Machine Learning for Robotic Manipulation

Abstract

The past decade has witnessed the tremendous successes of machine learning techniques in the supervised learning paradigm, where there is a clear demarcation between training and testing. In the supervised learning paradigm, learning is inherently passive, seeking to distill human-provided supervision in large-scale datasets into high capacity models. Following these successes, machine learning researchers have looked beyond this paradigm and became interested in tasks that are more dynamic. To them, robotics serve as an excellent test-bed, for the challenges of robotics break many of the assumptions that made supervised learning successful. Out of the many different areas within robotics, robotic manipulation has become a favorite area for researchers to demonstrate new algorithms because of the vast numbers of possible applications and its highly dynamical and complex nature. This document surveys recent robotics conferences and identifies the major trends with which machine learning techniques have been applied to the challenges of robotic manipulation.

Review paper written for UCSD PhD Research Exam

References in corpus (18)

• Solving Rubik's Cube with a Robot Hand
• Deep Dynamics Models for Learning Dexterous Manipulation
• SoftGym: Benchmarking Deep Reinforcement Learning for Deformable Object Manipulation
• S4G: Amodal Single-view Single-Shot SE(3) Grasp Detection in Cluttered Scenes
• Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updates
• Better Exploration with Optimistic Actor-Critic
• Visual Imitation Made Easy
• Towards Practical Multi-Object Manipulation using Relational Reinforcement Learning
• Learning 3D Dynamic Scene Representations for Robot Manipulation
• Towards Learning to Detect and Predict Contact Events on Vision-based Tactile Sensors
• 3D-OES: Viewpoint-Invariant Object-Factorized Environment Simulators
• Learning Object Manipulation Skills via Approximate State Estimation from Real Videos
• Exploratory Grasping: Asymptotically Optimal Algorithms for Grasping Challenging Polyhedral Objects
• MAT: Multi-Fingered Adaptive Tactile Grasping via Deep Reinforcement Learning
• DexPilot: Vision Based Teleoperation of Dexterous Robotic Hand-Arm System
• Physics-Based Dexterous Manipulations with Estimated Hand Poses and Residual Reinforcement Learning
• A Long Horizon Planning Framework for Manipulating Rigid Pointcloud Objects
• Robot Object Retrieval with Contextual Natural Language Queries