Future Trajectories Control
Adrien discusses a groundbreaking system developed with Haruki and Boris at Stanford, focusing on controlling multiple future trajectories to avoid frozen car scenarios in self-driving vehicles. The concept of risk-sensitive control and entropic risk optimization are highlighted, showcasing the innovative approach to minimizing risk while optimizing driving objectives.In this clip
From this podcast
Gradient Dissent - A Machine Learning Podcast
Adrien Gaidon — Advancing ML Research in Autonomous Vehicles
Related Questions