A 3D Dense mapping backend library of SLAM based on taichi-Lang designed for the aerial swarm.

Overview

TaichiSLAM

This project is a 3D Dense mapping backend library of SLAM based Taichi-Lang, designed for the aerial swarm.

Intro

Taichi is an efficient domain-specific language (DSL) designed for computer graphics (CG), which can be adopted for high-performance computing on mobile devices. Thanks to the connection between CG and robotics, we can adopt this powerful tool to accelerate the development of robotics algorithms.

In this project, I am trying to take advantages of Taichi, including parallel optimization, sparse computing, advanced data structures and CUDA acceleration. The original purpose of this project is to reproduce dense mapping papers, including Octomap, Voxblox, Voxgraph etc.

Note: This project is only backend of 3d dense mapping. For full SLAM features including real-time state estimation, pose graph optimization, depth generation, please take a look on VINS and my fisheye fork of VINS.

Demos

Octomap/Occupy map at different accuacy: drawing drawing drawing

Truncated signed distance function (TSDF): Surface reconstruct by TSDF (not refined) Occupy map and slice of original TSDF

Usage

Install taichi via pip

pip install taichi

Download taichi_three and TaichiSlAM to your dev folder and add them to PYTHONPATH

git clone https://github.com/taichi-dev/taichi_three
git clone https://github.com/xuhao1/TaichiSLAM

echo export PYTHONPATH=`pwd`/taichi_three:`pwd`/TaichiSLAM:\$PYTHONPATH >> ~/.bashrc
#Or if using zshrc
echo export PYTHONPATH=`pwd`/taichi_three:`pwd`/TaichiSLAM:\$PYTHONPATH >> ~/.zshrc

Download cow_and_lady_dataset from voxblox.

Running TaichiSLAM octomap demo

python examples/TaichiSLAM_demo.py -b ~/pathto/your/bag/cow_and_lady_dataset.bag

TSDF(Voxblox)

python examples/TaichiSLAM_demo.py -m esdf -b ~/data/voxblox/cow_and_lady_dataset.bag

Use - and = key to change accuacy. Mouse to rotate the map. -h to get more help.

usage: TaichiSLAM_demo.py [-h] [-r RESOLUTION RESOLUTION] [-m METHOD] [-c] [-t] [--rviz] [-p MAX_DISP_PARTICLES] [-b BAGPATH] [-o OCCUPY_THRES] [-s MAP_SIZE MAP_SIZE] [--blk BLK]
                          [-v VOXEL_SIZE] [-K K] [-f] [--record]

Taichi slam fast demo

optional arguments:
  -h, --help            show this help message and exit
  -r RESOLUTION RESOLUTION, --resolution RESOLUTION RESOLUTION
                        display resolution
  -m METHOD, --method METHOD
                        dense mapping method: octo/esdf
  -c, --cuda            enable cuda acceleration if applicable
  -t, --texture-enabled
                        showing the point cloud's texture
  --rviz                output to rviz
  -p MAX_DISP_PARTICLES, --max-disp-particles MAX_DISP_PARTICLES
                        max output voxels
  -b BAGPATH, --bagpath BAGPATH
                        path of bag
  -o OCCUPY_THRES, --occupy-thres OCCUPY_THRES
                        thresold for occupy
  -s MAP_SIZE MAP_SIZE, --map-size MAP_SIZE MAP_SIZE
                        size of map xy,z in meter
  --blk BLK             block size of esdf, if blk==1; then dense
  -v VOXEL_SIZE, --voxel-size VOXEL_SIZE
                        size of voxel
  -K K                  division each axis of octomap, when K>2, octomap will be K**3-map
  -f, --rendering-final
                        only rendering the final state
  --record              record to C code

Roadmap

Paper Reproduction

  • Octomap
  • Voxblox
  • Voxgraph

Features

Mapping

  • Octotree occupancy map
  • TSDF
  • Incremental ESDF
  • Submap
  • Loop Detection

MISC

  • ROS/RVIZ/rosbag interface
  • 3D occupancy map visuallizer
  • 3D TSDF/ESDF map visuallizer
  • Export to C/C++
  • Benchmark

Know issue

Memory issue on ESDF generation, debugging...

LICENSE

LGPL

Owner
XuHao
PhD student @ HKUST.UAV http://www.xuhao1.me Check my swarm projects on https://github.com/HKUST-Swarm
XuHao
Hyperbolic Hierarchical Clustering.

Hyperbolic Hierarchical Clustering (HypHC) This code is the official PyTorch implementation of the NeurIPS 2020 paper: From Trees to Continuous Embedd

HazyResearch 154 Dec 15, 2022
Playing around with FastAPI and streamlit to create a YoloV5 object detector

FastAPI-Streamlit-based-YoloV5-detector Playing around with FastAPI and streamlit to create a YoloV5 object detector It turns out that a User Interfac

2 Jan 20, 2022
I decide to sync up this repo and self-critical.pytorch. (The old master is in old master branch for archive)

An Image Captioning codebase This is a codebase for image captioning research. It supports: Self critical training from Self-critical Sequence Trainin

Ruotian(RT) Luo 1.3k Dec 31, 2022
Jittor Medical Segmentation Lib -- The assignment of Pattern Recognition course (2021 Spring) in Tsinghua University

THU模式识别2021春 -- Jittor 医学图像分割 模型列表 本仓库收录了课程作业中同学们采用jittor框架实现的如下模型: UNet SegNet DeepLab V2 DANet EANet HarDNet及其改动HarDNet_alter PSPNet OCNet OCRNet DL

48 Dec 26, 2022
CUP-DNN is a deep neural network model used to predict tissues of origin for cancers of unknown of primary.

CUP-DNN CUP-DNN is a deep neural network model used to predict tissues of origin for cancers of unknown of primary. The model was trained on the expre

1 Oct 27, 2021
This repository provides the code for MedViLL(Medical Vision Language Learner).

MedViLL This repository provides the code for MedViLL(Medical Vision Language Learner). Our proposed architecture MedViLL is a single BERT-based model

SuperSuperMoon 39 Jan 05, 2023
Local Attention - Flax module for Jax

Local Attention - Flax Autoregressive Local Attention - Flax module for Jax Install $ pip install local-attention-flax Usage from jax import random fr

Phil Wang 16 Jun 16, 2022
Keras Realtime Multi-Person Pose Estimation - Keras version of Realtime Multi-Person Pose Estimation project

This repository has become incompatible with the latest and recommended version of Tensorflow 2.0 Instead of refactoring this code painfully, I create

M Faber 769 Dec 08, 2022
Embeddinghub is a database built for machine learning embeddings.

Embeddinghub is a database built for machine learning embeddings.

Featureform 1.2k Jan 01, 2023
IndoNLI: A Natural Language Inference Dataset for Indonesian

IndoNLI: A Natural Language Inference Dataset for Indonesian This is a repository for data and code accompanying our EMNLP 2021 paper "IndoNLI: A Natu

15 Feb 10, 2022
OpenFed: A Comprehensive and Versatile Open-Source Federated Learning Framework

OpenFed: A Comprehensive and Versatile Open-Source Federated Learning Framework Introduction OpenFed is a foundational library for federated learning

25 Dec 12, 2022
GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond

GCNet for Object Detection By Yue Cao, Jiarui Xu, Stephen Lin, Fangyun Wei, Han Hu. This repo is a official implementation of "GCNet: Non-local Networ

Jerry Jiarui XU 1.1k Dec 29, 2022
A Parameter-free Deep Embedded Clustering Method for Single-cell RNA-seq Data

A Parameter-free Deep Embedded Clustering Method for Single-cell RNA-seq Data Overview Clustering analysis is widely utilized in single-cell RNA-seque

AI-Biomed @NSCC-gz 3 May 08, 2022
Data, notebooks, and articles associated with the RSNA AI Deep Learning Lab at RSNA 2021

RSNA AI Deep Learning Lab 2021 Intro Welcome Deep Learners! This document provides all the information you need to participate in the RSNA AI Deep Lea

RSNA 65 Dec 16, 2022
Layer 7 DDoS Panel with Cloudflare Bypass ( UAM, CAPTCHA, BFM, etc.. )

Blood Deluxe DDoS DDoS Attack Panel includes CloudFlare Bypass (UAM, CAPTCHA, BFM, etc..)(It works intermittently. Working on it) Don't attack any web

272 Nov 01, 2022
Six - a Python 2 and 3 compatibility library

Six is a Python 2 and 3 compatibility library. It provides utility functions for smoothing over the differences between the Python versions with the g

Benjamin Peterson 919 Dec 28, 2022
LSTM-VAE Implementation and Relevant Evaluations

LSTM-VAE Implementation and Relevant Evaluations Before using any file in this repository, please create two directories under the root directory name

Lan Zhang 5 Oct 08, 2022
Interactive dimensionality reduction for large datasets

BlosSOM 🌼 BlosSOM is a graphical environment for running semi-supervised dimensionality reduction with EmbedSOM. You can use it to explore multidimen

19 Dec 14, 2022
Official repository for the NeurIPS 2021 paper Get Fooled for the Right Reason: Improving Adversarial Robustness through a Teacher-guided curriculum Learning Approach

Get Fooled for the Right Reason Official repository for the NeurIPS 2021 paper Get Fooled for the Right Reason: Improving Adversarial Robustness throu

Sowrya Gali 1 Apr 25, 2022
Reinforcement Learning Theory Book (rus)

Reinforcement Learning Theory Book (rus)

qbrick 206 Nov 27, 2022