Zero-shot Imitation Learning from Demonstrations for Legged Robot Visual Navigation
Authors:
- 1 May 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 679-685
Abstract
Imitation learning is a popular approach for training effective visual navigation policies. However, collecting expert demonstrations for legged robots is challenging as these robots can be hard to control, move slowly, and cannot operate continuously for long periods of time. In this work, we propose a zero-shot imitation learning framework for training a goal-driven visual navigation policy on a legged robot from human demonstrations (third-person perspective), allowing for high-quality navigation and cost-effective data collection. However, imitation learning from third-person demonstrations raises unique challenges. First, these demonstrations are captured from different camera perspectives, which we address via a feature disentanglement network (FDN) that extracts perspective-invariant state features. Second, as transition dynamics vary between systems, we reconstruct missing action labels by either building an inverse model of the robot’s dynamics in the feature space and applying it to the human demonstrations or developing a Graphic User Interface (GUI) to label human demonstrations. To train a navigation policy we use a model-based imitation learning approach with FDN and action-labeled human demonstrations. We show that our framework can learn an effective policy for a legged robot, Laikago, from human demonstrations in both simulated and real-world environments. Our approach is zero-shot as the robot never navigates the same paths during training as those at testing time. We justify our framework by performing a comparative study.Keywords
All Related Versions
This publication has 22 references indexed in Scilit:
- Cognitive Mapping and Planning for Visual Navigation2017
- Target-driven visual navigation in indoor scenes using deep reinforcement learning2017
- DeepMPC: Learning Deep Latent Features for Model Predictive Control2015
- Dense visual SLAM for RGB-D cameras2013
- Google Street View: Capturing the World at Street LevelComputer, 2010
- View-based MapsThe International Journal of Robotics Research, 2010
- Visual Navigation for Mobile Robots: A SurveyJournal of Intelligent & Robotic Systems, 2008
- Optical Flow Aided Motion Estimation for Legged Locomotion2006
- Robust Estimation of a Location Parameter1992
- A note on two problems in connexion with graphsNumerische Mathematik, 1959