CMSA Computer Science for Mathematicians: Large-scale multi-robot systems: From algorithmic foundations to smart-mobility applications
Kiril Solovey - Stanford University and SLAC National Accelerator Laboratory
Multi-robot systems are already playing a crucial role in manufacturing, warehouse automation, and natural resource monitoring, and in the future they will be employed in even broader domains from space exploration to search-and-rescue. Moreover, these systems will likely be incorporated in our daily lives through drone delivery services and smart mobility systems that comprise of thousands of autonomous vehicles. The anticipated benefits of multi-robot systems are numerous, ranging from automating dangerous jobs, to broader societal facets such as easing traffic congestion and sustainability. However, to reap those rewards we must develop control mechanisms for such systems that can adapt rapidly to unexpected changes on a massive scale. Importantly, these mechanisms must capture: (i) dynamical and collision-avoidance constraints of individual robots; (ii) interactions between multiple robots; and (iii) more broadly, the interaction of those systems with the environment. All these considerations give rise to extremely complex and high-dimensional optimization problems that need to be solved in real-time.
In this talk I will present recent progress on the design of algorithms for control and decision-making to allow the safe, effective, and societally-equitable deployment of multi-robot systems. I will highlight both results on fundamental capabilities for multi-robot systems (e.g., motion planning and task allocation), as well as applications in smart mobility, including multi-drone delivery and autonomous mobility-on-demand systems. Along the way, I will mention a few related open problems in mathematics and algorithm design.
Kiril Solovey is roboticist specializing in multi-robot systems and their applications to smart mobility. He is currently a Postdoctoral Scholar at the Department of Aeronautics and Astronautics, Stanford University, working with Marco Pavone, where he is supported by the Center for Automotive Research (CARS). He obtained a PhD in Computer Science from Tel Aviv University, where he was advised by Dan Halperin.
Kiril's research focuses on the design of effective control and decision-making mechanisms to allow multi-robot systems to tackle complex problems for the benefit of the society. His work draws upon ideas that span across the disciplines of engineering, computer science, and transportation science, to develop scalable optimization approaches with substantial guarantees regarding quality and robustness of the solution. For his work he received multiple awards, including the Clore Scholars and Fulbright Postdoctoral Fellowships, best paper awards and nominations (at Robotics: Science and Systems, International Conference on Robotics and Automation, International Symposium on Multi-Robot and Multi-Agent System, and European Control Conference), and teaching awards.