MMD-OPT : Maximum Mean Discrepancy Based Sample Efficient Collision Risk Minimization for Autonomous Driving
This addresses collision risk minimization for autonomous driving systems, offering a sample-efficient improvement over existing methods.
The paper tackled the problem of minimizing collision risk for autonomous driving under arbitrary obstacle prediction distributions by proposing MMD-OPT, a sample-efficient approach using Maximum Mean Discrepancy in RKHS, which resulted in safer trajectories at low sample regimes compared to CVaR-based methods.
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).