Learning Navigation Subroutines from Egocentric Videos

Abstract

Planning at a higher level of abstraction instead of low level torques improves the sample efficiency in reinforcement learning, and computational efficiency in classical planning. We propose a method to learn such hierarchical abstractions, or subroutines from egocentric video data of experts performing tasks. We learn a self-supervised inverse model on small amounts of random interaction data to pseudo-label the expert egocentric videos with agent actions. Visuomotor subroutines are acquired from these pseudo-labeled videos by learning a latent intent-conditioned policy that predicts the inferred pseudo-actions from the corresponding image observations. We demonstrate our proposed approach in context of navigation, and show that we can successfully learn consistent and diverse visuomotor subroutines from passive egocentric videos. We demonstrate the utility of our acquired visuomotor subroutines by using them as is for exploration, and as sub-policies in a hierarchical RL framework for reaching point goals and semantic goals. We also demonstrate behavior of our subroutines in the real world, by deploying them on a real robotic platform. Project website: https://ashishkumar1993.github.io/subroutines/.

References in corpus (12)

• Adam: A Method for Stochastic Optimization
• Categorical Reparameterization with Gumbel-Softmax
• Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
• DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills
• On Evaluation of Embodied Navigation Agents
• Learning to Navigate in Complex Environments
• Matterport3D: Learning from RGB-D Data in Indoor Environments
• One-Shot Visual Imitation Learning via Meta-Learning
• One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning
• Imitating Latent Policies from Observation
• PyRobot: An Open-source Robotics Framework for Research and Benchmarking
• Visual Memory for Robust Path Following

Cited by in corpus (4)

• OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning
• AutoPreview: A Framework for Autopilot Behavior Understanding
• Zero-shot Imitation Learning from Demonstrations for Legged Robot Visual Navigation
• Feudal Steering: Hierarchical Learning for Steering Angle Prediction