PATCH: Action-Chunk-Conditioned Latent Patch Innovation Monitoring for Robot Manipulation
arXiv, 2026 · First author
Yanan Zhou 「周亚楠」
PhD student at the University of Sydney
I am a PhD student at the University of Sydney, supervised by Dr Weiming (William) Zhi. I completed my B.E. (Honours) in Electrical Engineering at the University of Sydney (2022–2026).
My research lies at the intersection of robot perception, manipulation, and multi-robot collaboration. I aim to develop robotic systems that operate reliably in unstructured real-world environments and continually improve through privacy-preserving learning across distributed platforms.
Research
I study the loop from perception to action to learning: how robots understand a scene, act within it, and improve after deployment.
- Research interests
- Robot perception, robot manipulation, multi-robot collaboration, and trustworthy AI.
- Research question
- How can robots continually improve their perception, manipulation, and collaboration in the real world while remaining reliable and privacy-preserving?
News
-
Started my PhD at the University of Sydney under the supervision of Dr Weiming (William) Zhi.
-
Graduated with a Bachelor of Engineering Honours in Electrical Engineering from the University of Sydney.
Publications
Research area 01
Robotics & Embodied Intelligence
Robots that Collaborate: Sequential Asymmetric Imitation for Learning Coupled Robot Policies
arXiv, 2026
TriPilot-FF: Coordinated Whole-Body Teleoperation with Force Feedback
arXiv, 2026
PoseCompass: Intelligent Synthetic Pose Selection for Visual Localization
IEEE ICME, 2026 · First author
Research area 02
Trustworthy & Federated Learning
GuardFed: A Trustworthy Federated Learning Framework Against Dual-Facet Attacks
arXiv, 2025
Toward Better Privacy-Protected Federated Learning for Healthcare Services in Non-IID Scenarios
IEEE TETCI, 2026
FedSCOPE: A Comprehensive Evaluation Framework for Federated Learning in Human-Centered Social Computing
IEEE TCSS, 2025