Toyota AI Seminar: Generating and Exploiting 3D Laser Data for Mobile Robotics

In this talk I will discuss a suite of work we are doing within the Oxford Mobile Robotics Group in exploiting and creating 3D lidar clouds for mobile robotics applications. I'll begin with the creation of useful point clouds and consider issue of sensor calibration using entropy optimisation and precision timing using statistical methods. I'll then describe some recent algorithms which exploit this 3D data beginning with a novel context aware 3D lidar compression scheme. I will conclude by describing an extension to the FABMAP appearance based mapping algorithm which exploits 3D range data and image data to offer improved performance.
Paul Newman obtained an M.Eng. in Engineering Science from Oxford University in 1995. He then undertook a Ph.D. in autonomous navigation at the Australian Center for Field Robotics, University of Sydney. In 1999 he returned to the United Kingdom to work in the commercial sub-sea navigation industry. In late 2000 he joined the Dept of Ocean Engineering at M.I.T. where as a post-doc and later a research scientist, he worked on algorithms and software for robust autonomous navigation for both land and sub-sea agents.

He is currently a Reader in Engineering Science at Oxford and Fellow of New College Oxford, heading-up the Oxford Mobile Robotics Research group. He is on the editorial board of the International Journal of Robotics Research and The Journal of Field Robotics and a EPSRC Leadership Fellow. His research interests are pretty much anything to do with mobile robot and autonomous vehicle navigation.