collaborators

17 papers

cs.RO2026

DexDirect: Direct Kinesthetic Arm Guidance for Efficient Dexterous Demonstration Collection

Beom Jun Kim, Shiu-Jen Wang, Jonathan Liu +7

DexDirect lets a user guide a gravity‑compensated robot arm by hand while a webcam maps the user’s other hand onto a dexterous robot hand, enabling fast, low‑setup collection of ma…

cs.RO2026

Proximal State Nudging: Reducing Skill Atrophy from AI Assistance

Megha Srivastava, Jonathan Ouyang, Eric Zhou +6

Skill atrophy, the gradual decline of human capability under AI assistance, poses a safety risk in shared-control of semi-autonomous systems, where operators may be unable to disti…

cs.RO2026

Learning from the Best: Smoothness-Driven Metrics for Data Quality in Imitation Learning

Soham Kulkarni, Raayan Dhar, Yuchen Cui

In behavioral cloning (BC), policy performance is fundamentally limited by demonstration data quality. Real-world datasets contain trajectories of varying quality due to operator s…

cs.HC2026

DiSCo: Diffusion Sequence Copilots for Shared Autonomy

Andy Wang, Xu Yan, Brandon McMahan +9

Shared autonomy combines human user and AI copilot actions to control complex systems such as robotic arms. When a task is challenging, requires high dimensional control, or is sub…

cs.RO2026

TeleDex: Accessible Dexterous Teleoperation

Omar Rayyan, Maximilian Gilles, Yuchen Cui

Despite increasing dataset scale and model capacity, robot manipulation policies still struggle to generalize beyond their training distributions. As a result, deploying state-of-t…

cs.RO2026

DexEXO: A Wearability-First Dexterous Exoskeleton for Operator-Agnostic Demonstration and Learning

Alvin Zhu, Mingzhang Zhu, Beom Jun Kim +10

Scaling dexterous robot learning is constrained by the difficulty of collecting high-quality demonstrations across diverse operators. Existing wearable interfaces often trade comfo…