Knowledge-based, AR-mediated Robot Planning under Uncertainty

Abstract

Knowledge representation and reasoning (KRR) is one of the earliest research topics in AI. Researchers have used KRR methods for representing and reasoning with commonsense knowledge, action knowledge, temporal knowledge, etc. However, people frequently find hose methods not performing well in scalability and robustness. Numerical methods have dominated recent developments in planning under uncertainty and reinforcement learning. In this talk, I will present recent work from my group that leverages declarative knowledge for robot (task and motion) planning and reinforcement learning. Lastly, I will introduce our very recent work, called ARROCH, on augmented reality for robots collaborating with a human.

Bio:

Dr. Shiqi Zhang is an Assistant Professor of Computer Science at SUNY Binghamton. From 2014 to 2016, he was a Postdoctoral Fellow working on a team of mobile service robots at UT Austin. He received his Ph.D. in Computer Science (2013) from Texas Tech University. Before that, he received his Master's (2008) and B.S. (2006) degrees from Harbin Institute of Technology in China. He received an AAMAS-2018 Best Robotics Paper Award, an OPPO Faculty Research Award, and multiple Ford URP Awards. Dr. Zhang's research lies in the intersection of artificial intelligence and robotics. He is particularly interested in developing intelligent robots that interact with people, provide services to people, and learn from this experience.

Please join the meeting in Sococo VH 102, or Zoom.

Join Zoom Meeting: https://tufts.zoom.us/j/98610939077

PASSWORD: See colloquia email

Dial by your location: +1 646 558 8656 US (New York)

Meeting ID: 986 1093 9077

PASSCODE: See colloquia email