forrest-z Goto Github PK

low_speed_global_path

Global path planning in structured environments.

lpastar_algorithm

lpslam

Image readout, processing and SLAM library

lqr_learning

lrm_carina

CaRINA I ROS packages

lsd_slam

LSD-SLAM

lslam

lsm

Lightweight Shared Memory Communications and Marshalling

m-explore

ROS packages for multi robot exploration

machine-learning-yearning-cn

Machine Learning Yearning 中文版 - 《机器学习训练秘籍》 - Andrew Ng 著

manda_coverage

ROS port of Damian Manda's MOOS based sonar coverage based path planner. https://github.com/mandad/moos-ivp-manda

manfred_ros_stack

Repository that contains a whole stack of ROS packages for the mobile manipulator MANFRED (UC3M)

maoris

Cutting most types of maps in smaller more meaningful bits.

map-fusion

Fusion multiple imperfect maps from multiple robots using SLAM, and produce a combined/adjusted final map.

map_matcher

map_mux

ROS Package for Map Multiplexer to support multi level traversal

mapeditor

mapf

Some Multi-Agent Path Planning algorithms

mapstogazebo

mapviz

Modular ROS visualization tool for 2D data.

marine-farm-cpp

Coverage path planning for an underwater robot monitoring an algae farm

marine_radar_layer

ROS plugin for costmap_2d that converts marine radar data into a costmap.

marker-based-slam

SPM-SLAM (improved)

mars_mapping

mas_domestic_robotics

Robot-independent ROS packages for domestic applications

mas_perception_libs

maskor_navigation

maskor navigation stack based on sbpl lattice planner

master_thesis

Source files generated during the development of my master research project.

master_thesis-1

Master Thesis about Coverage Path Planning with Genetic Algorithms.

master_thesis_local_planning_algorithms_in_ros

The main goal of this work is to compare several local planning algorithms (planners). The assumption is to compare, two algorithms which are already implemented in ROS environment and two selected motion planning algorithms. Based on the performed research of the available motion planning approaches, two algorithms have been selected, Potential field based algorithm and BUG0 algorithm (Chapters 2-3). In order to achieve the main goal of this master thesis, the whole test environment based on ROS has been created. The Gazebo2 simulator and the Pioneer 3-DX robot model have been used in that order. The Gazebo2 simulator and the robot model have been configured with the ROS environment compatibility (Chapter 4). Selected algorithms have been implemented in Python 2.7 programming language. Implemented algorithms and ROS algorithms have been configured with previously created test environment (Chapters 5-6). The robot working area became the rectangular building wit dimensions, 100x30[m]. About 40 obstacles, with different size, have been created in the building (Chapter 7.1). Next, the tests have been performed, in the prepared working area, in order to obtain the optimal parameters sets for each algorithm.