XRoboToolKit-T preprint released
XRoboToolKit-T, a teleoperation system with tactile sensing for stable and precise contact-rich manipulation, is now available on arXiv. Read the preprint
Recent research achievements, major paper acceptances, academic awards, and team updates.
XRoboToolKit-T, a teleoperation system with tactile sensing for stable and precise contact-rich manipulation, is now available on arXiv. Read the preprint
CopilotTele, a shared-autonomy teleoperation system for bimanual manufacturing assembly with risk-guided arbitration, is accepted to the IEEE International Conference on Automation Science and Engineering (CASE 2026) and selected as a Best Student Paper Award Finalist.
AssemblyMate, an interactive context-aware AI-XR co-worker with multimodal spatial-temporal reasoning for manufacturing assembly, is published in npj Advanced Manufacturing. Prof. Yunbo Zhang is the corresponding author. Read the paper
Our AR-assisted cyber-physical system for manual spray painting of complex geometries receives the ASME IDETC/CIE 2026 VARE Technical Committee Best Paper Award.
Prof. Zhang speaks on “Embodied Physical Intelligence for Smart Manufacturing: Challenges, Pathways and Applications” at the AI-Empowered Industrial Manufacturing and Robotics Forum in Shenzhen.
Prof. Zhang shares the lab’s view on field data, human-robot collaboration and robot execution at EAC 2026 (Shanghai Automobile Exhibition Center).
Frontier Intelligent Robotics Lab will join the Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences (HKISI-CAS) in June 2026. Professor Zhang will join HKISI-CAS as a Professor (Research Fellow).
Our research paper titled "VLAbot: A Human Vision-Language-Action Models Interaction Framework for Robotic Assembly" was published in RCIM (Elsevier). The framework explores how multi-expert VLA agents and augmented reality interfaces interact for long-horizon robotic assembly tasks.
Our paper titled "Indoor Depth Completion via Geometry Processing with RGB Image" was published in ESWA. The paper establishes a geometry processing pipeline to reconstruct high-accuracy indoor depth maps in challenging manufacturing scenarios.
The paper "RoPESim: A Framework for Robot Manipulation Policy Evaluation via Simulation" was accepted to the IEEE International Conference on Automation Science and Engineering (CASE 2025). The benchmark provides automated simulation validation for learned manipulation policies.
The lab released new work on zero-shot robot manipulation via action decomposition and composition, and on HALO hierarchical long-horizon manipulation with failure recovery, together with full real-robot video demonstrations. The two works were published at IEEE CASE 2026 and the IISE Annual Conference & Expo 2025, respectively.
The system "RADAR: Robotics Assembly by Demonstration via Augmented Reality" was presented at IEEE/RSJ IROS 2024, demonstrating intuitive spatial computing interfaces for robot assembly programming.
Our research on 6-DoF robot grasp pose learning through augmented reality teleoperation demonstrations was presented at the IEEE International Conference on Robotics and Automation (ICRA 2024).
Our empirical study on mid-air gesture cybersecurity vulnerabilities and password leakage in mixed-reality manufacturing systems was published in the ASME Journal of Computing and Information Science in Engineering.
Research on collaborative robot interfaces and human-assisted assembly appeared in JIM, establishing foundational principles for multimodal interaction in smart manufacturing.