Frantisek Duchon

RGB-D map for robot navigation

In this paper we present an algorithm for 3D map generation with an RGB-D sensor. The purpose of the generated map is to improve the navigation and localization abilities of a mobile robot. Single RGB-D frames were captured and a complex 3D representation was created using simple geometric transformations.

Real-time path planning for the robot in known environment

This article deals with path planning algorithms based on known representation of the environment. In terms of such planning choice of suitable environment representation is important. The introduction of this article is dedicated to this issue. The main body is concerned about the path planning algorithms. Several algorithms are described, verified and compared. Key contribution of this article is a comparison of these algorithms and their analysis of the suitability for various applications in mobile robotics.

Sensoric subsystem of automated guided vehicle: TCP communication between SIMATIC S7 PLC and Arduino

The cheap work with high precision is very necessary in industry for a long time. Research in robotics gives us opportunity for development of automatically guided vehicle controlled by PLC, which can be easily used for supplement transport inside factory, or even for human transport. Main aim of this work is to show, how to replace expensive industrial sensors with integrated communication interface by simple cheap open-source technology. Our solution is focused on TCP communication between Arduino and PLC. The Arduino is extended to Ethernet shield. It makes possibility to connect third-party devices to PLC and save I/O PLC modules. The Arduino pre-process data from ultrasonic and line-following sensors and combine them into one data packet which is send over the network to PLC server.

Using Octree Maps and RGBD Cameras to Perform Mapping and A* Navigation

Ability to explore unknown environments and ability to successfully navigate in these environments are two key abilities of any truly autonomous mobile robot. In this article, an efficient implementation of mapping and navigation using only RGBD cameras is presented. The map created by Visual SLAM techniques is converted into Octree structure, and successful A* Navigation between two points in 3D is performed. The created mapping system is able to operate in real-time even on small mobile robot and can be easily extended with new state-of-the art techniques. Proposed way of octree encoding, due to its minimum storage requirements, enables efficient distribution of map between multiple robots over the network. Presented path-planning method with its optimizations runs in sufficient time even in higher resolution maps.

Hardware and Software Realization of EDSD for Acupuncture Research and Practice

Traditional acupuncture as a diagnostic and therapeutic method has been known in China for more than 3000 years. Electrodermal screening tests (EDSTs) and electrodermal screening devices (EDSDs) that are based on the knowledge derived from traditional Chinese medicine appeared in the 1950s. This article deals with design, development and realization of such a device. The design considers the principles of two widely used EDSTs and modern trends in the field of electronics and data management. A computer program with simple user interface that provides graphic evaluation and intercomparison of measured data are presented. The designed system is suitable not only for acupuncture research but also for ordinary acupuncture diagnostics.

3D map reconstruction with sensor kinect: Searching for solution applicable to small mobile robots

Although it is relatively easy to equip mobile robot with Kinect sensor, implementation of mapping algorithm can be non trivial. In this article, we describe sensor device, robot map formats and two main approaches to 3D reconstruction, problem closely connected to SLAM mapping problem with Kinect sensor. We experimentally evaluate reference implementations of both algorithms, compare their results and discuss published and possible improvements of both approaches.

Homogenous multi-robot system for mapping of unknown environment

Aim of this article is to design and to implement autonomous multi-agent system, which is used for effective mapping of unknown environment. Proposed system is compared with single mapping robot. Robots used only simple systems such as odometry and gyro-odometry for their localization. Obstacles are detected by bumpers and IR sensors. System is controlled by superior server and each agent communicates with server by TCP/IP protocol. Activity of each agent is coordinated by server and the generated map is stored in MySQL database. Navigation of each agent is implemented in two levels - local level (obstacle avoidance) and global level (environment examination). System was verified with real robots - several iRobot Create platforms enhanced by own modules. At the end of article, the results prove that even a simple system can be effectively used for environment mapping with relatively good accuracy.

Laboratory animals tracking in videosequences

This article deals with tracking of laboratory animals (guinea pigs) in cage. Authors collective applied machine vision tools based on global automatic thresholding, adaptive thresholding, differential operators and color matching algorithms. Animal activity and trajectory is significant marker in research of selected pathologies (gastrointestinal diseases in our case). Tracking is done in the huge database of videosequences of healthy animals (reference) and animals with induced gastric pain (gastric ulcer). The solution also be used like non-expensive replacement of radio-frequency laboratory trackers.

Detection of door's components in automotive industry by simple image processing

Aim of this article is the implementation of simple image processing in the inspection process. The inspection process is focused on door components in automotive industry. Article describes the needs of such process, implementation of solution and evaluation of results. Final application is based on OpenCV library and its components. Moreover, the process is optimized for real inspection system and it was tested in this system.