Research Areas
We develop algorithms and systems for robots that physically interact with complex real-world environments.
Physical Embodiment
We integrate force-aware control and tactile sensing to enhance the physical capabilities of robotic systems. By processing high-fidelity contact feedback and haptic data, our robots achieve safe and stable interaction in unstructured environments, moving beyond purely vision-based approaches.
Visuomotor Policy
We build end-to-end learning systems that map sensory inputs directly to motor commands. Utilizing imitation learning and Vision-Language-Action (VLA) models, our research enables robots to generalize across diverse tasks and follow complex natural language instructions in real-world settings.
Whole-Body Control
We develop optimization-based control frameworks for high-degree-of-freedom robotic systems. By leveraging Hierarchical Quadratic Programming (HQP) for multi-objective constraint satisfaction and Model Predictive Path Integral (MPPI) for nonlinear dynamics, we enable agile, balanced, and coordinated full-body movements.
Research Projects
Ongoing and recent projects — videos and details will be updated as work progresses.
Mobile Manipulator Door Navigation
Motion planning and whole-body control enabling a mobile manipulator to autonomously traverse door environments, handling complex contact constraints and task transitions.
Imitation Learning for Manipulation
End-to-end visuomotor policy learning from human demonstrations, enabling robots to perform dexterous manipulation tasks in unstructured environments via behavior cloning and VLA models.
HQP-based Whole-Body Control
Hierarchical quadratic programming framework for whole-body robot control with continuous task transitions, enabling smooth switching between task priorities and real-time collision avoidance.
MPPI for Mobile Manipulation
Model Predictive Path Integral control for nonlinear whole-body dynamics, providing real-time obstacle avoidance and agile motion generation for hybrid cable-driven and legged robotic platforms.