Abstract: Perception systems constitute the backbone of any navigation stack for autonomous vehicles, from self-driving cars to autonomous drones. These systems provide functionalities such as estimating the state of the vehicle, building a map of obstacles in the surrounding environment, detecting and tracking moving objects, and attaching a semantic meaning to objects and obstacles. Contrarily to other applications, robot perception has to operate under strict resource constraints (power, computation, payload) and must provide timely estimates in order to support real-time control and decision making. In this talk, I review old and new results on real-time visual-inertial state estimation and mapping. I discuss how to obtain ultra-efficient visual-inertial navigation systems through a combination of clever algorithms and novel hardware. Moreover, I present recent and ongoing work on lightweight map representations that can provide real-time high-level understanding of the environment on resource-constrained platforms.
Bio: Luca Carlone is the Charles Stark Draper Assistant Professor in the Department of Aeronautics and Astronautics at the Massachusetts Institute of Technology, and a Principal Investigator in the Laboratory for Information & Decision Systems (LIDS). He received his PhD from the Polytechnic University of Turin in 2012. He joined LIDS as a postdoctoral associate (2015) and later as a Research Scientist (2016), after spending two years as a postdoctoral fellow at the Georgia Institute of Technology (2013-2015). His research interests include nonlinear estimation, numerical and distributed optimization, and probabilistic inference, applied to sensing, perception, and decision-making in single and multi-robot systems. His work includes seminal results on certifiably-correct algorithms for localization and mapping, as well as approaches for visual-inertial navigation and distributed mapping. He is the recipient of the 2017 Transactions on Robotics King-Sun Fu Memorial Best Paper Award, the best paper award at WAFR 2016, the best Student paper award at the 2018 Symposium on VLSI Circuits, and was best paper finalist at RSS 2015.