Indonesian Journal of Electrical Engineering and Computer Science Vol. 26, No. 1, April 2022, pp. 450~461 ISSN: 2502-4752, DOI: 10.11591/ijeecs.v26.i1.pp450-461  450 Journal homepage: http://ijeecs.iaescore.com Path planning for assisting blind people in purposeful navigation Andrés Díaz-Toro, Paula Mosquera-Ortega, Gustavo Herrera-Silva, Sixto Campaña-Bastidas School of Basic Sciences, Technology and Engineering, Universidad Nacional Abierta y a Distancia, Pasto, Colombia Article Info ABSTRACT Article history: Received Oct 27, 2021 Revised Feb 8, 2022 Accepted Feb 12, 2022 Blind people present dificulties for reaching objects of interest in the daily life. In this sense, the integration of a path planning module for assisting blind people in purposeful navigation is noteworthy. In this work, we present an algorithm that leverages the high capability of an embedded computer with graphics processing unit (GPU) NVIDIA Jetson TX2 for computing optimal paths to objects of interest. The algorithm computes the optimal path to the objective, considering changes in the environment and changes in the position of the user. The algorithm is efficient for computing new paths when the environment changes by reusing parts of previous computations. In order to compare the performance, the algorithms were implemented and evaluated in MATLAB, C++ and CUDA, for different size of the grid and percentage of unknown obstacles. We found that the implementation on GPU has a speed up of 20 times W.R.T the implementation in C++ and more than 400 times W.R.T the implementation in MATLAB. These results boost us to integrate this module to our main system based on a stereo camera and a haptic belt and so provide to the user assistance in purposeful navigation at real time. Keywords: Dynamic environment Graphics processing unit Occupancy grid Parallel programming Performance evaluation Real time processing Replanning This is an open access article under the CC BY-SA license. Corresponding Author: Andrés Díaz-Toro School of Basic Sciences, Technology and Engineering, Universidad Nacional Abierta y a Distancia Pasto, Colombia Email: andres.diaz@unad.edu.co 1. INTRODUCTION People with severe visual impairment, especially the ones with total loss of sight, struggle to move and carry out activities in unfamiliar environments [1], which reduces their opportunities in education, work, health, and social activities, affecting considerably their quality of life. Purposeful navigation consists in setting a destination and computing a path to guide the user to the target. There are few systems that provide assistance to blind people in purposeful navigation, like [2]-[6]. Some reasons for this shortage are listed next. i) These applications require to process dense data at real time, so a computer with high computational capabilities is needed; ii) These applications require that the user moves and carries the hardware, so the computer must also be portable; iii) These applications require complex algorithms to localize in indoors without the help of global positioning system (GPS) (like the ones presented in [7]-[9]), detect static and dynamic obstacles, and build incrementally a representation of the environment; iv) Until few years ago, the algorithms for object detection were not efficient. With the advent in the last years of advanced algorithms of artificial intelligence applied to computer vision (like the ones presented in [10]-[12]), efficient modules for object detection than run on graphics processing unit (GPU) have been plausible; v) Most algorithms for path planning were focused on video games and driverless vehicles (like the ones presented in [13]-[16]), especially due to economic interests.