SRBA-SLAM

Section: Mobile Robot Programming Toolkit - MRPT (1)
 

NAME

srba-slam - A demo program for Relative Bundle Adjustment (RBA)  

SYNOPSIS

srba-slam --help

srba-slam --list-problems

This graphical application allows creating models of robotic manipulators by introducing the corresponding Denavit-Hartenberg (DH) parameters. It's a useful tool for teaching and learning the basics of robotic arm kinematics.

A GUI demonstrating the holonomic navigation algorithms implemented in mrpt-reactivenav.

This program allows testing, learning and tuning these algorithms:

• VFF (Virtual Force Field)
• ND (Nearness Diagram)

Example video:

This program takes a simplemap as input, generates one or several metric maps from its observations and poses, and dumps the map representations to individual files.

(Write me!)

1. Description

kinect-stereo-calib is a program for: 

1. Interactive calibration of the intrinsic and extrinsic parameters of Kinect sensors with a checkerboard.
2. Calibration of arbitrary stereo cameras, from images already grabbed by the user. It supports cameras of dissimilar resolutions, any baseline and any arbitrary rotation between cameras, etc. 

A custom implementation of a Levenberg-Marquartd optimizer has been written in C++, which also provides as output the uncertainty of each estimated parameter (its underlying mathematical details will be reported in a document, to be linked here).

1. Description

This GUI application allows you to closely analyze what has happened during a mobile robot navigation: all the sensed obstacles at each time step, the motion direction decided by the reactive navigator, etc. (see screenshot).

It can also export a MATLAB script for generating high-quality graphs with the robot trajectory (the robot shape is rotated all along the path according to the path) and the superposition of all the point clouds of detected obstacles:

Description:

The program track-video-features demonstrates live detection and tracking of features in a video stream. 

To invoke it, just type from the console:

$ track-video-features

and a GUI dialog will ask you to pick the video source (among video files, rawlogs, live firewire or USB cameras, a Kinect sensor, etc.). Alternatively, use:

$ track-video-features  <DATASET.rawlog>
$ track-video-features  <video_file.{avi/mpg/mp4/flv}>