End Automatic Parking](https://mlsanity.com/paper/2503.06071/) (2025)
- [MultiPark: Multimodal Parking Transformer with Next-Segment Prediction](https://mlsanity.com/paper/2508.11537/) (2025)
- [ParkFormer: A Transformer-Based Parking Policy with Goal Embedding and Pedestrian-Aware Control](https://mlsanity.com/paper/2506.16856/) (2025)
- [Reachable Set-based Path Planning for Automated Vertical Parking System](https://mlsanity.com/paper/2308.05992/) (2023)
- [A Diffusion-Refined Planner with Reinforcement Learning Priors for Confined-Space Parking](https://mlsanity.com/paper/2510.14000/) (2025)
- [Adapting Reinforcement Learning for Path Planning in Constrained Parking Scenarios](https://mlsanity.com/paper/2601.22545/) (2026)
- [N3P: Accelerated Automated Parking via a Learning-Based Naturalistic Three-Stage Scheme](https://mlsanity.com/paper/2605.22722/) (2026)

## Abstract (arXiv)

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.