RoboBrain: Large-Scale Knowledge Engine for Robots

In this talk, I'll present knowledge engine, which learns and shares knowledge representations, for robots to carry out a variety of tasks. Building such an engine brings with it the challenge of dealing with multiple data modalities including symbols, natural language, haptic senses, robot trajectories, visual features and many others.

The knowledge stored in the engine comes from multiple sources including physical interactions that robots have while performing tasks (perception, planning and control) and from WWW (such as YouTube videos and WikiHow). We then discuss several applications including in computer vision, smart cars, and several robotics applications.

Ashutosh Saxena is an assistant professor in the Computer Science department at Cornell University, currently at Stanford University. His research interests include machine learning, robotics and 3D computer vision. He received his MS in 2006 and Ph.D. in 2009 from Stanford University, and his B.Tech. in 2004 from Indian Institute of Technology (IIT) Kanpur. He has also won best paper awards in 3DRR, RSS, IEEE ACE and IROS. He was named a co-chair of IEEE technical committee on robot learning, and is an associate editor of the IEEE Transactions on Robotics. He was a recipient of National Talent Scholar award in India and Google Faculty award in 2011. He was named a Alred P. Sloan Fellow in 2011, named a Microsoft Faculty Fellow in 2012, received a NSF Career award in 2013, received a Career Award at RSS 2014, and one of eight innovators in 2015 listed by Smithsonian.

Aditya Jami is the Co-Founder and CTO of Predict Effect, a startup thats building state of the art machine learning algorithms to do deep user modeling by analyzing billions of multi modal documents (Web & Social) everyday. He is also a visiting research scientist at Cornell and Stanford University where he focuses on large probabilistic robot knowledge bases and deep social learning. Previously, he was a founding member of the Cloud Solutions team at Netflix where he worked on Simian Army (Chaos Monkey), Cassandra/Priam, that are currently open sourced and used by several companies. Prior to that, he was the recipient of You Rock and Data Wizard award at Yahoo, where he worked on Data Highway, a realtime data platform that collects and analyzes 300 Billion web events (15TB) a day with a total hardware installation footprint of 500,000 nodes to power Yahoo's instant content recommendation and Behavioral ad targeting platforms. He received hisMasters in Computer Science at Stanford University under the supervision of Hector Garcia Molina. Problems he investigate are motivated by large scale multi modal data, the Web, on-line media and Knowledge bases