Multi-Robot Learning: Leveraging Communication and Explanations
Effective communication is key to successful coordination. Yet, it is far from obvious what information is crucial to the task at hand, and how and when it must be shared among agents. In this talk, I first discuss how we leverage machine learning methods to generate effective communication strategies to solve hard coordination tasks. I present some pioneering real-robot experiments that demonstrate the transfer of our methods to the physical world. The learning process itself, however, remains challenging, especially in rule-dense environments. I conclude the talk by introducing how explanation engineering can be used in lieu of reward engineering to accelerate the learning process in such cases.
Amanda Prorok is an Associate Professor in the Department of Computer Science and Technology, at Cambridge University, and a Fellow of Pembroke College. Prior to joining Cambridge, she was a postdoctoral researcher at the General Robotics, Automation, Sensing and Perception (GRASP) Laboratory at the University of Pennsylvania, USA. She completed her Ph.D. at EPFL, Switzerland. She is interested in multi-agent and multi-robot systems. Her mission is to develop methods to coordinate artificially intelligent agents to achieve common goals in shared physical and virtual spaces. This research brings in methods from machine learning, planning, and control, and has numerous applications, including automated transport and logistics, intelligent infrastructure, environmental monitoring, and search & rescue.
Amanda has been honored by numerous research awards, including an ERC Starting Grant, an Amazon Research Award, the EPSRC New Investigator Award, the Isaac Newton Trust Early Career Award, and several Best Paper awards. Her Ph.D. thesis was awarded the Asea Brown Boveri (ABB) prize for the best thesis at EPFL in Computer Science. She serves as Associate Editor for IEEE Robotics and Automation Letters (R-AL) and Associate Editor for Autonomous Robots (AURO).