admin – Bullet Real-Time Physics Simulation

Kubric: a scalable dataset generator

admin — Mon, 21 Mar 2022 00:01:24 +0000

Kubric is an open-source Python framework that interfaces with PyBullet and Blender to generate photo-realistic scenes, with rich annotations, and seamlessly scales to large jobs distributed over thousands of machines, and generating TBs of data. Kubric can generate semi-realistic synthetic multi-object videos with rich annotations such as instance segmentation masks, depth maps, and optical flow.

You can find the paper here, or access the source code from github.

NeuralSim: Augmenting Differentiable Simulators with Neural Networks

admin — Fri, 21 May 2021 03:35:07 +0000

We are developing a new differentiable simulator for robotics learning, called Tiny Differentiable Simulator, or TDS. The simulator allows for hybrid simulation with neural networks. It allows different automatic differentiation backends, for forward and reverse mode gradients. TDS can be trained using Deep Reinforcement Learning, or using Gradient based optimization (for example LFBGS). In addition, the simulator can be entirely run on CUDA for fast rollouts, in combination with Augmented Random Search. This allows for 1 million simulation steps per second.

Tiny Differentiable Simulator training a policy using ARS simulation in CUDA

TDS is used in a couple of research papers, such as the ICRA 2021 NeuralSim: Augmenting Differentiable Simulators with Neural Networks”, by Eric Heiden, David Millard, Erwin Coumans, Yizhou Sheng and Gaurav S. Sukhatme.

You can checkout the source code here:
https://github.com/google-research/tiny-differentiable-simulator

PyBullet in a colab

admin — Thu, 15 Apr 2021 23:18:00 +0000

You can directly try out PyBullet in your web browser, using Google Colab. !pip install pybullet takes about 15 seconds, since there is a precompiled Python wheel.

Here is an example training colab a PyBullet Gym environment using Stable Baselines PPO:

It is also possible to use hardware OpenGL3 rendering in a Colab, through EGL. Make sure to set the MESA environment variables. Here is an example colab.

Learning Agile Robotic Locomotion Skills by Imitating Animals

admin — Thu, 24 Sep 2020 17:27:48 +0000

Our research on imitating animals won the best paper award of RSS 2020! Thanks to Jason Peng and collaborators. See the project website.

See the related repository with model-predictive-control (MPC) quadruped locomotion and the motion imitation research at https://github.com/google-research/motion_imitation

Also tagged a github release of Bullet Physics and PyBullet, both version 3.05. The release was used for our motion imitation research, and also includes various improvements for the finite-element-method (FEM) deformable simulation, by Xuchen Han and Chuyuan Fu .

https://github.com/bulletphysics/bullet3/releases

Assistive gym @ ICRA, 2020

admin — Wed, 03 Jun 2020 19:48:58 +0000

Assistive Gym leverages PyBullet for physical human-robot interaction and assistive robotics. Assistive Gym currently supports four collaborative robots and six physically assistive tasks.
It also supports learning-based control algorithms, and includes models of human motion, human preferences, robot base pose optimization, and realistic pose-dependent human joint limits

Paper Link: https://ras.papercept.net/proceedings/ICRA20/1572.pdf Zackory Erickson, Vamsee Gangaram, Ariel Kapusta, C. Karen Liu, and Charles C. Kemp, “Assistive Gym: A Physics Simulation Framework for Assistive Robotics”, IEEE International Conference on Robotics and Automation (ICRA), 2020.

Learning Agile Robotic Locomotion Skills by Imitating Animals

admin — Fri, 03 Apr 2020 19:05:49 +0000

In “Learning Agile Robotic Locomotion Skills by Imitating Animals”, we present a framework that takes a reference motion clip recorded from an animal (a dog, in this case) and uses RL to train a control policy that enables a robot to imitate the motion in the real world. By providing the system with different reference motions, we are able to train a quadruped robot to perform a diverse set of agile behaviors, ranging from fast walking gaits to dynamic hops and turns. The policies are trained primarily in simulation, and then transferred to the real world using a latent space adaptation technique that can efficiently adapt a policy using only a few minutes of data from the real robot. All simulations are performed using PyBullet.

Rapidly Adaptable Legged Robots via Evolutionary Meta-Learning

admin — Tue, 17 Mar 2020 18:59:20 +0000

Robots can use meta-learning to quickly adapt from simulation to various real world conditions.

See paper at https://arxiv.org/abs/2003.01239

Lumote game using Bullet

admin — Thu, 27 Feb 2020 05:40:27 +0000

Become the squishy glowing creature you’ve always wanted to be. Take control of the worlds inhabitants to solve puzzles. Overthrow the Mastermote! Check it out at https://store.steampowered.com/app/791240/Lumote

Alphabet ‘Everyday Robot’

admin — Fri, 22 Nov 2019 04:51:27 +0000

Check out the Wired article about the Alphabet ‘Everyday Robot’.

PyBullet and Bullet Physics is used in the collaboration, as discussed in this “Speeding up robot learning by 100x with simulation” paper and described in those sim-to-real slides and the “Challenges of Self-Supervision via Interaction in Robotics” slides.

Facebook Habitat v0.1.3 adds Bullet Physics

admin — Fri, 22 Nov 2019 02:46:52 +0000

Facebook AI Habitat is a new open source simulation platform created by Facebook AI that’s designed to train embodied agents (such as virtual robots) in photo-realistic 3D environments. The latest version adds Bullet Physics.

The github repo is here: https://github.com/facebookresearch/habitat-sim

Also check the online demo (no physics): aihabitat.org/demo