Abstract: Human-robot interactions have been recognized to be a key element of future robots in many application domains such as manufacturing, transportation and service. In factories, robots are cooperating with human workers. In transportation systems, automated vehicles are running on public roads. These robots need to be human-friendly while maintaining high performance. In this talk, the general methodology in designing the behaviors of these robots through cognition and motion planning will be overviewed, followed by an in-depth discussion on the robot safe interaction system (RSIS) for intelligent industrial co-robots. RSIS adopts an optimization-based parallel planning and control architecture, which achieves real-time computation with limited computation power, and enables the robot to interact safely and efficiently with human workers as validated by experiments. The work on RSIS shows a promising way to build intelligent robots that can better serve, assist and collaborate with people in their daily lives across work, home and leisure.

Biosketch: Changliu Liu is a Ph.D. candidate in the Department of Mechanical Engineering, University of California at Berkeley, expected to graduate in May, 2017. She received the B.S. degree in mechanical engineering and the B.S. degree in economics from Tsinghua University (China) in 2012, and the M.S. degree in mechanical engineering and the M.A. degree in mathematics from University of California at Berkeley in 2014 and in 2016 respectively. Her research interests lie in the intersection of robotics, human-robot interactions, control and motion planning, optimal control and optimization, multi-agent system and game theory, machine learning and artificial intelligence. She was the recipient of the Chinese National Scholarship in 2010 and the Berkeley fellowship in 2012. Her Ph.D. work has been supported by the Berkeley fellowship, Denso International and FANUC Corporation.