Seminar: Towards Multimodal, Human-Centered, and Trustworthy Robotics

For robots to reliably assist with activities of daily living, it is important that they leverage multisensory feedback, enable contact-rich manipulations, and behave in ways that people perceive as safe and trustworthy. My research develops human-in-the-loop frameworks that integrate multimodal perception with learning-based control to enable adaptive and trustworthy interactions. 

In this talk, I will present work on robotic manipulation benchmarking methods that integrate modular components into interchangeable pipelines, as well as robotic assistive frameworks designed for human-centered tasks, such as tactile-driven garment button fastening. These systems address key challenges in assistive manipulation, including enabling robots to use everyday tools, operate safely near the human body, manipulate deformable objects, and assist individuals who may be hesitant to trust automation. I will also outline future directions for incorporating trust-building mechanisms to improve the safety and acceptance of human-robot collaboration.

About the Speaker(s)

Huajing Zhao
Postdoctoral Researcher, UMass, Lowell

Huajing Zhao is an incoming assistant professor in the Department of Mechanical Engineering at the University of Tulsa. She is currently a postdoctoral researcher at the NERVE Center at the University of Massachusetts, Lowell. She earned a PhD in mechanical and aerospace engineering from the University of California, Los Angeles, a BS degree from Harbin Institute of Technology, an MEng degree from the University of California, Berkeley, and an MS degree from the University of Michigan, Ann Arbor. 

Her research has been supported by NASA Ames Research Center, the Office of Naval Research, the National Science Foundation, and Amazon Science Hub. Her work has been featured in venues such as IEEE Transactions on Control Systems Technology, the IEEE Haptics Symposium, and the IEEE-RAS International Conference on Soft Robotics. She received the Best Paper Award at the 2025 AAAI Fall Symposium on Unifying Representations for Robot Application Development.

Her recent research centers on advancing assistive robotics through tactile sensing, contact modeling, and reinforcement learning, benchmarking modular robotic manipulation pipelines, and developing human-robot interaction frameworks to understand and improve user trust in robot-assisted tasks near the human body.

Contact

For more information, contact Yanqiao Li at yanqiao.li@dartmouth.edu .