Today, robotics engineers have to contend with a flood of log data that robots generate. With little warning, you can end up with thousands of rosbags and other log files. There isn’t much tooling available to manage all of this data, which causes significant friction during research and development. In this talk, we'll cover key lessons learned from productizing robots at Amazon over the last decade, and introduce a framework for processing and searching large volumes of robotics data at scale. We'll also discuss opportunities to host and share robotics datasets and algorithms for community use.
Benji Barash is the co-founder and CEO at Roboto AI, a new startup based in Seattle and Zurich focused on accelerating the search and analysis of robotics data. Prior to founding Roboto, Benji worked as an engineering leader at Amazon Robotics, and as an Entrepreneur in Residence at the Allen Institute for AI (AI2). Benji was a founding engineer on Amazon's drone delivery program in Cambridge, UK, where he led the development of large-scale simulation platforms and safety-critical autonomy algorithms. Originally from London, Benji holds a Master's degree in Computer Science from the University of Bristol.