Synthetically Trained Neural Networks for Learning Human-Readable Plans from Real-World Demonstrations
Authors:
- 1 May 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Abstract
We present a system to infer and execute a human-readable program from a real-world demonstration. The system consists of a series of neural networks to perform perception, program generation, and program execution. Leveraging convolutional pose machines, the perception network reliably detects the bounding cuboids of objects in real images even when severely occluded, after training only on synthetic images using domain randomization. To increase the applicability of the perception network to new scenarios, the network is formulated to predict in image space rather than in world space. Additional networks detect relationships between objects, generate plans, and determine actions to reproduce a real-world demonstration. The networks are trained entirely in simulation, and the system is tested in the real world on the pick-and-place problem of stacking colored cubes using a Baxter robot.Keywords
All Related Versions
This publication has 4 references indexed in Scilit:
- Temporal Grounding Graphs for Language Understanding with Accrued Visual-Linguistic Context2017
- Articulated Human Detection with Flexible Mixtures of PartsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Apprenticeship learning via inverse reinforcement learning2004
- Efficient Training of Artificial Neural Networks for Autonomous NavigationNeural Computation, 1991