Autonomous racecar adapts control for overtaking and stability

Driving Context-guided Model Predictive Planning and Control for Autonomous Car Racing at the Limit and Beyond

Robotics

Summary

Driving a racecar autonomously at high speed is very challenging because the car needs to make quick decisions depending on what’s happening on the track. The authors designed a system that can switch between different driving styles, such as normal driving, overtaking other cars, or recovering from slippery turns. Their approach uses a planning and control method that looks ahead and adjusts the car's motions accordingly. They tested their method on a real racecar and got lap times almost as fast as the best human drivers, proving the system can handle tough driving scenarios smoothly.

What this means in practice

Authors

Ayoub Raji, Federico Sacco, Nicola Musiu, Marko Bertogna

Abstract

This paper presents a Model Predictive Control-based motion planning and control pipeline for autonomous car racing capable of adapting to different driving contexts, such as overtaking, nominal driving, and countersteering. A Cost Blending state machine manages the identification of different driving contexts and the selection of their predefined weights to be applied to the Model Predictive Planning (MPP) and Control (MPC) modules. The two optimization-based solutions share the same problem formulation and model, differing only in horizon length, rate, tuning, and in their open-loop versus closed-loop approach to maximize the effectiveness of their interaction. The work is validated on the fully autonomous open-wheel racecar Superformula EAV-25, with a lap time achieved that is within 2% of the best human driver reference. The results demonstrate the capability of the solution in driving at the limit of handling, smoothly executing overtaking maneuvers, and quickly reacting to high oversteering conditions to recover the vehicle stability.