# VEGA: Electric Vehicle Navigation Agent via Physics-Informed Neural Operator and Proximal Policy Optimization

Source: [VEGA: Electric Vehicle Navigation Agent via Physics-Informed Neural Operator and Proximal Policy Optimization](<https://www.sota2.com/research/paper/68fa7b691e209131cea88476>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-10T05:00:05.424Z

Authors: Hansol Lim, Minhyeok Im, Jonathan Boyack, Jee Won Lee, Jongseong Brad Choi

Published: 2025-09-16T11:27:50.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [EV Routing on San Francisco to New York (~4,860 km) (Evaluation Route)](<https://www.sota2.com/research/sota/ev-routing-on-san-francisco-to-new-york-4-860-km-evaluation-route.md>): EV routing; San Francisco to New York (~4,860 km) (Evaluation Route); Distance (km): 4854.96.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2509.13386>)

[PDF](<https://arxiv.org/pdf/2509.13386.pdf>)
