Learning to Drift in Extreme Turning with Active Exploration and Gaussian Process Based MPC

2024-10-08

AI Summary

To address model mismatch and conventional controller failure under extreme cornering with large side-slip angles in autonomous drifting, this paper proposes a model predictive control (MPC) framework integrating Gaussian process regression (GPR)-based model correction and uncertainty-driven active exploration. Innovatively, the predictive uncertainty of the GPR model is leveraged online to guide optimal drift-velocity exploration, while dynamic model correction is concurrently performed during both drift-equilibrium solving and MPC receding-horizon optimization. Validation via Simulink–CarSim co-simulation and 1:10-scale RC vehicle experiments demonstrates significant improvements: lateral tracking error is reduced by 52.8% (attributable to GPR correction) and 27.1% (due to active exploration); velocity root-mean-square error decreases by 10.6% (simulation) and 7.2% (real vehicle). The method substantially enhances trajectory and velocity tracking accuracy, as well as adaptability, under sustained drifting conditions.

Technology Category

• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Intelligent Robots: State Estimation
• Computer Vision: Motion & Tracking

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Extreme cornering in racing often leads to large sideslip angles, presenting a significant challenge for vehicle control. Conventional vehicle controllers struggle to manage this scenario, necessitating the use of a drifting controller. However, the large sideslip angle in drift conditions introduces model mismatch, which in turn affects control precision. To address this issue, we propose a model correction drift controller that integrates Model Predictive Control (MPC) with Gaussian Process Regression (GPR). GPR is employed to correct vehicle model mismatches during both drift equilibrium solving and the MPC optimization process. Additionally, the variance from GPR is utilized to actively explore different cornering drifting velocities, aiming to minimize trajectory tracking errors. The proposed algorithm is validated through simulations on the Simulink-Carsim platform and experiments with a 1:10 scale RC vehicle. In the simulation, the average lateral error with GPR is reduced by 52.8% compared to the non-GPR case. Incorporating exploration further decreases this error by 27.1%. The velocity tracking Root Mean Square Error (RMSE) also decreases by 10.6% with exploration. In the RC car experiment, the average lateral error with GPR is 36.7% lower, and exploration further leads to a 29.0% reduction. Moreover, the velocity tracking RMSE decreases by 7.2% with the inclusion of exploration.

Problem

• Managing large sideslip angles in extreme racing turns
• Correcting vehicle model mismatch during drifting control
• Minimizing trajectory tracking errors via active velocity exploration

Innovation

• Gaussian Process Regression corrects model mismatches
• Active exploration minimizes trajectory tracking errors
• MPC and GPR integration enhances drift control precision