Distributed Reinforcement Learning of Targeted Grasping with Active Vision for Mobile Manipulators
arXiv:2007.08082
Abstract
Developing personal robots that can perform a diverse range of manipulation tasks in unstructured environments necessitates solving several challenges for robotic grasping systems. We take a step towards this broader goal by presenting the first RL-based system, to our knowledge, for a mobile manipulator that can (a) achieve targeted grasping generalizing to unseen target objects, (b) learn complex grasping strategies for cluttered scenes with occluded objects, and (c) perform active vision through its movable wrist camera to better locate objects. The system is informed of the desired target object in the form of a single, arbitrary-pose RGB image of that object, enabling the system to generalize to unseen objects without retraining. To achieve such a system, we combine several advances in deep reinforcement learning and present a large-scale distributed training system using synchronous SGD that seamlessly scales to multi-node, multi-GPU infrastructure to make rapid prototyping easier. We train and evaluate our system in a simulated environment, identify key components for improving performance, analyze its behaviors, and transfer to a real-world setup.
Accepted at IROS 2020
References in corpus (14)
- Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
- Dota 2 with Large Scale Deep Reinforcement Learning
- QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation
- Solving Rubik's Cube with a Robot Hand
- Revisiting Distributed Synchronous SGD
- Massively Parallel Methods for Deep Reinforcement Learning
- Visualizing and Understanding Atari Agents
- Distributional Reinforcement Learning with Quantile Regression
- Mechanical Search: Multi-Step Retrieval of a Target Object Occluded by Clutter
- Grasp2Vec: Learning Object Representations from Self-Supervised Grasping
- ChainerRL: A Deep Reinforcement Learning Library
- rlpyt: A Research Code Base for Deep Reinforcement Learning in PyTorch
- Robustness via Retrying: Closed-Loop Robotic Manipulation with Self-Supervised Learning
- Object Finding in Cluttered Scenes Using Interactive Perception