MMD-OPT : Maximum Mean Discrepancy Based Sample Efficient Collision Risk Minimization for Autonomous Driving

TL;DR

MMD-OPT introduces a novel, sample-efficient collision risk minimization method for autonomous driving using MMD in RKHS, outperforming existing approaches especially with limited data.

Contribution

The paper presents MMD-OPT, a new approach leveraging MMD in RKHS for more efficient collision risk estimation in autonomous vehicle trajectory planning.

Findings

MMD-OPT achieves safer trajectories with fewer samples.

It outperforms CVaR-based methods in low-sample regimes.

Validated on synthetic and real-world datasets.

Abstract

We propose MMD-OPT: a sample-efficient approach for minimizing the risk of collision under arbitrary prediction distribution of the dynamic obstacles. MMD-OPT is based on embedding distribution in Reproducing Kernel Hilbert Space (RKHS) and the associated Maximum Mean Discrepancy (MMD). We show how these two concepts can be used to define a sample efficient surrogate for collision risk estimate. We perform extensive simulations to validate the effectiveness of MMD-OPT on both synthetic and real-world datasets. Importantly, we show that trajectory optimization with our MMD-based collision risk surrogate leads to safer trajectories at low sample regimes than popular alternatives based on Conditional Value at Risk (CVaR).