Learning Stability Attention in Vision-based End-to-end Driving Policies

Wang, Tsun-Hsuan, Xiao, Wei, Chahine, Makram, Amini, Alexander, Hasani, Ramin, Rus, Daniela

arXiv.org Artificial Intelligence 

Modern end-to-end learning systems can learn to explicitly infer control from perception. However, it is difficult to guarantee stability and robustness for these systems since they are often exposed to unstructured, high-dimensional, and complex observation spaces (e.g., autonomous driving from a stream of pixel inputs). We propose to leverage control Lyapunov functions (CLFs) to equip end-to-end vision-based policies with stability properties and introduce stability attention in CLFs (att-CLFs) to tackle environmental changes and improve learning flexibility. We also present an uncertainty propagation technique that is tightly integrated into att-CLFs. We demonstrate the effectiveness of att-CLFs via comparison with classical CLFs, model predictive control, and vanilla end-to-end learning in a photo-realistic simulator and on a real full-scale autonomous vehicle.

Duplicate Docs Excel Report

Title
None found

Similar Docs  Excel Report  more

TitleSimilaritySource
None found