iwangshuo Goto Github PK

20170410

first try of github project

android_apps

Applications built on top of the rosjava android libraries.

android_core

Android libraries for rosjava

android_remocons

Android based remote controllers for 1-1 robot pairing and multi-robot concerts.

aws-robomaker-sample-application-cloudwatch

Use AWS RoboMaker and demonstrate monitoring robot health and operational metrics with AWS CloudWatch.

cadrl

Implementation of paper "Decentralized Non-communicating Multiagent Collision Avoidance with Deep Reinforcement Learning". NO LONGER MAINTAINED. CHECK OUT CrowdNav.

cadrl_ros

ROS package for dynamic obstacle avoidance for ground robots trained with deep RL

cmakepractice

《CMake实践》这本书的练习

code-vectors-artifact

Artifacts and other data for "Code Vectors: Understanding Programs Through Embedded Abstraced Symbolic Traces"

code-vectors-example

程序路径分析工具

controller

Andoid + ROS Indigo + Robot = Magic

coursera-ml-andrewng-notes

吴恩达老师的机器学习课程个人笔记

crowdnav

[ICRA19] Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learning

cs-notes

:books: Computer Science Learning Notes

d2l-zh

《动手学深度学习》

deeplearning_ai_books

deeplearning.ai（吴恩达老师的深度学习课程笔记及资源）

effective_robotics_programming_with_ros

Effective Robotics Programming with ROS

gym-collision-avoidance

haros

H(igh) A(ssurance) ROS - Static analysis of ROS application code.

hexo-theme-next

Elegant theme for Hexo.

index.ros.org

The source for index.ros.org generated by https://github.com/ros-infrastructure/rosindex

iwangshuo.github.io

kinect-gesture

基于kinect 的人体 动作识别

kobuki

Software for iClebo Kobuki

linphone4android

LinPhone是一个网络电话或者IP语音电话（VOIP），是一款遵循GPL的开源的网络视频电话系统，其主要如下：使用linphone，我们可以在互联网上随意的通信，通过语音、视频、即时文本消息。linphone使用SIP协议，是一个标准的开源网络电话系统，你能将linphone与任何基于SIP的VoIP运营商连接起来，包括我们自己开发的免费的基于SIP的Audio/Video服务器。LinPhone是一款自由软件（或者开源软件），你可以随意的下载和在LinPhone的基础上二次开发。LinPhone是可用于桌面电脑：Linux, Windows, MacOSX 以及移动设备：Android, iPhone, Blackberry.

linux0.11

Linux内核0.11完全注释V3.0配套源代码

openni_tracker

openpose

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

path-following-by-dqn

posture-and-fall-detection-system-using-3d-motion-sensors

This work presents a supervised learning approach for training a posture detection classifier, and implementing a fall detection system using the posture classification results as inputs with a Microsoft Kinect v2 sensor. The Kinect v2 skeleton tracking provides 3D depth coordinates for 25 body parts. We use these depth coordinates to extract seven features consisting of the height of the subject and six angles between certain body parts. These features are then fed into a fully connected neural network that outputs one of three considered postures for the subject: standing, sitting, or lying down. An average classification rate of over 99.30% for all three postures was achieved on test data consisting of multiple subjects where the subjects were not even facing the Kinect depth camera most of the time and were located in different locations. These results show the feasibility to classify human postures with the proposed setup independently of the location of the subject in the room and orientation to the 3D sensor.