Visual Imitation Made Easy

Abstract

Visual imitation learning provides a framework for learning complex manipulation behaviors by leveraging human demonstrations. However, current interfaces for imitation such as kinesthetic teaching or teleoperation prohibitively restrict our ability to efficiently collect large-scale data in the wild. Obtaining such diverse demonstration data is paramount for the generalization of learned skills to novel scenarios. In this work, we present an alternate interface for imitation that simplifies the data collection process while allowing for easy transfer to robots. We use commercially available reacher-grabber assistive tools both as a data collection device and as the robot's end-effector. To extract action information from these visual demonstrations, we use off-the-shelf Structure from Motion (SfM) techniques in addition to training a finger detection network. We experimentally evaluate on two challenging tasks: non-prehensile pushing and prehensile stacking, with 1000 diverse demonstrations for each task. For both tasks, we use standard behavior cloning to learn executable policies from the previously collected offline demonstrations. To improve learning performance, we employ a variety of data augmentations and provide an extensive analysis of its effects. Finally, we demonstrate the utility of our interface by evaluating on real robotic scenarios with previously unseen objects and achieve a 87% success rate on pushing and a 62% success rate on stacking. Robot videos are available at https://dhiraj100892.github.io/Visual-Imitation-Made-Easy.

References in corpus (9)

• A Simple Framework for Contrastive Learning of Visual Representations
• End to End Learning for Self-Driving Cars
• Unsupervised Data Augmentation for Consistency Training
• Reinforcement Learning with Augmented Data
• Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules
• Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels
• Reinforcement and Imitation Learning for Diverse Visuomotor Skills
• Robot Learning in Homes: Improving Generalization and Reducing Dataset Bias
• Multiple Interactions Made Easy (MIME): Large Scale Demonstrations Data for Imitation

Cited by in corpus (10)

• What Matters in Learning from Offline Human Demonstrations for Robot Manipulation
• Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning
• Reinforcement Learning with Prototypical Representations
• Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation
• Goal-Auxiliary Actor-Critic for 6D Robotic Grasping with Point Clouds
• Learning Visual Robotic Control Efficiently with Contrastive Pre-training and Data Augmentation
• A Workflow for Offline Model-Free Robotic Reinforcement Learning
• Machine Learning for Robotic Manipulation
• Back to Reality for Imitation Learning
• Single RGB-D Camera Teleoperation for General Robotic Manipulation