Skip to main content

Reachability

Unmanned Aerial Vehicle Safe Autonomous Operations

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.

Provable Safety and Efficient Memory for Language Models

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.