4 papers
TACO: Trajectory-Aware Controller Optimization for Quadrotors
Hersh Sanghvi, Spencer Folk, Vijay Kumar +1
Controller performance in quadrotor trajectory tracking depends heavily on parameter tuning, yet standard approaches often rely on fixed, manually tuned parameters that sacrifice t…
OCCAM: Online Continuous Controller Adaptation with Meta-Learned Models
Hersh Sanghvi, Spencer Folk, Camillo Jose Taylor
Control tuning and adaptation present a significant challenge to the usage of robots in diverse environments. It is often nontrivial to find a single set of control parameters by h…
Recent Approaches for Perceptive Legged Locomotion
Hersh Sanghvi
As both legged robots and embedded compute have become more capable, researchers have started to focus on field deployment of these robots. Robust autonomy in unstructured environm…
Fast Footstep Planning on Uneven Terrain Using Deep Sequential Models
Hersh Sanghvi, Camillo Jose Taylor
One of the fundamental challenges in realizing the potential of legged robots is generating plans to traverse challenging terrains. Control actions must be carefully selected so th…