Peter Hubinský

MOBILE ROBOT NAVIGATION BASED ON CIRCLE RECOGNITION

This paper presents a navigation method for a mobile robot using a visual system. Circular marks with specific colors are used for marking the significant points of the mobile robot’s trajectory that it needs to pass. The colors of the used marks are signalizing the way of their bypassing with the mobile robot (from the left or right side). The mobile robot uses only one camera for the marks recognition task and it is able to determine its own relative position from the detected marks. The image processing and the mobile robot’s trajectory planning algorithm working in real-time are described in this paper.

Simple Image Processing Algorithms for Robot Navigation in Unknown Environment

This article deals with simple image processing algorithms which are used for navigation of the robot in unknown environment. In the beginning of the article image processing procedures used in these algorithms are defined. The transformation of coordinate system of camera to robot’s coordinate system is introduced. The main body of the article consists of the definition of L-K optical flow method used in proposed visual odometry system. Article also contains the parameter settings of the used methods. Emphasis in these algorithms has been placed on simplicity and speed, so that they can be carried out in real-time. Algorithms have been verified on several scenarios.

Android-Based Mobile Robotic Platform Performance Testing for Real-Time Navigation

This paper discusses the suitability of usage of smartphones running on Android operating system in robot navigation tasks. These phones are equipped with many sensors useful in robotics. Robot navigation tasks are often recommending high-performance devices (computers) to work on. Nowadays smartphones are also equipped with very powerful processors. Therefore a performance test of different devices with Android operating system including their sensorial equipment has been made to determine the usability of these devices for real-time robot navigation.

Foundations of Visual Linear Human–Robot Interaction via Pointing Gesture Navigation

This paper presents a human–robot interaction method for controlling an autonomous mobile robot with a referential pointing gesture. A human user points to a specific location, robot detects the pointing gesture, computes its intersection with surrounding planar surface and moves to the destination. A depth camera mounted on the chassis is used. The user does not need to wear any extra clothing or markers. The design includes necessary mathematical concepts such as transformations between coordinate systems and vector abstraction of features needed for simple navigation, which other current research works misses. We provide experimental evaluation with derived probability models. We term this approach “Linear HRI” and define 3 laws of Linear HRI.

Robotic Cell Control System Standardization

Nowadays, in the modern manufacturing factories and in the companies engaged in the robotic cells manufacture it is necessary to optimize the production time, diagnostics and commissioning of the control system. The control system should meet with several criteria for the functionality and transparency. These criteria can be achieved by introducing the program control standardization. Well designed and tested control algorithms can reduce the time needed for the preparation and commissioning of the robotic cell. Ultimately, costs reduction for the preparation of such robotic cell, transparency and rapid response for errors diagnostics in the control system will be achieved.

Probabilistic Approach to Mobile Robot Localization Based on Gaussian Models of Sensors

In this paper the probabilistic approach to mobile robot localization is discussed. Generally probabilistic localization uses some type of sensors model. In this paper Gaussian model, which is the most appropriate probabilistic model of the sensors, is used. The main body of the article deal with the proposal of own approach to probabilistic localization, which is inspired by Markov localization. That is why the Markov localization is described in the introduction of the article. At the end of the article several experiments with the real robot are described. Results of the experiments have proven that proposed localization is accurate, fast and reliable.

Integration of Inertial Measuring Unit Platform into MATLAB Simulink

Abstract This documents describes a modular hardware platform for inertial measuring unit and its integration into Matlab Simulink. Its purpose is to give students a way to work with real device in an environment which they are familiar with. They can train various methods of signal processing and filtering and they can get familiar with used MEMS gyroscopes and accelerometers.