Recent years have seen impressive progress in robot perception, including accurate visual-inertial odometry, dense metric reconstruction, and object recognition in real time. Surprisingly, however, most existing approaches to simultaneous localization and mapping (SLAM) rely on low-level geometric features and do not take advantage of object-level information. This talk will focus on a unifying view of geometry, semantics, and data association in SLAM. A major contribution of our approach is the use of structured object-models to build meaningful maps online and probabilistic data association that avoids making hard, potentially wrong associations between semantic features and objects in ambiguous environments. We show that the complexity of incorporating probabilistic data association in SLAM is equivalent to computing matrix permanents. Finally, we will consider the active SLAM problem in which a team of robots aims to build a rich environment model autonomously. This problem offers promising applications in environmental monitoring, search and rescue, security and surveillance, and precision agriculture. We will discuss how to manage the complexity of active SLAM with respect to long planning horizons and large robot teams. These results lead to computationally scalable, non-myopic algorithms with quantified performance for exploration and autonomous mapping. Nikolay A. Atanasov Assistant Professor Department of Electrical and Computer Engineering University of California, San Diego To ask the speaker a question, click on the speech bubble icon in the lower right hand corner and type in the question in the window that pops up. The question will be sent directly to us. Please note that there is a little bit of a delay when streaming. What participants see is a few minutes behind what is happening at our end. The longer we stream, the greater the delay may become so the questions submitted at the very end may not reach us in time. The best way to get the questions answered is to send them as they come up.