(Empirically) Data-Driven Robotic Manipulation

Organizers: Maria Bauza, Gilwoo Lee, Robbie Paolini, Rod Grupen, Alberto Rodriguez

Website: https://ddm2017.mit.edu/

There is a great excitement surrounding data-driven techniques for perceptual classification, inference, and motor control. These techniques come to robotic manipulation with the promise of enabling behavior with greater robustness, performance, and adaptability, as well as suggesting new representations for physical interaction. Recent excitement in the lab, however, is tempered by significant challenges faced when building practical data-driven robots. This workshop sets the focus on those challenges involved in making the data-driven approach work for robotic manipulation.

Robot manipulation is a useful "petri dish" for studying data-driven systems with significant potential impact. Hands, or end-effectors, are where the "rubber hits the road"—where robots make and break contact with the world; and where visual, tactile, and proprioceptive feedback combine to explore, model, and control interaction with the environment. In the course of such interaction, the robot is exposed to a great deal of information, in the form of data that is challenging to collect, maintain, organize, and use. On one end, we can only start capturing data with an already functional robotic system, which over time is prone to degrade and/or break. On the other end, the dynamics and perceptual feedback from robotic manipulation systems yield multi-modal data that is complicated to make sense of. The goal of this workshop is to identify the challenges that are preventing data-driven robotic manipulation from experiencing the same performance jump as other fields that have embraced it, and what can we do to overcome them.