Robust Eco-Driving Control of Autonomous Vehicles Connected to Traffic Lights

TL;DR

This paper presents a data-driven, robust eco-driving control method for connected autonomous vehicles at traffic lights, reducing fuel consumption by 40% while handling uncertain signal timings without prior distribution knowledge.

Contribution

It introduces a chance constrained robust optimization framework for eco-driving that accounts for uncertain traffic light timings using empirical data and dynamic programming.

Findings

40% reduction in vehicle fuel consumption

Maintains similar arrival times as baseline models

Enhanced robustness to uncertain traffic signal timings

Abstract

This paper focuses on the speed planning problem for connected and automated vehicles (CAVs) communicating to traffic lights. The uncertainty of traffic signal timing for signalized intersections on the road is considered. The eco-driving problem is formulated as a data-driven chance constrained robust optimization problem. Effective red light duration (ERD) is defined as a random variable, and describes the feasible passing time through the signalized intersections. In practice, the true probability distribution for ERD is usually unknown. Consequently, a data-driven approach is adopted to formulate chance constraints based on empirical sample data. This incorporates robustness into the eco-driving control problem with respect to uncertain signal timing. Dynamic programming (DP) is employed to solve the optimization problem. Simulation results demonstrate that the proposed method can generate optimal speed reference trajectories with 40% less vehicle fuel consumption, while maintaining the arrival time at a similar level when compared to a modified intelligent driver model (IDM). The proposed control approach significantly improves the controller robustness in the face of uncertain signal timing, without requiring to know the distribution of the random variable a priori.