VEGA为电动车提供自适应能耗导航，结合物理模型与强化学习，规划更省电的路线。
VEGA: Electric Vehicle Navigation Agent via Physics-Informed Neural Operator and Proximal Policy Optimization
- 用神经算子从短时车速加速度数据估计车辆物理参数
- 在美全国高速网训练后，跨州行程仅需20次充电，最低电量11.41%
- 推理速度快于基线20倍，且可直接用于法日道路网络
我们提出VEGA，一种面向电动汽车的自适应能耗导航系统，融合物理信息参数估计与基于强化学习的充能路径规划。该系统包含两个耦合模块：(1) 物理信息神经算子（PINO），从车载短时速度与加速度数据中估计车辆特定物理参数——阻力、滚动阻力、质量、电机及再生制动效率、辅助负载；(2) 近端策略优化（PPO）智能体，在标注充电桩的路网图上联合选择路径与充电点，满足续航状态约束。智能体通过行为克隆初始化，使用课程引导的PPO在全美高速公路网（含特斯拉超充站）上微调。在旧金山至纽约（约4,860公里）跨州路线中，生成可行的20次充电方案，总耗时56.12小时，最低剩余电量11.41%。相比受控的能耗感知A*基线，里程和驾驶时间差异极小（-8.49公里，+0.37小时），且推理速度提升超过20倍。所学策略无需重新训练即可泛化至法国与日本道路网络。
原文摘要 · Abstract (English)
We present VEGA, a vehicle-adaptive energy-aware routing system for electric vehicles (EVs) that integrates physics-informed parameter estimation with RL-based charge-aware path planning. VEGA consists of two copupled modules: (1) a physics-informed neural operator (PINO) that estimates vehicle-specific physical parameters-drag, rolling resistance, mass, motor and regenerative-braking efficiencies, and auxiliary load-from short windows of onboard speed and acceleration data; (2) a Proximal Policy Optimization (PPO) agent that navigates a charger-annotated road graph, jointly selecting routes and charging stops under state-of-charge constraints. The agent is initialized via behavior cloning from an A* teacher and fine-tuned with cirriculum-guided PPO on the full U.S. highway network with Tesla Supercharger locations. On a cross-country San Francisco-to-New York route (~4,860km), VEGA produces a feasible 20-stop plan with 56.12h total trip time and minimum SoC 11.41%. Against the controlled Energy-aware A* baseline, the distance and driving-time gaps are small (-8.49km and +0.37h), while inference is >20x faster. The learned policy generalizes without retraining to road networks in France and Japan.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。