Abstract

Agile micro aerial vehicles will have a massive societal impact over the next decades, creating novel opportunities for large-scale precision agriculture, fast delivery of medical supplies, and disaster response, and providing new perspectives on environmental monitoring and artificial pollination. This future requires the design of lightweight and robust perception algorithms, which interpret sensor data into a coherent world representation, in the face of measurement noise and outliers, and enable on-board situational awareness and decision-making. In this talk, I present my work on lightweight and robust robot perception. I start by discussing an algorithm for fast visual-inertial navigation, which estimates the motion of the robot from visual and inertial cues, and demonstrate its use for agile flight of micro aerial vehicles. Then, I focus on robustness and show that fundamental insights from optimization and Riemannian geometry lead to the design of estimation techniques that are provably robust to large noise, providing the first certifiably correct algorithm for localization and mapping. I also discuss the challenges connected to scaling down perception to nano and pico aerial vehicles, where sensing and computation are subject to strict payload and power constraints. I argue that enabling autonomy on miniaturized platforms requires a paradigm shift in perception, sensing, and communication, and discuss how we can draw inspiration from nature in designing the next generation of flying robots.

Bio

Luca Carlone is a research scientist in the Laboratory for Information and Decision Systems at the Massachusetts Institute of Technology. Before joining MIT, he was a postdoctoral fellow at Georgia Tech (2013-2015), and a visiting researcher at the University of California Santa Barbara (2011). He got his Ph.D. from the Polytechnic University of Turin, Italy, in 2012. His research interests include nonlinear estimation, numerical and distributed optimization, computer vision and probabilistic inference applied to sensing, perception, and control of single and multi robot systems. He published more than 60 papers on international journals and conferences, including a best paper award finalist at RSS 2015 and a best paper award winner at WAFR 2016.