NeuralParker：面向不规则停车环境的强化学习规划器

中文摘要 AI 辅助

自动泊车通常假设存在标记车位和短距离接近操作，但配送车与服务车辆可能需要从较远的起点在不规则有界环境中到达操作者指定的位姿。现有基于学习的泊车规划器常依赖局部观测，这会限制长距离路径推理。为解决该问题，我们提出NeuralParker，一种面向任意位姿泊车的基于强化学习的混合规划器。NeuralParker以目标相对顶点表示编码全环境障碍物与边界几何，使策略在接近过程中保留路径定义上下文；它进一步将学习到的曲率-长度弧策略与循环内终端集成器耦合，该集成器通过曲率正则化代价从多种三次厄米特连接中选择。我们还建立了阶乘与长距离路径选择基准，以评估规划成功率与轨迹质量。在这些基准上的实验表明，NeuralParker相较于评估的基线方法实现了更高的规划成功率与更优的整体轨迹质量； ablation研究验证了目标相对全局表示与终端集成器的益处。最后，实车评估证实该规划器可有效迁移至实际配送车感知系统，在工作停车场以低计算成本成功规划。

英文摘要

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.

发表机构

• Tsinghua University（清华大学）
• Central University of Finance and Economics（中央财经大学）
• Meituan（美团）

机构由 AI 辅助整理，请以论文原文为准。