Robots that Collaborate: Sequential Asymmetric Imitation
Learning to wait, yield, and recover as a partner changes the task.
Read paper
Publications
The question keeps widening.
From motion planning and human contact to memory and multi-robot interaction, these papers follow one question: how can a robot act without losing sight of what — or who — its next action affects? These are selected works; the full research history is on Scholar.
TRACE: Trajectory-Routed Causal Memory
Carrying evidence forward when the clue has already left the scene.
Read paper
TriPilot-FF: Coordinated Whole-Body Teleoperation
Giving hands and feet a shared language for contact, reach, and motion.
Read paper
TAPOM: Task-Space Topology-Guided Planning
Finding the passage before searching the high-dimensional motion space.
Read paper
Robot-Friendly Scaffolding with Passive Error Correction
A tapered connector turns imperfect alignment into a reliable assembly step.
Read paper
Operational Behaviors Inference for Physical HREI
Predicting human intent while optimizing motion around real contact.
Read paper