Early Model of Vision-Based Obstacle Mapping Utilizing Grid-Edge-Depth Map
Budi Rahmani1, Agus Harjoko2, Tri Kuntoro Priyambodo3, Hugo Aprilianto4
1Budi Rahmani*, Department of Informatics, STMIK Banjarbaru, Kalimantan Selatan, Indonesia.
2Agus Harjoko, Department of Computer Science and Electronics, Faculty of Mathematics and Natural Science, Universitas Gadjah Mada, Yogyakarta, Indonesia.
3Tri Kuntoro Priyambodo, Department of Computer Science and Electronics, Faculty of Mathematics and Natural Science, Universitas Gadjah Mada, Yogyakarta, Indonesia.
4Hugo Aprilianto, Department of Informatics, STMIK Banjarbaru, Kalimantan Selatan, Indonesia.
Manuscript received on November 22, 2019. | Revised Manuscript received on December 15, 2019. | Manuscript published on December 30, 2019. | PP: 4419-4423 | Volume-9 Issue-2, December, 2019. | Retrieval Number: B4550129219/2019©BEIESP | DOI: 10.35940/ijeat.B4550.129219
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: This paper described a new method of obstacle mapping in an indoor environment utilizing a Grid-edge-depth map. The Grid-edge-depth map contained the information of distance and relative position of the object in the front of the robot. This mapping method utilized this information to mark off the visible obstacle/s in a particular virtual map. The 2D map created as a representative of the environment using a 300 by 500 pixels image. Every pixel represents a one by one cm of the environment and the obstacle’s size. The obstacle’s size was 30 by 30 pixels when it mapped by the system. It was a fixed size in the mapping process since the system cannot calculate the dimension of the detected obstacle. If the obstacle detected, the system checked its distance in GED-map. Then the system calculated the obstacle’s position against the goal, and finally map it in the 2D map. In this case, the proposed method in building a 2D map of the obstacle in the indoor environment combined with the rules to decide the direction of the mobile robot. The rules used to avoid the collision to the obstacle. The evaluation of the method showed that the system could map the detected obstacles, the initial position, and the goal’s relatif distance and position. The robot also reaches the goal position while avoiding the collision to the obstacle.
Keywords: GED-map, Map building, Mobile robot, Stereovision, distance.