🤖 AI Summary
Frequent lateral maneuvers (e.g., lane changes, turning) of electric vehicles (EVs) in urban traffic lead to high energy consumption and elevated collision risks.
Method: We propose a data-driven robust optimization framework for real-time EV navigation. It integrates vehicle-body- and inertial-frame dynamics with battery-state evolution into a unified dynamical model; constructs probabilistically guaranteed future occupancy sets from historical obstacle trajectories; and transforms stochastic collision-avoidance constraints into deterministic robust constraints via convex programming duality.
Contribution/Results: This work is the first to unify data-driven occupancy modeling and robust optimization for EV navigation, jointly minimizing energy consumption and collision risk. Simulations demonstrate a 12.7% reduction in energy consumption under curved-road and multi-obstacle scenarios, while achieving 100% safety compliance—i.e., zero constraint violations.
📝 Abstract
In this paper, we simultaneously tackle the problem of energy optimal and safe navigation of electric vehicles in a data-driven robust optimization framework. We consider a dynamic model of the electric vehicle which includes kinematic variables in both inertial and body coordinate systems in order to capture both longitudinal and lateral motion as well as state-of-energy of the battery. We leverage past data of obstacle motion to construct a future occupancy set with probabilistic guarantees, and formulate robust collision avoidance constraints with respect to such an occupancy set using convex programming duality. Consequently, we present the finite horizon optimal control problem subject to robust collision avoidance constraints while penalizing resulting energy consumption. Finally, we show the effectiveness of the proposed approach in reducing energy consumption and ensuring safe navigation via extensive simulations involving curved roads and multiple obstacles.
