Learn More
We present a novel vision-based grasp point detection algorithm that can reliably detect the corners of a piece of cloth, using only geometric cues that are robust to variation in texture. Furthermore, we demonstrate the effectiveness of our algorithm in the context of folding a towel using a general-purpose two-armed mobile robotic platform without the use(More)
We propose a new developmental approach to goalbased imitation learning that allows a robot to: (1) learn probabilistic models of actions through self-discovery and experience, (2) utilize these learned models for inferring the goals of human demonstrations, and (3) perform goal-based imitation for humanrobot collaboration. Our approach is based on(More)
Programmers receive feedback about program correctness in several ways. The most common static feedback is typechecking: if a program typechecks successfully, then all program executions are guaranteed to be free of certain classes of errors. Dynamic feedback is obtained by running a program and observing the output of a single program execution.(More)
  • 1