ROAM Lab

Dexterous Interface for Transparent TeleOperation

A Multimodal Tactile Finger with Taxelized Dynamic Sensing for Dexterous Manipulation

Healthy-to-Stroke Few-Shot Adaptation for sEMG-Based Intent Detection

Learning Human-in-the-Loop Policies with Diffusion Models

Stable, Low-Latency Intent Detection from sEMG via Masked Modeling

Active Acoustic Tactile Sensing for Contact-Rich Manipulation

Design Co-optimization with Reinforcement Learning via a Differentiable Hardware Model Proxy

Task-Based Design and Policy Co-Optimization for Tendon-Driven Underactuated Kinematic Chains

Dexterous In-Hand Manipulation by Guiding Exploration with Simple Sub-Skill Controllers

Decision Making for Human-in-the-Loop Robotic Agents via Uncertainty-Aware Reinforcement Learning

Sampling-Based Exploration for Reinforcement Learning of Dexterous Manipulation

Discovering Synergies for Robot Manipulation with Multi-Task Reinforcement Learning

On the Feasibility of Learning Finger-Gaiting In-Hand Manipulation with Intrinsic Sensing

Adaptive Semi-Supervised Intent Inferral to Control a Powered Hand Orthosis for Stroke

Hardware as Policy: Mechanical and Computational Co-Optimization using Deep Reinforcement Learning