Safety guarantees for autonomous drones and air taxis: learned reachable sets that build collision avoidance into the controller, and camera-based 3D models from neural radiance fields for safe path planning.
My doctoral research at Purdue: fast, data-driven ways to prove that learned, networked and multi-agent autonomous systems stay safe, and to expose how attackers could exploit them.
Using control theory to make language-model components predictable enough for safety-critical deployment: safety classifiers that can prove their decisions, and fine-tuning adapters whose memory can be analyzed and compressed with guarantees.