PyRep: Bringing V-REP to Deep Robot Learning

Abstract

PyRep is a toolkit for robot learning research, built on top of the virtual robotics experimentation platform (V-REP). Through a series of modifications and additions, we have created a tailored version of V-REP built with robot learning in mind. The new PyRep toolkit offers three improvements: (1) a simple and flexible API for robot control and scene manipulation, (2) a new rendering engine, and (3) speed boosts upwards of 10,000x in comparison to the previous Python Remote API. With these improvements, we believe PyRep is the ideal toolkit to facilitate rapid prototyping of learning algorithms in the areas of reinforcement learning, imitation learning, state estimation, mapping, and computer vision.

Cited by in corpus (24)

• Open-Sourced Reinforcement Learning Environments for Surgical Robotics
• Pose Estimation for Robot Manipulators via Keypoint Optimization and Sim-to-Real Transfer
• Language-Conditioned Imitation Learning for Robot Manipulation Tasks
• Robust Policies via Mid-Level Visual Representations: An Experimental Study in Manipulation and Navigation
• A Purely-Reactive Manipulability-Maximising Motion Controller
• ACNMP: Skill Transfer and Task Extrapolation through Learning from Demonstration and Reinforcement Learning via Representation Sharing
• Traversing the Reality Gap via Simulator Tuning
• Object and Relation Centric Representations for Push Effect Prediction
• OffWorld Gym: open-access physical robotics environment for real-world reinforcement learning benchmark and research
• Towards Robotic Assembly by Predicting Robust, Precise and Task-oriented Grasps
• Ivy: Templated Deep Learning for Inter-Framework Portability
• The Logical Options Framework
• Towards Autonomous Pipeline Inspection with Hierarchical Reinforcement Learning
• Using Soft Actor-Critic for Low-Level UAV Control
• RL STaR Platform: Reinforcement Learning for Simulation based Training of Robots
• Context-aware robot control using gesture episodes
• Data-Driven Stochastic Motion Evaluation and Optimization with Image by Spatially-Aligned Temporal Encoding
• Bringing A Robot Simulator to the SCAMP Vision System
• Self-Calibrating Active Binocular Vision via Active Efficient Coding with Deep Autoencoders
• Fully-simulated Integration of Scamp5d Vision System and Robot Simulator
• Low-Dimensional State and Action Representation Learning with MDP Homomorphism Metrics
• End-to-End Egospheric Spatial Memory
• Reinforcement Learning with Time-dependent Goals for Robotic Musicians
• Towards a Sample Efficient Reinforcement Learning Pipeline for Vision Based Robotics