Publications

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

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

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

Enabling micro aerial vehicles to detect and traverse manholes for ballast water tank exploration.

Task-driven compression method for collision encoding based on depth images.

Autonomous mapping and spectroscopic analysis of distributed radiation fields using aerial robots.

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

Shape and motion planning for a reconfigurable aerial robotic system.

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

Teamed exploration of subterranean environments using legged and aerial robots.

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

Various open-source tools and frameworks for robotics and simulation.

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

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 Multi-Modal SLAM Framework for resilience against sensor degradation.