Wei Xiao Wins 2020 IEEE CDC Outstanding Student Paper Award
The paper primarily applies to safe robot navigation in environments full of obstacles. Photo courtesy of Jeromey Balderrama.Wei Xiao, Boston University PhD candidate (SE), won a 2020 IEEE Conference on Decisions and Control Outstanding Student Paper Award for his paper entitled “Feasibility-Guided Learning for Constrained Optimal Control Problems”. His paper was published in Proc. of 59th IEEE Conference on Decision and Control on December 18, 2020.
This prestigious award was judged on “originality, clarity and potential impact on practical applications or theoretical foundations of control.” Over 1300 papers were presented at the conference. 64 were nominated for the Outstanding Student Paper award. Wei Xiao received one of the 4 Outstanding Student Paper Awards.
Xiao co-authored the paper with his advisors: CISE faculty affiliates, Professors Christos Cassandras (SE, ECE, Division Head of Systems Engineering) and Calin Belta (ME, ECE, SE). The paper addresses a fundamental and challenging problem in control theory: stabilizing a dynamical system while optimizing a cost and satisfying constraints. “Typically, such problems include autonomous driving in traffic and robot safe exploration in unknown environments,” says Xiao. “When safety becomes critical, it is desired to prioritize the strict satisfaction of constraints over optimality.”
In this paper, the researchers adopt the control barrier function (CBF) method to improve the feasibility of optimal control problems with stringent safety constraints and tight control limitations in an unknown environment. Since control functions are often too conservative in their response to unknown aspects of the environment, the researchers apply machine learning techniques to improve the feasible regions that a system can access. With this approach, an appropriate and safe response to unpredictable obstructions is created. Xiao tested these methods on a robot for the purpose of the study, although his work could be applied to improving the ability of autonomous vehicles to navigate around obstacles, ensuring safety for passengers and surrounding individuals.
Says Prof Cassandras, “This paper addresses a crucial dilemma in modern engineering: how to bridge the gap between control planning and powerful motion learning techniques? This paper is original in its approach to marrying classical control engineering with emerging machine learning techniques.”
Click here to read Xiao’s award-winning paper, Xiao, W., Belta, C., and Cassandras, C.G., “Feasibility-Guided Learning for Constrained Optimal Control Problems”, Proc. of 59th IEEE Conference on Decision and Control, pp. 1896-1901, 2020.
Xiao is a fourth year PhD student specializing in Connected Automated Vehicles (CAVs), Robotics, Lyapunov methods, Machine Learning, and Temporal Logic. Read more about his work here.