Wednesday, November 23, 2016 - 4:30pm
Event Calendar Category
LIDS & Stats Tea
Building and Room Number
Localization and mapping are the backbone of many robotics applications including self-driving cars and autonomous drones. In this talk I discuss a Maximum Likelihood formulation of robot Simultaneous Localization and Mapping (SLAM). While the resulting estimation problem is NP-hard, I show how to compute a set of estimates that contains the maximum likelihood solution with high probability. The derivation involves a nice mix of probabilistic inference, geometry, graph theory, and nonlinear optimization, and assumes no prior knowledge about robotics.
This is a joint work with Andrea Censi.