15 citations · 40 across the 22 of their papers we have counts for
19 papers · 1 filter
Value as Memory: Online Value-Guided Post-training for General Robot Policies
Wenye Yu, Yijin Chen, Kaiyi Xiong +7
Real-world post-training of generalist robot policies faces two challenges: partial observability makes action selection ambiguous, while offline post-training methods delay feedba…
FA-RDP: A Frequency-Adaptive Reactive Diffusion Policy for Contact-Rich Manipulation
Lifeng Zhuo, Wendi Chen, Han Xue +4
In contact-rich manipulation, action multimodality and reactivity dominate different stages of a single episode. Before contact, multiple trajectories might be equally valid, makin…
Never Too Late for Force: Accelerating VLA Post-Training with Reactive Force Injection
Yi Wang, Wendi Chen, Zimo Wen +8
Pretrained vision-language-action (VLA) policies provide strong language-conditioned manipulation knowledge, but they remain largely vision-driven and can struggle once manipulatio…
ActiveGlasses: Learning Manipulation with Active Vision from Ego-centric Human Demonstration
Yanwen Zou, Chenyang Shi, Wenye Yu +5
Large-scale real-world robot data collection is a prerequisite for bringing robots into everyday deployment. However, existing pipelines often rely on specialized handheld devices…
RoboPocket: Improve Robot Policies Instantly with Your Phone
Junjie Fang, Wendi Chen, Han Xue +7
Scaling robot learning is bottlenecked not only by data volume, but also by whether the data targets the policy's failures. Existing robot-free handheld interfaces enable portable…
Rethinking Camera Choice: An Empirical Study on Fisheye Camera Properties in Robotic Manipulation
Han Xue, Nan Min, Xiaotong Liu +5
The adoption of fisheye cameras in robotic manipulation, driven by their exceptionally wide Field of View (FoV), is rapidly outpacing a systematic understanding of their downstream…
ImplicitRDP: An End-to-End Visual-Force Diffusion Policy with Structural Slow-Fast Learning
Wendi Chen, Han Xue, Yi Wang +6
Human-level contact-rich manipulation relies on the distinct roles of two key modalities: vision provides spatially rich but temporally slow global context, while force sensing cap…
ARMADA: Autonomous Online Failure Detection and Human Shared Control Empower Scalable Real-world Deployment and Adaptation
Wenye Yu, Jun Lv, Zixi Ying +3
Imitation learning has shown promise in learning from large-scale real-world datasets. However, pretrained policies usually perform poorly without sufficient in-domain data. Beside…
SOE: Sample-Efficient Robot Policy Self-Improvement via On-Manifold Exploration
Yang Jin, Jun Lv, Han Xue +3
Intelligent agents progress by continually refining their capabilities through actively exploring environments. Yet robot policies often lack sufficient exploration capability due…
Knowledge-Driven Imitation Learning: Enabling Generalization Across Diverse Conditions
Zhuochen Miao, Jun Lv, Hongjie Fang +2
Imitation learning has emerged as a powerful paradigm in robot manipulation, yet its generalization capability remains constrained by object-specific dependencies in limited expert…
SIME: Enhancing Policy Self-Improvement with Modal-level Exploration
Yang Jin, Jun Lv, Wenye Yu +3
Self-improvement requires robotic systems to initially learn from human-provided data and then gradually enhance their capabilities through interaction with the environment. This i…
Novel Demonstration Generation with Gaussian Splatting Enables Robust One-Shot Manipulation
Sizhe Yang, Wenye Yu, Jia Zeng +5
Visuomotor policies learned from teleoperated demonstrations face challenges such as lengthy data collection, high costs, and limited data diversity. Existing approaches address th…
AirExo-2: Scaling up Generalizable Robotic Imitation Learning with Low-Cost Exoskeletons
Hongjie Fang, Chenxi Wang, Yiming Wang +11
Scaling up robotic imitation learning for real-world applications requires efficient and scalable demonstration collection methods. While teleoperation is effective, it depends on…
TieBot: Learning to Knot a Tie from Visual Demonstration through a Real-to-Sim-to-Real Approach
Weikun Peng, Jun Lv, Yuwei Zeng +5
The tie-knotting task is highly challenging due to the tie's high deformation and long-horizon manipulation actions. This work presents TieBot, a Real-to-Sim-to-Real learning from…
Human-Agent Joint Learning for Efficient Robot Manipulation Skill Acquisition
Shengcheng Luo, Quanquan Peng, Jun Lv +4
Employing a teleoperation system for gathering demonstrations offers the potential for more efficient learning of robot manipulation. However, teleoperating a robot arm equipped wi…
DiffGen: Robot Demonstration Generation via Differentiable Physics Simulation, Differentiable Rendering, and Vision-Language Model
Yang Jin, Jun Lv, Shuqiang Jiang +1
Generating robot demonstrations through simulation is widely recognized as an effective way to scale up robot data. Previous work often trained reinforcement learning agents to gen…
ClothesNet: An Information-Rich 3D Garment Model Repository with Simulated Clothes Environment
Bingyang Zhou, Haoyu Zhou, Tianhai Liang +10
We present ClothesNet: a large-scale dataset of 3D clothes objects with information-rich annotations. Our dataset consists of around 4400 models covering 11 categories annotated wi…
SAM-RL: Sensing-Aware Model-Based Reinforcement Learning via Differentiable Physics-Based Simulation and Rendering
Jun Lv, Yunhai Feng, Cheng Zhang +3
Model-based reinforcement learning (MBRL) is recognized with the potential to be significantly more sample-efficient than model-free RL. How an accurate model can be developed auto…
SAGCI-System: Towards Sample-Efficient, Generalizable, Compositional, and Incremental Robot Learning
Jun Lv, Qiaojun Yu, Lin Shao +3
Building general-purpose robots to perform a diverse range of tasks in a large variety of environments in the physical world at the human level is extremely challenging. It require…