Official implementation of "Learning Forward Dynamics Model and Informed Trajectory Sampler for Safe Quadruped Navigation" (RSS 2022)

Overview

Intro

Official implementation of "Learning Forward Dynamics Model and Informed Trajectory Sampler for Safe Quadruped Navigation" Robotics:Science and Systems (RSS 2022)

[Project page] [Paper]

Dependencies

Set conda environment

conda create -n quadruped_nav python=3.8
conda activate quadruped_nav

Install torch(1.10.1), numpy(1.21.2), matplotlib, scipy, ruamel.yaml

conda install pytorch==1.10.1 torchvision==0.11.2 torchaudio==0.10.1 cudatoolkit=11.3 -c pytorch -c conda-forge
conda install numpy=1.21.2
conda install matplotlib
conda install scipy
pip install ruamel.yaml

Install wandb and login. 'wandb' is a logging system similar to 'tensorboard'.

pip install wandb
wandb login

Install required python packages to compute Dynamic Time Warping in Parallel

pip install dtw-python
pip install fastdtw
pip install joblib

Install OMPL (Open Motion Planning Library). Python binding version of OMPL is used.

Download OMPL installation script in https://ompl.kavrakilab.org/installation.html.
chmod u+x install-ompl-ubuntu.sh
./install-ompl-ubuntu.sh --python

Simulator setup

RaiSim is used. Install it following the installation guide.

Then, set up RaisimGymTorch as following.

cd /RAISIM_DIRECTORY_PATH/raisimLib
git clone [email protected]:awesomericky/complex-env-navigation.git
cd complex-env-navigation
python setup.py develop

Path setup

Configure following paths. Parts that should be configured is set with TODO: PATH_SETUP_REQUIRED flag.

  1. Project directory
    • cfg['path']['home'] in /RAISIM_DIRECTORY_PATH/raisimLib/complex-env-navigation/raisimGymTorch/env/envs/test/cfg.yaml
  2. OMPL Python binding
    • OMPL_PYBIND_PATH in /RAISIM_DIRECTORY_PATH/raisimLib/complex-env-navigation/raisimGymTorch/env/envs/train/global_planner.py

Train model

Set logging: True in /RAISIM_DIRECTORY_PATH/raisimLib/complex-env-navigation/raisimGymTorch/env/envs/train/cfg.yaml, if you want to enable wandb logging.

Train Forward Dynamics Model (FDM).

  • Click 'c' to continue when pdb stops the code
  • To quit the training, click 'Ctrl + c' to call pdb. Then click 'q'.
  • Path of the trained velocity command tracking controller should be given with -tw flag.
  • Evaluations of FDM are visualized in /RAISIM_DIRECTORY_PATH/raisimLib/complex-env-navigation/trajectory_prediction_plot.
python raisimGymTorch/env/envs/train/FDM_train.py -tw /RAISIM_DIRECTORY_PATH/raisimLib/complex-env-navigation/data/command_tracking_flat/final/full_16200.pt

Download data to train Informed Trajectory Sampler (386MB) [link]

# Unzip the downloaded zip file and move it to required path.
unzip analytic_planner_data.zip
mv analytic_planner_data /RAISIM_DIRECTORY_PATH/raisimLib/complex-env-navigation/.

Train Informed Trajectory Sampler (ITS)

  • Click 'c' to continue when pdb stops the code.
  • To quit the training, click 'Ctrl + c' to call pdb. Then click 'q'.
  • Path of the trained Forward Dynamics Model should be given with -fw flag.
python raisimGymTorch/env/envs/train/ITS_train.py -fw /RAISIM_DIRECTORY_PATH/raisimLib/complex-env-navigation/data/FDM_train/XXX/full_XXX.pt

Run demo

Configure the trained weight paths (cfg['path']['FDM'] and cfg['path']['ITS']) in /RAISIM_DIRECTORY_PATH/raisimLib/complex-env-navigation/raisimGymTorch/env/envs/test/cfg.yaml. Parts that should be configured is set with TODO: WEIGHT_PATH_SETUP_REQUIRED flag.

Open RaiSim Unity to see the visualized simulation.

Run point-goal navigation with trained weight (click 'c' to continue when pdb stops the code)

python raisimGymTorch/env/envs/test/pgn_runner.py

Run safety-remote control with trained weight (click 'c' to continue when pdb stops the code)

python raisimGymTorch/env/envs/test/src_runner.py

To quit running the demo, click 'Ctrl + c' to call pdb. Then click 'q'.

Extra notes

  • This repository is not maintained anymore. If you have a question, send an email to [email protected].
  • We don't take questions regarding installation. If you install the dependencies successfully, you can easily run this.
  • For the codes in rsc/, ANYbotics' license is applied. MIT license otherwise.
  • More details of the provided velocity command tracking controller for quadruped robots in flat terrain can be found in this paper and repository.

Cite

@INPROCEEDINGS{Kim-RSS-22, 
    AUTHOR    = {Yunho Kim AND Chanyoung Kim AND Jemin Hwangbo}, 
    TITLE     = {Learning Forward Dynamics Model and Informed Trajectory Sampler for Safe Quadruped Navigation}, 
    BOOKTITLE = {Proceedings of Robotics: Science and Systems}, 
    YEAR      = {2022}, 
    ADDRESS   = {New York, USA}, 
    MONTH     = {June}
} 
Owner
Yunho Kim
Yunho Kim
Combining Reinforcement Learning and Constraint Programming for Combinatorial Optimization

Hybrid solving process for combinatorial optimization problems Combinatorial optimization has found applications in numerous fields, from aerospace to

117 Dec 13, 2022
Si Adek Keras is software VR dangerous object detection.

Si Adek Python Keras Sistem Informasi Deteksi Benda Berbahaya Keras Python. Version 1.0 Developed by Ananda Rauf Maududi. Developed date: 24 November

Ananda Rauf 1 Dec 21, 2021
Scikit-event-correlation - Event Correlation and Forecasting over High Dimensional Streaming Sensor Data algorithms

scikit-event-correlation Event Correlation and Changing Detection Algorithm Theo

Intellia ICT 5 Oct 30, 2022
CoINN: Correlated-informed neural networks: a new machine learning framework to predict pressure drop in micro-channels

CoINN: Correlated-informed neural networks: a new machine learning framework to predict pressure drop in micro-channels Accurate pressure drop estimat

Alejandro Montanez 0 Jan 21, 2022
pytorch implementation of dftd2 & dftd3

torch-dftd pytorch implementation of dftd2 [1] & dftd3 [2, 3] Install # Install from pypi pip install torch-dftd # Install from source (for developer

33 Nov 28, 2022
A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised Learning

LABES This is the code for EMNLP 2020 paper "A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised L

17 Sep 28, 2022
The Wearables Development Toolkit - a development environment for activity recognition applications with sensor signals

Wearables Development Toolkit (WDK) The Wearables Development Toolkit (WDK) is a framework and set of tools to facilitate the iterative development of

Juan Haladjian 114 Nov 27, 2022
Using contrastive learning and OpenAI's CLIP to find good embeddings for images with lossy transformations

The official code for the paper "Inverse Problems Leveraging Pre-trained Contrastive Representations" (to appear in NeurIPS 2021).

Sriram Ravula 26 Dec 10, 2022
LF-YOLO (Lighter and Faster YOLO) is used to detect defect of X-ray weld image.

This project is based on ultralytics/yolov3. LF-YOLO (Lighter and Faster YOLO) is used to detect defect of X-ray weld image. Download $ git clone http

26 Dec 13, 2022
ICCV2021 Expert-Goal Trajectory Prediction

ICCV 2021: Where are you heading? Dynamic Trajectory Prediction with Expert Goal Examples This repository contains the code for the paper Where are yo

hz 21 Dec 12, 2022
Code for "Localization with Sampling-Argmax", NeurIPS 2021

Localization with Sampling-Argmax [Paper] [arXiv] [Project Page] Localization with Sampling-Argmax Jiefeng Li, Tong Chen, Ruiqi Shi, Yujing Lou, Yong-

JeffLi 71 Dec 17, 2022
Face2webtoon - Despite its importance, there are few previous works applying I2I translation to webtoon.

Despite its importance, there are few previous works applying I2I translation to webtoon. I collected dataset from naver webtoon 연애혁명 and tried to transfer human faces to webtoon domain.

이상윤 64 Oct 19, 2022
Pretrained Pytorch face detection (MTCNN) and recognition (InceptionResnet) models

Face Recognition Using Pytorch Python 3.7 3.6 3.5 Status This is a repository for Inception Resnet (V1) models in pytorch, pretrained on VGGFace2 and

Tim Esler 3.3k Jan 04, 2023
Tzer: TVM Implementation of "Coverage-Guided Tensor Compiler Fuzzing with Joint IR-Pass Mutation (OOPSLA'22)“.

Artifact • Reproduce Bugs • Quick Start • Installation • Extend Tzer Coverage-Guided Tensor Compiler Fuzzing with Joint IR-Pass Mutation This is the s

12 Dec 29, 2022
Lexical Substitution Framework

LexSubGen Lexical Substitution Framework This repository contains the code to reproduce the results from the paper: Arefyev Nikolay, Sheludko Boris, P

Samsung 37 Sep 15, 2022
Image Restoration Toolbox (PyTorch). Training and testing codes for DPIR, USRNet, DnCNN, FFDNet, SRMD, DPSR, BSRGAN, SwinIR

Image Restoration Toolbox (PyTorch). Training and testing codes for DPIR, USRNet, DnCNN, FFDNet, SRMD, DPSR, BSRGAN, SwinIR

Kai Zhang 2k Dec 31, 2022
Unoffical implementation about Image Super-Resolution via Iterative Refinement by Pytorch

Image Super-Resolution via Iterative Refinement Paper | Project Brief This is a unoffical implementation about Image Super-Resolution via Iterative Re

LiangWei Jiang 2.5k Jan 02, 2023
Metric learning algorithms in Python

metric-learn: Metric Learning in Python metric-learn contains efficient Python implementations of several popular supervised and weakly-supervised met

1.3k Dec 28, 2022
A deep-learning pipeline for segmentation of ambiguous microscopic images.

Welcome to Official repository of deepflash2 - a deep-learning pipeline for segmentation of ambiguous microscopic images. Quick Start in 30 seconds se

Matthias Griebel 39 Dec 19, 2022
Opinionated code formatter, just like Python's black code formatter but for Beancount

beancount-black Opinionated code formatter, just like Python's black code formatter but for Beancount Try it out online here Features MIT licensed - b

Launch Platform 16 Oct 11, 2022