Learning One-Shot Imitation From Humans Without Humans
- 2 March 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 5 (2) , 3533-3539
Abstract
Humans can naturally learn to execute a new task by seeing it performed by other individuals once, and then reproduce it in a variety of configurations. Endowing robots with this ability of imitating humans from third person is a very immediate and natural way of teaching new tasks. Only recently, through meta-learning, there have been successful attempts to one-shot imitation learning from humans; however, these approaches require a lot of human resources to collect the data in the real world to train the robot. But is there a way to remove the need for real world human demonstrations during training? We show that with Task-Embedded Control Networks, we can infer control polices by embedding human demonstrations that can condition a control policy and achieve one-shot imitation learning. Importantly, we do not use a real human arm to supply demonstrations during training, but instead leverage domain randomisation in an application that has not been seen before: sim-to-real transfer on humans. Upon evaluating our approach on pushing and placing tasks in both simulation and in the real world, we show that in comparison to a system that was trained on real-world data we are able to achieve similar results by utilising only simulation data. Videos can be found here: https://sites.google.com/view/tecnets-humans.Keywords
All Related Versions
Funding Information
- Dyson Technology Ltd
This publication has 15 references indexed in Scilit:
- Domain randomization for transferring deep neural networks from simulation to the real world2017
- Transferring skills to humanoid robots by extracting semantic representations from observations of human activitiesArtificial Intelligence, 2017
- High precision grasp pose detection in dense clutter2016
- A syntactic approach to robot imitation learning using probabilistic activity grammarsRobotics and Autonomous Systems, 2013
- Trajectories and keyframes for kinesthetic teaching2012
- Online movement adaptation based on previous sensor experiences2011
- Learning Actions from ObservationsIEEE Robotics & Automation Magazine, 2010
- Teaching a Humanoid Robot to Recognize and Reproduce Social Cues2006
- Teaching and learning of robot tasks via observation of human performanceRobotics and Autonomous Systems, 2004
- Apprenticeship learning via inverse reinforcement learning2004