7 papers
Robot-Powered Data Flywheels: Deploying Robots in the Wild for Continual Data Collection and Foundation Model Adaptation
Jennifer Grannen, Michelle Pan, Kenneth Llontop +4
Foundation models (FM) have unlocked powerful zero-shot capabilities in vision and language, yet their reliance on internet pretraining data leaves them brittle in unstructured, re…
Constraint-Preserving Data Generation for Visuomotor Policy Learning
Kevin Lin, Varun Ragunath, Andrew McAlinden +4
Large-scale demonstration data has powered key breakthroughs in robot manipulation, but collecting that data remains costly and time-consuming. We present Constraint-Preserving Dat…
Gentle Object Retraction in Dense Clutter Using Multimodal Force Sensing and Imitation Learning
Dane Brouwer, Joshua Citron, Heather Nolte +2
Dense collections of movable objects are common in everyday spaces-from cabinets in a home to shelves in a warehouse. Safely retracting objects from such collections is difficult f…
Vision in Action: Learning Active Perception from Human Demonstrations
Haoyu Xiong, Xiaomeng Xu, Jimmy Wu +3
We present Vision in Action (ViA), an active perception system for bimanual robot manipulation. ViA learns task-relevant active perceptual strategies (e.g., searching, tracking, an…
Crossing the Human-Robot Embodiment Gap with Sim-to-Real RL using One Human Demonstration
Tyler Ga Wei Lum, Olivia Y. Lee, C. Karen Liu +1
Teaching robots dexterous manipulation skills often requires collecting hundreds of demonstrations using wearables or teleoperation, a process that is challenging to scale. Videos…
Motion Tracks: A Unified Representation for Human-Robot Transfer in Few-Shot Imitation Learning
Juntao Ren, Priya Sundaresan, Dorsa Sadigh +2
Teaching robots to autonomously complete everyday tasks remains a challenge. Imitation Learning (IL) is a powerful approach that imbues robots with skills via demonstrations, but i…