Isaac Gym Environments for Legged Robots

Related tags

Hardwarelegged_gym
Overview

Isaac Gym Environments for Legged Robots

This repository provides the environment used to train ANYmal (and other robots) to walk on rough terrain using NVIDIA's Isaac Gym. It includes all components needed for sim-to-real transfer: actuator network, friction & mass randomization, noisy observations and random pushes during training.
Maintainer: Nikita Rudin
Affiliation: Robotic Systems Lab, ETH Zurich
Contact: [email protected]

Useful Links

Project website: https://leggedrobotics.github.io/legged_gym/ Paper: https://arxiv.org/abs/2109.11978

Installation

  1. Create a new python virtual env with python 3.6, 3.7 or 3.8 (3.8 recommended)
  2. Install pytorch 1.10 with cuda-11.3:
    • pip3 install torch==1.10.0+cu113 torchvision==0.11.1+cu113 torchaudio==0.10.0+cu113 -f https://download.pytorch.org/whl/cu113/torch_stable.html
  3. Install Isaac Gym
    • Download and install Isaac Gym Preview 3 (Preview 2 will not work!) from https://developer.nvidia.com/isaac-gym
    • cd isaacgym_lib/python && pip install -e .
    • Try running an example python examples/1080_balls_of_solitude.py
    • For troubleshooting check docs isaacgym/docs/index.html)
  4. Install rsl_rl (PPO implementation)
  5. Install legged_gym
    • Clone this repository
    • cd legged_gym && git checkout develop && pip install -e .

CODE STRUCTURE

  1. Each environment is defined by an env file (legged_robot.py) and a config file (legged_robot_config.py). The config file contains two classes: one conatianing all the environment parameters (LeggedRobotCfg) and one for the training parameters (LeggedRobotCfgPPo).
  2. Both env and config classes use inheritance.
  3. Each non-zero reward scale specified in cfg will add a function with a corresponding name to the list of elements which will be summed to get the total reward.
  4. Tasks must be registered using task_registry.register(name, EnvClass, EnvConfig, TrainConfig). This is done in envs/__init__.py, but can also be done from outside of this repository.

Usage

  1. Train:
    python issacgym_anymal/scripts/train.py --task=anymal_c_flat
    • To run on CPU add following arguments: --sim_device=cpu, --rl_device=cpu (sim on CPU and rl on GPU is possible).
    • To run headless (no rendering) add --headless.
    • Important: To improve performance, once the training starts press v to stop the rendering. You can then enable it later to check the progress.
    • The trained policy is saved in issacgym_anymal/logs/ / _ /model_ .pt . Where and are defined in the train config.
    • The following command line arguments override the values set in the config files:
    • --task TASK: Task name.
    • --resume: Resume training from a checkpoint
    • --experiment_name EXPERIMENT_NAME: Name of the experiment to run or load.
    • --run_name RUN_NAME: Name of the run.
    • --load_run LOAD_RUN: Name of the run to load when resume=True. If -1: will load the last run.
    • --checkpoint CHECKPOINT: Saved model checkpoint number. If -1: will load the last checkpoint.
    • --num_envs NUM_ENVS: Number of environments to create.
    • --seed SEED: Random seed.
    • --max_iterations MAX_ITERATIONS: Maximum number of training iterations.
  2. Play a trained policy:
    python issacgym_anymal/scripts/play.py --task=anymal_c_flat
    • By default the loaded policy is the last model of the last run of the experiment folder.
    • Other runs/model iteration can be selected by setting load_run and checkpoint in the train config.

Adding a new environment

The base environment legged_robot implements a rough terrain locomotion task. The corresponding cfg does not specify a robot asset (URDF/ MJCF) and no reward scales.

  1. Add a new folder to envs/ with ' _config.py , which inherit from an existing environment cfgs
  2. If adding a new robot:
    • Add the corresponding assets to resourses/.
    • In cfg set the asset path, define body names, default_joint_positions and PD gains. Specify the desired train_cfg and the name of the environment (python class).
    • In train_cfg set experiment_name and run_name
  3. (If needed) implement your environment in .py, inherit from an existing environment, overwrite the desired functions and/or add your reward functions.
  4. Register your env in isaacgym_anymal/envs/__init__.py.
  5. Modify/Tune other parameters in your cfg, cfg_train as needed. To remove a reward set its scale to zero. Do not modify parameters of other envs!

Troubleshooting

  1. If you get the following error: ImportError: libpython3.8m.so.1.0: cannot open shared object file: No such file or directory, do: sudo apt install libpython3.8

Known Issues

  1. The contact forces reported by net_contact_force_tensor are unreliable when simulating on GPU with a triangle mesh terrain. A workaround is to use force sensors, but the force are propagated through the sensors of consecutive bodies resulting in an undesireable behaviour. However, for a legged robot it is possible to add sensors to the feet/end effector only and get the expected results. When using the force sensors make sure to exclude gravity from trhe reported forces with sensor_options.enable_forward_dynamics_forces. Example:
    sensor_pose = gymapi.Transform()
    for name in feet_names:
        sensor_options = gymapi.ForceSensorProperties()
        sensor_options.enable_forward_dynamics_forces = False # for example gravity
        sensor_options.enable_constraint_solver_forces = True # for example contacts
        sensor_options.use_world_frame = True # report forces in world frame (easier to get vertical components)
        index = self.gym.find_asset_rigid_body_index(robot_asset, name)
        self.gym.create_asset_force_sensor(robot_asset, index, sensor_pose, sensor_options)
    (...)

    sensor_tensor = self.gym.acquire_force_sensor_tensor(self.sim)
    self.gym.refresh_force_sensor_tensor(self.sim)
    force_sensor_readings = gymtorch.wrap_tensor(sensor_tensor)
    self.sensor_forces = force_sensor_readings.view(self.num_envs, 4, 6)[..., :3]
    (...)

    self.gym.refresh_force_sensor_tensor(self.sim)
    contact = self.sensor_forces[:, :, 2] > 1.
Owner
Robotic Systems Lab - Legged Robotics at ETH Zürich
The Robotic Systems Lab investigates the development of machines and their intelligence to operate in rough and challenging environments.
Robotic Systems Lab - Legged Robotics at ETH Zürich
Detic ros - A simple ROS wrapper for Detic instance segmentation using pre-trained dataset

Detic ros - A simple ROS wrapper for Detic instance segmentation using pre-trained dataset

Hirokazu Ishida 12 Nov 19, 2022
Python library for the Phomemo m02s bluetooth thermal printer

Phomemo M02S Python library This is a basic Python library for controlling the Phomemo M02S bluetooth thermal printer. It probably only works on Mac &

Stargirl Flowers 28 Nov 07, 2022
This is the remake of the program PYOBD. It works on Python3 and all new libraries. It was tested on Linux, Windows, and it should work on MAC too.

This is the remake of the program PYOBD. It works on Python3 and all new libraries. It was tested on Linux, Windows, and it should work on MAC too. You just need an ELM327 USB or bluetooth device and

127 Jan 06, 2023
Resmed_myair_sensors - This is a Home Assistant custom component to pull daily CPAP data from ResMed's myAir service using an undocumented API

resmed_myair This component will set up the following platforms. Platform Description sensor Show info from the myAir API. Installation Using the tool

Preston Tamkin 17 Dec 29, 2022
Python application, displaying currently played track from Spotify on OLED display connected via I2C

RaspberryPi Spotify OLED Display This application will display currently played track on SSD1306 OLED display connected to RaspberryPi. Displayed stuf

Wojciech Olech 2 Dec 30, 2021
ok-system-helper是一个简单的系统硬件的实时信息收集工具,使用python3.x开发

ok-system-helper ok-system-helper是一个简单的系统硬件的实时信息收集工具,使用python3.x开发,支持哪些硬件:CPU、内存、SWAP、磁盘、网卡流量。用户可在自己的项目中直接引入、开箱即用,或者结合flask等web框架轻松做成http接口供前端调用,亦可通过注

xlvchao 1 Feb 08, 2022
ArduinoWaterHeaterIOT - IoT Probe of a solar PV water heating system - Arduino, Python, MQTT, MySQL

ArduinoWaterHeaterIOT IoT Probe of a solar PV water heating system - Arduino, Raspberry Pi, Python, MQTT, MySQL The Arduino sends the AC and DC watts

Jacques Fourie 1 Jan 11, 2022
Event-based hardware simulation framework

An event-based multi-device simulation framework providing configuration and orchestration of complex multi-device simulations.

Diamond Light Source Controls Group 3 Feb 01, 2022
LT-OCF: Learnable-Time ODE-based Collaborative Filtering, CIKM'21

LT-OCF: Learnable-Time ODE-based Collaborative Filtering Our proposed LT-OCF Our proposed dual co-evolving ODE Setup Python environment for LT-OCF Ins

Jeongwhan Choi 15 Dec 28, 2022
Jarvis: a personal assistant which can help you to manage your system

Jarvis Jarvis is personal AI based assistant which can help you to manage stuff in your computer. This is demo but I decided to make it more better so

2 Jun 02, 2022
A dashboard for Raspberry Pi to display environmental weather data, rain radar, weather forecast, etc. written in Python

Weather Clock for Raspberry PI This project is a dashboard for Raspberry Pi to display environmental weather data, rain radar, weather forecast, etc.

Markus Geiger 1 May 01, 2022
🐱 Petkit feeder components for HomeAssistant

Petkit for HomeAssistant Installing Download and copy custom_components/xiaomi_miot folder to custom_components folder in your HomeAssistant config fo

62 Dec 29, 2022
Python script for printing to the Hanshow price-tag

This repository contains Python code for talking to the ATC_TLSR_Paper open-source firmware for the Hanshow e-paper pricetag. Installation # Clone the

12 Oct 06, 2022
Run this code to blink your ThinkPad LED with a hidden mysterious Morse code! ;)

TMorse Run this code to blink your ThinkPad LED with a hidden mysterious Morse code! ;) Compatible with python3.9+. No third-party library is required

Mahyar 2 Jul 11, 2022
Poupool is an overflow swimming pool control software

Poupool - The swimming pool controller Poupool is a swimming pool control software. It is based on Transitions, Pykka and Paho MQTT. The user interfac

Cyril Jaquier 8 Jul 18, 2022
Imbalaced Classification and Robust Semantic Segmentation

Imbalaced Classification and Robust Semantic Segmentation This repo implements two algoritms. The imbalance clibration (IC) algorithm for image classi

24 Jul 23, 2022
Control the lights of Alienware computers under GNU/Linux systems.

Before requesting support please consider that this software is not actively developed. I created it in 2014 for managing my Alienware M14X-R1 (where

rsm 111 Dec 05, 2022
BoneIO is a compact IO controller for home automation.

Project description BoneIO is a compact IO controller for home automation. Main features of this controller are Compact size (27x11x6)cm - 15 DIN modu

Maciej Krasuski 120 Nov 30, 2022
LedFx is a network based LED effect controller with support for advanced real-time audio effects

Welcome to LedFx ✨ -Making music come alive! LedFx website: https://ledfx.app/ What is LedFx? What LedFx offers is the ability to take audio input, an

786 Jan 02, 2023
PBA: Pleco Breeding Assistant

A small monitor that reports the external, fishroom and water change parameters to have suitable water parameters and induce breeding. These two features already represent 50% of the "reproductive su

Mirko Mancin 1 Jan 19, 2022