1. Home
  2. Honda R&D Technical Review Vol.32 N...
  3. Traversability Analysis for Mobile ...

Technical Review e-Book: Summary

Traversability Analysis for Mobile Robot Navigation in Rough Terrain

Article of Honda R&D Technical Review Vol.32 No.2

Summary

For the research described here, the road surface necessary to enable autonomous navigation by a robot in rough terrain was modeled and a method of traversability analysis of that road surface was created. As in much preceding research, this method consists of three steps, which are (1) dividing the road surfaces around the robot into grids, (2) generating a road surface model of each grid, and then (3) performing traversability analysis of those road surfaces by evaluating those models. The new contribution made by this method is that, by optimizing the grid size of the road surface to be modeled, it can assure the validity of modeling a road surface on rough terrain by means of planes. In addition, this method is robust with regard to outliers and noise near maximum and minimum values in a measurement point cloud, and the small number of setting parameters is another distinguishing characteristic. Application of this method to an environment of rough terrain, including slopes, uneven surfaces, and obstacles, made it possible for robots to correctly perform traversability analysis of road surfaces and to navigate autonomously in that environment.

Reference

(1) Duckett, T., Pearson, S., Blackmore, S., Grieve, B.: Agricultural robotics: the future of robotic Agriculture, UK-RAS White Papers, EPSRC UK-Robotics and Autonomous Systems Network, (2018)
(2) Suger, B., Steder, B., Burgard, W.: Traversability analysis for mobile robots in outdoor environments: a semi-supervised learning approach based on 3d-lidar data, In: Proceedings—IEEE international conference on robotics and automation, p. 3941-3946, (2015)
(3) Chavez-Garcia, R. O., Guzzi, J., Gambardella, L. M., Giusti, A.: Image classification for ground traversability estimation in robotics, Proc. 18th Int. Conf. Adv. Concepts Intell. Vision Syst., p. 325-336, (2017)
(4) Chavez-Garcia, R. O., Guzzi, J., Gambardella, L. M., Giusti, A.: Learning ground traversability from simulations, IEEE Robot. Autom. Lett., vol. 3, no. 3, p. 1695-1702, (2018)
(5) Hirose, N., Sadeghian, A., Vázquez, M., Goebel, P., Savarese, S.: Gonet: A semi-supervised deep learning approach for traversability estimation, Proc. IEEE/RSJ Int. Conf. Intell. Robots Syst., p. 3044-3051, (2018)
(6) Hirose, N., Sadeghian, A., Xia, F., Martín-Martín, R., Savarese, S.: Vunet: Dynamic scene view synthesis for traversability estimation using an RGB camera, IEEE Robot. Autom. Lett., vol. 4, no. 2, p. 2062-2069, (2019)
(7) Bekhti, M. A., Kobayashi, Y.: Regressed Terrain Traversability Cost for Autonomous Navigation Based on Image Textures, MDPI. applied sciences. Vol. 10, no. 1195, (2020)
(8) Schilling, F., Chen, X., Folkesson, J., Jensfelt, P.: Geometric and visual terrain classification for autonomous mobile navigation, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), p. 2678-2684, (2017)
(9) Bogoslavskyi, I., Vysotska, O., Serafin, J., Grisetti, G., Stachniss, C.: Efficient traversability analysis for mobile robots using the kinect sensor, European Conference on Mobile Robots (ECMR), (2013)
(10) Škoda, J.: 3D Navigation for Mobile Robots, (2017)
(11) Fischler., M. A., Bolles, R. C.: Random sample consensus: A paradigm for modelfitting with applications to image analysis and automated cartography, Communications of the ACM, 24(6):381-395, (1981)
(12) Braun, T., Bitsch, H., Berns, K.: Visual terrain traversability estimation using a combined slope/elevation model, in LNCS, vol. 5243, (2008)
(13) Chilian, A., Hirschmuller, H.: Stereo camera based navigation of mobile robots on rough terrain, Intell. Robots and Systems (IROS), p. 4571-4576, (2009)
(14) Ye, C., Borenstein, J.: A Method for Mobile Robot Navigation on Rough Terrain, Proceedings of the 2004 IEEE International Conference on Robotics and Automation, p. 3863-3869, (2004)
(15) Tanaka, Y., Ji, Y., Yamashita, A., Asama, H.: Fuzzy Based Traversability Analysis for a Mobile Robot on Rough Terrain, Proceedings of the 2015 IEEE International Conference on Robotics and Automation, p. 3965-3970, (2015)

Author (organization or company)

Shintaro HIDAKA(Life Creation Center)、Norio NEKI(Life Creation Center)

We would like to get your opinion on this research paper. (This is only applicable to registered members.)

The readers of this research paper have also selected these research papers.

Guide Robot Management System
Article of Honda R&D Technical Review Vol.32 No.2
Analysis of Subjective Values of Car Users in Japan and U.S. Using Free Description Keyword Method
Article of Honda R&D Technical Review Vol.32 No.2
Modeling and Utilizing Expert’s Knowledge, Experience, and Thinking in Automobile Development
Article of Honda R&D Technical Review Vol.32 No.2