Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning

08/24/2021
by   Viktor Makoviychuk, et al.
19

Isaac Gym offers a high performance learning platform to train policies for wide variety of robotics tasks directly on GPU. Both physics simulation and the neural network policy training reside on GPU and communicate by directly passing data from physics buffers to PyTorch tensors without ever going through any CPU bottlenecks. This leads to blazing fast training times for complex robotics tasks on a single GPU with 2-3 orders of magnitude improvements compared to conventional RL training that uses a CPU based simulator and GPU for neural networks. We host the results and videos at <https://sites.google.com/view/isaacgym-nvidia> and isaac gym can be downloaded at <https://developer.nvidia.com/isaac-gym>.

READ FULL TEXT

Authors

page 4

page 5

page 7

page 15

page 16

page 17

page 20

page 29

10/12/2018

GPU-Accelerated Robotic Simulation for Distributed Reinforcement Learning

Most Deep Reinforcement Learning (Deep RL) algorithms require a prohibit...
11/06/2018

GPU Acceleration of an Established Solar MHD Code using OpenACC

GPU accelerators have had a notable impact on high-performance computing...
11/18/2020

ACRONYM: A Large-Scale Grasp Dataset Based on Simulation

We introduce ACRONYM, a dataset for robot grasp planning based on physic...
07/28/2020

Performance Analysis of Noise Subspace-based Narrowband Direction-of-Arrival (DOA) Estimation Algorithms on CPU and GPU

High-performance computing of array signal processing problems is a crit...
09/04/2017

FLASH: Randomized Algorithms Accelerated over CPU-GPU for Ultra-High Dimensional Similarity Search

We present FLASH ( Fast LSH Algorithm for Similarity search accelerat...
06/28/2021

Habitat 2.0: Training Home Assistants to Rearrange their Habitat

We introduce Habitat 2.0 (H2.0), a simulation platform for training virt...
05/21/2020

Signal Processing for a Reverse-GPS Wildlife Tracking System: CPU and GPU Implementation Experiences

We present robust high-performance implementations of signal-processing ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.