Preprint
Aug 2026
NeuralParker: A Reinforcement Learning Planner for Irregular Parking Environments
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.
Zihan Wang, Baixiang Huang, Yang Guan et al.
· 1 citation