Showing cs.ROShow all
3 papers · 1 filter
cs.RO2026
DEFT-VLA: Stage-Localized Force Specialization for Contact-Rich Robotic Manipulation
Zan Huang, Yibo Qiu, Kan Ding +4
Contact-rich manipulation poses a stage-dependent sensory conflict: vision and proprioception are essential for localization and approach, when force is largely uninformative and p…
cs.RO2026
GRAFT: Grounded and Efficient Online Reinforcement Adaptation for Fine-Grained Robot Manipulation
Yibo Qiu, Haoliang Ye, Shu'ang Sun +3
Pretrained vision-language-action (VLA) policies provide strong priors for robot manipulation, yet adapting them online to fine-grained biomedical tasks remains challenging. Task s…
cs.RO2026
Keyframe-Guided Structured Rewards for Reinforcement Learning in Long-Horizon Laboratory Robotics
Yibo Qiu, Shu'ang Sun, Haoliang Ye +2
Long-horizon precision manipulation in laboratory automation, such as pipette tip attachment and liquid transfer, requires policies that respect strict procedural logic while opera…