6 papers
X-OP: Cross-Morphology Whole-Body Teleoperation via MPC Retargeting
Jen-Wei Wang, Sarthak Kaingade, Andrea Tagliabue +1
Whole-body teleoperation is essential for scalable robot data collection in loco-manipulation tasks, yet existing approaches relying on exoskeleton suits or multi-camera setups imp…
Aerobatic maneuvers in insect-scale flapping-wing aerial robots via deep-learned robust tube model predictive control
Yi-Hsuan Hsiao, Andrea Tagliabue, Owen Matteson +4
Aerial insects exhibit highly agile maneuvers such as sharp braking, saccades, and body flips under disturbance. In contrast, insect-scale aerial robots are limited to tracking non…
Terrain-aware Low Altitude Path Planning
Yixuan Jia, Andrea Tagliabue, Annika Thomas +2
In this paper, we study the problem of generating low-altitude path plans for nap-of-the-earth (NOE) flight in real time with only RGB images from onboard cameras and the vehicle p…
PRIMER: Perception-Aware Robust Learning-based Multiagent Trajectory Planner
Kota Kondo, Claudius T. Tewari, Andrea Tagliabue +4
In decentralized multiagent trajectory planners, agents need to communicate and exchange their positions to generate collision-free trajectories. However, due to localization error…
Efficient Deep Learning of Robust Policies from MPC using Imitation and Tube-Guided Data Augmentation
Andrea Tagliabue, Jonathan P. How
Imitation Learning (IL) can generate computationally efficient policies from demonstrations provided by Model Predictive Control (MPC). However, IL methods often require extensive…
CGD: Constraint-Guided Diffusion Policies for UAV Trajectory Planning
Kota Kondo, Andrea Tagliabue, Xiaoyi Cai +4
Traditional optimization-based planners, while effective, suffer from high computational costs, resulting in slow trajectory generation. A successful strategy to reduce computation…