Robust vision-only control improves lane keeping on sharp curves
Robust Offset-Free Lane-Keeping Control Framework for Vision-Only Automated Vehicles
RoboticsComputer Vision and Pattern Recognition
Summary
Keeping a car safely within its lane, especially when driving fast around sharp turns, is a hard problem for self-driving cars that use only cameras. The authors designed a new method that helps a car follow lanes more accurately and stay stable, even when the road bends sharply. They tested different algorithms and found one that controls the vehicle quickly and reliably. The method also measures how uncertain the car’s camera system is about what it sees on roads it has not encountered before. This work could help make vision-based self-driving cars safer on complicated roads.
What this means in practice
- •For autonomous vehicle engineers: Implement faster and more stable lane-keeping control using cameras only, especially for high-speed driving on sharp turns.
- •For automotive safety teams: Assess and enhance the robustness of visual perception systems under unfamiliar traffic scenes for safer vehicle operation.
Authors
Der-Hau Lee
Abstract
Achieving accurate, real-time lane-keeping control during high-speed cornering on large-curvature roads while ensuring robust vehicle stability is a critical challenge in autonomous driving. To address this challenge, this study developed a robust offset-free model predictive control (OF-MPC) framework for vision-based autonomous vehicle lane-keeping. The regulation problem in this framework is solved using several algorithms. Numerical simulation results indicated that the interpolation-tube-based constrained iterative linear quadratic regulator (itube-CILQR) algorithm outperformed solvers based on the standard Interior Point Optimizer (IPOPT) and Operator Splitting Quadratic Program (OSQP), achieving a mean computation time of less than 5 ms. The itube-CILQR algorithm was then used for vehicle control in vision-based lane-keeping experiments in a simulation environment to quantify the perceptual uncertainty of a visual perception model (multitask UNet). This quantification was performed using the OF-MPC framework for traffic scenes that were not encountered during model training. Overall, the developed OF-MPC framework and the proposed method for characterizing the perceptual uncertainty of a visual perception system in unseen environments can contribute to the future development of advanced autonomous driving systems.