Hsiao Ray's repositories
TsingHuaDataStructOj
mooc-清华数据结构与算法(邓俊辉) OJ习题
grid_map_navigation_planner
Grid map based navigation planner and tools
Shadow
Robot Follower implemented using ROS on iROBOT vaccum cleaner with Kinect
peopleTracker
People Detection and Tracking on RGB-D data
Potential_Field_GlobalPlanner_ROS
a simple implementation of potential field as a global planner plugin in ros
navigation
ROS Navigation stack. Code for finding where the robot is and how it can get somewhere else.
ROS
Some scripts about fundamental ROS, Slam, Movebase and people tracking
Data-structure-and-algorithm
以前学数据结构和算法的时候写的一些程序
Fuzzy-Robot
Path following mobile robot using fuzzy logic
tracker_kcf_ros
基于ros下应用深度相机的kcf追踪算法实现
zhihu-python
获取知乎内容信息，包括问题，答案，用户，收藏夹信息
turtlebot-follower
Project Repo for Turtlebot Project for ECE 6562
Turtlebot_Navigation
This project was completed on May 15, 2015. The goal of the project was to implement software system for frontier based exploration and navigation for turtlebot-like robots.
proxemics_anytimerrts
The sampling-based motion planner integrates both the SMP's RRT* with dynamic social cost map. This project could exist thanks to srl-freiburg's global planner project as well as Marina Kollmitz's human aware navigation project. I truly appreciate you guys from the bottom of my heart.
tld_turtlebot_follower
This is a ROS package, which can make the turtlebot follow an pre-selected object. The visual tracking algorithm is TLD.
tld_turtlebot_follower-release
The release package for the ROS package tld_turtlebot_follower
socially_normative_navigation
Socially normative mobile robot navigation
Temporal_Difference_Learning_Path_Planning
When born, animals and humans are thrown into an unknown world forced to use their sensory inputs for survival. As they begin to understand and develop their senses they are able to navigate and interact with their environment. The process in which we learn to do this is called reinforcement learning. This is the idea that learning comes from a series of trial and error where there exists rewards and punishments for every action. The brain naturally logs these events as experiences, and decides new actions based on past experience. An action resulting in a reward will then be higher favored than an action resulting in a punishment. Using this concept, autonomous systems, such as robots, can learn about their environment in the same way. Using simulated sensory data from ultrasonic sensors, moisture sensors, encoders, shock sensors, pressure sensors, and steepness sensors, a robotic system will be able to make decisions on how to navigate through its environment to reach a goal. The robotic system will not know the source of the data or the terrain it is navigating. Given a map of an open environment simulating an area after a natural disaster, the robot will use model-free temporal difference learning with exploration to find the best path to a goal in terms of distance, safety, and terrain navigation. Two forms of temporal difference learning will be tested; off-policy (Q-Learning) and onpolicy (Sarsa). Through experimentation with several world map sizes, it is found that the off-policy algorithm, Q-Learning, is the most reliable and efficient in terms of navigating a known map with unequal states.
TurtleBot
Turtle Bot SLAM Project with Obstacle Avoidance
srl_global_planner
The SRL_GLOBAL_PLANNER package provides an implementation of the sampling based motion planners (RRT, RGG, RRT*, Theta*-RRT) as global planner plugin for Move-base, a ROS framework
lattice_planner
The lattice_planner package provides a move_base global planner plugin for a time-bounded A* lattice planner. The planner is designed to plan time dependent, dynamically feasible navigation paths for robots with differential drive constraints. It uses a dynamic cost map which is based on the ROS costmap representation from the costmap_2d package.
HRI
Human Robot Interaction course project (robot cooking assistant with NLP)
srl_dstar_lite
ROS move_base plugin that implements the D* Lite algorithm
srl_rhcf_planner
A move_base ROS global_planner plug-in that quickly finds from a socially-informed Voronoi diagram a set of homotopy classes and generates a kinodynamic trajectory, into the best class, by using an optimal sampling-based motion planner
edge_leg_detector
ROS package for leg detection with a laser scanner
Dodger
Path planning in cluttered dynamic environments by predicting the motions of obstacles.