Graph-Structured Visual Imitation
arXiv:1907.05518
Abstract
We cast visual imitation as a visual correspondence problem. Our robotic agent is rewarded when its actions result in better matching of relative spatial configurations for corresponding visual entities detected in its workspace and teacher's demonstration. We build upon recent advances in Computer Vision,such as human finger keypoint detectors, object detectors trained on-the-fly with synthetic augmentations, and point detectors supervised by viewpoint changes and learn multiple visual entity detectors for each demonstration without human annotations or robot interactions. We empirically show the proposed factorized visual representations of entities and their spatial arrangements drive successful imitation of a variety of manipulation skills within minutes, using a single demonstration and without any environment instrumentation. It is robust to background clutter and can effectively generalize across environment variations between demonstrator and imitator, greatly outperforming unstructured non-factorized full-frame CNN encodings of previous works.
arXiv comment8 pages, 3 figures, 1 table
References in corpus (11)
- Rethinking the Inception Architecture for Computer Vision
- State Representation Learning for Control: An Overview
- Graph networks as learnable physics engines for inference and control
- Universal Correspondence Network
- Dense Object Nets: Learning Dense Visual Object Descriptors By and For Robotic Manipulation
- Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics
- Third-Person Imitation Learning
- Learning to Poke by Poking: Experiential Learning of Intuitive Physics
- Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperation
- Vision-based Teleoperation of Shadow Dexterous Hand using End-to-End Deep Neural Network
- Learning Relevant Features for Manipulation Skills using Meta-Level Priors