Autonomy

Safe navigation using Neural Control Barrier Functions (NCBFs) for aerial robots.

Deep reinforcement learning approach for inspection path planning with semantic awareness.

Winning team (Team CERBERUS) of the DARPA Subterranean Challenge.

A unified pilot for enabling GPS-denied autonomy across different robotic embodiments.

Autonomous navigation using aerial robots with semantic awareness for collision prediction.

Teamed exploration of subterranean environments using legged and aerial robots.

A field-tested autonomy architecture commanding a diverse set of robots.

General visual inspection of ship ballast water tanks using aerial robots.

A Multi-Modal SLAM Framework for resilience against sensor degradation.

Exploiting Deep Collision Encoding for autonomous flight in dense environments.

A framework for highly parallelized simulation of aerial robots based on NVIDIA Isaac Gym.

A collision-tolerant flying robot for autonomous subterranean exploration.

Shape and motion planning for a reconfigurable aerial robotic system.