arXiv subjects

Libor Přeučil

Publications and source records attributed to Libor Přeučil.

22 records · Page 2Linked to original sources

arXiv2019

Improved Discrete RRT for Coordinated Multi-robot Planning

This paper addresses the problem of coordination of a fleet of mobile robots - the problem of finding an optimal set of collision-free trajectories for individual robots in the fleet. Many approaches have been introduced during the last decades, but a minority of them is practically applicable, i.e. fast, producing near-optimal solutions, and complete. We propose a novel probabilistic approach based on the Rapidly Exploring Random Tree algorithm (RRT) by significantly improving its multi-robot variant for discrete environments. The presented experimental results show that the proposed approach is fast enough to solve problems with tens of robots in seconds. Although the solutions generated by the approach are slightly worse than one of the best state-of-the-art algorithms presented in (ter Mors et al., 2010), it solves problems where ter Mors's algorithm fails.

cs.RO↗

arXiv2017

Practical Aspects of Autonomous Exploration with a Kinect2 sensor

Exploration of an unknown environment by a mobile robot is a complex task involving solution of many fundamental problems from data processing, localization to high-level planning and decision making. The exploration framework we developed is based on processing of RGBD data provided by a MS Kinect2 sensor, which allows to take advantage of state-of-the-art SLAM (Simultaneous Localization and Mapping) algorithms and to autonomously build a realistic 3D map of the environment with projected visual information about the scene. In this paper, we describe practical issues that appeared during deployment of the framework in real indoor and outdoor environments and discuss especially properties of SLAM algorithms processing MS Kinect2 data on an embedded computer.

cs.RO↗

arXiv2017

Speed-up of Self-Organizing Networks for Routing Problems in a Polygonal Domain

Routing problems are optimization problems that consider a set of goals in a graph to be visited by a vehicle (or a fleet of them) in an optimal way, while numerous constraints have to be satisfied. We present a solution based on multidimensional scaling which significantly reduces computational time of a self-organizing neural network solving a typical routing problem -- the Travelling Salesman Problem (TSP) in a polygonal domain, i.e. in a space where obstacles are represented by polygons. The preliminary results show feasibility of the proposed approach and although the results are presented only for TSP, the method is general so it can be used also for other variants of routing problems.

cs.RO↗

arXiv2017

Real-Time Visual Localisation in a Tagged Environment

In a robotised warehouse a major issue is the safety of human operators in case of intervention in the work area of the robots. The current solution is to shut down every robot but it causes a loss of productivity, especially for large robotised warehouses. In order to avoid this loss we need to ensure the operator's security during his/her intervention in the warehouse without powering off the robots. The human operator needs to be localised in the warehouse and the trajectories of the robots have to be modified so that they do not interfere with the human. The purpose of this paper is to demonstrate a visual localisation method with visual elements that are already available in the current warehouse setup.

cs.CV↗