ABSTRACT:
It has long been a dream to improve human existence by integrating artificially intelligent robots into our society. We are now discovering that we not only desire, but need, such robots to help with current industrial and societal shortcomings, most recently highlighted by the pandemic. For the vision of intelligent robots to materialize, robots must autonomously operate over long periods of time. When robots team up with people, e.g., in disaster relief and manufacturing, most critical is the ability for them to adaptively work with other robots and engage in natural collaboration with humans. In this talk, I will present my fundamental research on lifelong collaborative autonomy that enables the above capabilities for intelligent robots. First, I will describe my work to address lifelong autonomy through representation learning and self-reflective adaptation for robots to build long-term environment representations and adjust their behaviors according to changes in not only the environment but also themselves. Next, I will describe my research on peer-to-peer teaming with a focus on collaborative perception and adaptive teaming to enable robots and humans to work together side by side with an interaction style that robots implicitly infer team behaviors and adaptively offer proactive assistance. Finally, I will broadly describe some of the most critical research gaps in creating intelligent robots before concluding with my long-term vision and plans to reimagine intelligence hierarchy for lifelong collaborative robots.

BIO:
Dr. Hao Zhang is currently a faculty member in the Department of Computer Science and the Robotics Graduate Program at the Colorado School of Mines (Mines). He joined Mines as an Assistant Professor in 2014 after receiving his Ph.D. degree in Computer Science, and was promoted to Associate Professor with tenure in 2020. As director of the Human-Centered Robotics Lab, Dr. Zhang leads and conducts research on lifelong collaborative autonomy and robot intelligence. His research interests broadly lie in artificial intelligence, machine learning, and extended reality for robotics. Dr. Zhang is the recipient of an NSF CAREER award and a DARPA Young Faculty Award (YFA) that recognize his contributions on human-inspired and human-integrated robot adaptation. His research program is sponsored by funding from diversified sources, such as NSF, DARPA, ARL, ARO, ONR, DOE, DOT, USAFA, and industry sponsors. Dr. Zhang regularly publishes at top robotics conferences and journals, such as RSS, ICRA, CoRL, IJRR, and RA-L, and has received multiple best paper nominations and awards.