Chenghao Li

I am currently a third-year Ph.D. candidate in Information Science at Japan Advanced Institute of Science and Technology (JAIST). My research interests focus on the interdisciplinary area of robot visual grasping, AI security, and human-robot interaction, aiming to enhance the safety of AI-powered visual grasping systems in human-robot interaction scenarios by designing reliable and stable grasping policies.

Google Scholar Github YouTube ORCID ResearchGate

chenghao (dot) li (at) ieee (dot) org

Quality-focused Active Adversarial Policy for Safe Grasping in Human-Robot Interaction

Chenghao Li, Razvan Beuran, and Nak Young Chong
IEEE Transactions on Automation Science and Engineering (T-ASE), 2025, Revision
Paper • Code • Video

Monozone-centric Instance Grasping Policy in Large-scale Dense Clutter

Chenghao Li, and Nak Young Chong
IEEE/ASME Transactions on Mechatronics (T-MECH), 2025
Paper • Code • Video

Shortcut-enhanced Multimodal Backdoor Attack in Vision-guided Robot Grasping

Chenghao Li, Ziyan Gao, and Nak Young Chong
IEEE Transactions on Automation Science and Engineering (T-ASE), 2025
Paper • Video

Membership: IEEE Robotics and Automation Society (RAS) Member, IEEE Graduate Student Member

Reviewer: IEEE Transactions on Automation Science and Engineering (T-ASE), Imaging and Vision Computing, Computers and Graphics, IEEE International Conference on Ubiquitous Robots (UR)

Beyond research, I have a deep passion for photography, which I have been practicing for over ten years. I particularly enjoy black-and-white street photography, as it allows me to capture raw, timeless moments and find relaxation through observing everyday life from unique perspectives.