Samuel Coogan

Hard safety guarantees no longer require hours of offline pre-computation: an online, interval-based verification pipeline brings formal reachability directly into sampling-based MPC while eliminating over 99% of trajectory violations.

Achieving reliable model discrimination in under 50 ms while ensuring safety could revolutionize fault diagnosis in high-stakes robotic applications.

MA-AC-MPC outperforms traditional models, achieving a perfect success rate in cooperative tasks while ensuring safety and feasibility in dynamic environments.

Interleaving motion planning with VLAs can yield over double the task progress in complex mobile manipulation scenarios without requiring more training data.