Department of Computer, Control and Management Engineering

Making future autonomous robots capable of accomplishing human-scale  manipulation tasks requires us to equip them with knowledge and  reasoning mechanisms.  We propose openEASE, a remote knowledge  representation and processing service that aims at facilitating  these capabilities. openEASE provides its users with unprecedented  access to knowledge of leading-edge autonomous robotic agents. It  also provides the representational infrastructure to make  inhomogeneous experience data from robots and human manipulation  episodes semantically accessible, as well as a suite of software tools that  enable researchers and robots to interpret, analyze, visualize, and  learn from the experience data.  Using openEASE users can retrieve  the memorized experiences of manipulation episodes and ask queries  regarding to what the robot saw, reasoned, and did as well as how  the robot did it, why, and what effects it caused.