20 papers
Mulligan: Performance-Guided Data Collection for Efficient On-Robot Learning
Lars Ankile, Perry Dong, Rohan Bhowmik +4
Learning from human demonstrations is a reliable way to teach robots new tasks, but the gains from each additional demonstration shrink as the policy improves. Continued improvemen…
NEEDLEWORK: Offline Rewriting of Robot Data with Verified Local Stitches
Juntao Ren, Yifan Hou, Shuran Song
Robot demonstrations may contain useful behavior even when individual episodes are inefficient or unsuccessful. Trajectory stitching offers a way to compose these behaviors into im…
Memory Anchors for Continual Robot Learning
Maximilian Du, Zhanyi Sun, Chen Xu +3
Robot policies deployed in the wild should have the capability to continually learn new tasks without forgetting existing behaviors. A common approach to combat such catastrophic f…
Mixture of Frames Policy: Multi-Frame Action Denoising for Bimanual Mobile Manipulation
Dian Wang, Jisang Park, Xiaomeng Xu +3
Robotic manipulation is inherently multi-frame: local actions may be simple in an end-effector frame, while transport, upright-object handling, and whole-body coordination are bett…
Multisensory Continual Learning: Adapting Pretrained Visuomotor Policies to Force
Jaden Clark, Changhao Wang, Yihuai Gao +5
Robot manipulation often relies on sensory feedback beyond vision, particularly in contact-rich settings where force, tactile, or audio signals reveal interaction states that are n…
Robustness of Robotic Manipulation: Foundations and Frontiers
Yifei Dong, Zhanyi Sun, Lujie Yang +5
Humans and animals exhibit remarkable robustness in physical manipulation, yet robots remain far behind. Progress toward human-level manipulation robustness is hindered by the abse…
What Enables In-Context Behavior Prompting for Manipulation?
Austin Patel, Ben Pekarek, Joel Enrique Castro Hernandez +1
Behavior prompting is a paradigm in which a sensorimotor robot demonstration, called a behavior prompt, serves as an in-context prompt for performing new tasks at test time. While…
PanoVine: Whole-Body Visuomotor Control for Soft Growing Vine Robot
Yimeng Qin, Xiaomeng Xu, William Heap +3
Vine robots, a class of soft, growing robots, are suitable for navigating complex and confined environments due to their compliant bodies and self-supporting growth mechanism. Howe…
DF-ExpEnse: Diffusion Filtered Exploration for Sample Efficient Finetuning
Calvin Luo, Chen Sun, Shuran Song
A natural recipe for intelligent robotic decision-making is initializing from pretrained generative control policies, which have summarized offline experience, and adapting them to…
Will People Enjoy a Robot Trainer? A Case Study with Snoopie the Pacerbot
Maximilian Du, Jennifer Grannen, Shuran Song +1
The physicality of exercise makes the role of athletic trainers unique. Their physical presence allows them to guide a student through a motion, demonstrate an exercise, and give i…
Gated Memory Policy: In-Context Memorization and Adaptation
Yihuai Gao, Jeff Jinyun Liu, Shuang Li +1
Robotic manipulation tasks exhibit varying memory requirements, ranging from Markovian tasks that require no memory to non-Markovian tasks that demand in-context memorization of hi…
From Prior to Pro: Efficient Skill Mastery via Distribution Contractive RL Finetuning
Zhanyi Sun, Shuran Song
We introduce Distribution Contractive Reinforcement Learning (DICE-RL), a framework that uses reinforcement learning (RL) as a "distribution contraction" operator to refine pretrai…
Minimalist Compliance Control
Haochen Shi, Songbo Hu, Yifan Hou +3
Compliance control is essential for safe physical interaction, yet its adoption is limited by hardware requirements such as force torque sensors. While recent reinforcement learnin…
In-the-Wild Compliant Manipulation with UMI-FT
Hojung Choi, Yifan Hou, Chuer Pan +5
Many manipulation tasks require careful force modulation. With insufficient force the task may fail, while excessive force could cause damage. The high cost, bulky size and fragili…
Locomotion Beyond Feet
Tae Hoon Yang, Haochen Shi, Jiacheng Hu +10
Most locomotion methods for humanoid robots focus on leg-based gaits, yet natural bipeds frequently rely on hands, knees, and elbows to establish additional contacts for stability…
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…
Compliant Residual DAgger: Improving Real-World Contact-Rich Manipulation with Human Corrections
Xiaomeng Xu, Yifan Hou, Chendong Xin +2
We address key challenges in Dataset Aggregation (DAgger) for real-world contact-rich manipulation: how to collect informative human correction data and how to effectively update p…
DexMachina: Functional Retargeting for Bimanual Dexterous Manipulation
Zhao Mandi, Yifan Hou, Dieter Fox +3
We study the problem of functional retargeting: learning dexterous manipulation policies to track object states from human hand-object demonstrations. We focus on long-horizon, bim…
DexUMI: Using Human Hand as the Universal Manipulation Interface for Dexterous Manipulation
Mengda Xu, Han Zhang, Yifan Hou +4
We present DexUMI - a data collection and policy learning framework that uses the human hand as the natural interface to transfer dexterous manipulation skills to various robot han…
GET-Zero: Graph Embodiment Transformer for Zero-shot Embodiment Generalization
Austin Patel, Shuran Song
This paper introduces GET-Zero, a model architecture and training procedure for learning an embodiment-aware control policy that can immediately adapt to new hardware changes witho…