12 papers
SkillFab: An Agent-Native Skill Production Platform
Anjie Xu, Yifeng Cai, Yi Li +5
SkillFab is an agent-native platform for turning missing capabilities into reviewed, reusable Agent Skills. At runtime, agents first search for reusable skills; when no adequate sk…
Efficient Sim-to-Real Transfer of World-Action Models from Synthetic Priors
Zixing Wang, Kausik Sivakumar, Jinghuan Shang +5
Bridging the sim-to-real gap is a core challenge in deploying learned manipulation policies. Sim-to-real learning is attractive because it can replace expensive real robot demonstr…
Passive iFIR filters for data-driven velocity control in robotics
Yi Zhang, Zixing Wang, Fulvio Forni
We present a passive, data-driven velocity control method for nonlinear robotic manipulators that achieves better tracking performance than optimized PID with comparable design com…
SkillTester: Benchmarking Utility and Security of Agent Skills
Leye Wang, Zixing Wang, Anjie Xu
This technical report presents SkillTester, a tool for evaluating the utility and security of agent skills. Its evaluation framework combines paired baseline and with-skill executi…
PPGuide: Steering Diffusion Policies with Performance Predictive Guidance
Zixing Wang, Devesh K. Jha, Ahmed H. Qureshi +1
Diffusion policies have shown to be very efficient at learning complex, multi-modal behaviors for robotic manipulation. However, errors in generated action sequences can compound o…
ExpertGen: Scalable Sim-to-Real Expert Policy Learning from Imperfect Behavior Priors
Zifan Xu, Ran Gong, Maria Vittoria Minniti +10
Learning generalizable and robust behavior cloning policies requires large volumes of high-quality robotics data. While human demonstrations (e.g., through teleoperation) serve as…
Multimodal Human-Intent Modeling for Contextual Robot-to-Human Handovers of Arbitrary Objects
Lucas Chen, Guna Avula, Hanwen Ren +2
Human-robot object handover is a crucial element for assistive robots that aim to help people in their daily lives, including elderly care, hospitals, and factory floors. The exist…
Physics-Conditioned Grasping for Stable Tool Use
Noah Trupin, Zixing Wang, Ahmed H. Qureshi
Tool use often fails not because robots misidentify tools, but because grasps cannot withstand task-induced wrench. Existing vision-language manipulation systems ground tools and c…
Implicit Physics-aware Policy for Dynamic Manipulation of Rigid Objects via Soft Body Tools
Zixing Wang, Ahmed H. Qureshi
Recent advancements in robot tool use have unlocked their usage for novel tasks, yet the predominant focus is on rigid-body tools, while the investigation of soft-body tools and th…
ContactHandover: Contact-Guided Robot-to-Human Object Handover
Zixi Wang, Zeyi Liu, Nicolas Ouporov +1
Robot-to-human object handover is an important step in many human robot collaboration tasks. A successful handover requires the robot to maintain a stable grasp on the object while…
AnyPose: Anytime 3D Human Pose Forecasting via Neural Ordinary Differential Equations
Zixing Wang, Ahmed H. Qureshi
Anytime 3D human pose forecasting is crucial to synchronous real-world human-machine interaction, where the term ``anytime" corresponds to predicting human pose at any real-valued…
DeRi-IGP: Learning to Manipulate Rigid Objects Using Deformable Objects via Iterative Grasp-Pull
Zixing Wang, Ahmed H. Qureshi
Robotic manipulation of rigid objects via deformable linear objects (DLO) such as ropes is an emerging field of research with applications in various rigid object transportation ta…