Hostname: page-component-76d6cb85b7-mgxrv Total loading time: 0 Render date: 2026-07-16T22:50:43.441Z Has data issue: false hasContentIssue false
  • English
  • Français

Real-time obstacle detection using range images: processing dynamically-sized sliding windows on a GPU

Published online by Cambridge University Press:  06 March 2015

Caio César Teodoro Mendes ,
Fernando Santos Osório  and
Denis Fernando Wolf
Caio César Teodoro Mendes*
Affiliation:
Mobile Robotics Laboratory, University of São Paulo (USP), Av. Trabalhador São-Carlense, 400, P.O. Box 668, 13.560-970 São Carlos, Brazil. E-mails: fosorio@icmc.usp.br, denis@icmc.usp.br
Fernando Santos Osório
Affiliation:
Mobile Robotics Laboratory, University of São Paulo (USP), Av. Trabalhador São-Carlense, 400, P.O. Box 668, 13.560-970 São Carlos, Brazil. E-mails: fosorio@icmc.usp.br, denis@icmc.usp.br
Denis Fernando Wolf
Affiliation:
Mobile Robotics Laboratory, University of São Paulo (USP), Av. Trabalhador São-Carlense, 400, P.O. Box 668, 13.560-970 São Carlos, Brazil. E-mails: fosorio@icmc.usp.br, denis@icmc.usp.br
*
*Corresponding author. E-mail: caiom@icmc.usp.br
Get access Rights & Permissions [Opens in a new window]

Summary

An efficient obstacle detection technique is required so that navigating robots can avoid obstacles and potential hazards. This task is usually simplified by relying on structural patterns. However, obstacle detection constitutes a challenging problem in unstructured unknown environments, where such patterns may not exist. Talukder et al. (2002, IEEE Intelligent Vehicles Symposium, pp. 610–618.) successfully derived a method to deal with such environments. Nevertheless, the method has a high computational cost and researchers that employ it usually rely on approximations to achieve real-time. We hypothesize that by using a graphics processing unit (GPU), the computing time of the method can be significantly reduced. Throughout the implementation process, we developed a general framework for processing dynamically-sized sliding windows on a GPU. The framework can be applied to other problems that require similar computation. Experiments were performed with a stereo camera and an RGB-D sensor, where the GPU implementations were compared to multi-core and single-core CPU implementations. The results show a significant gain in the computational performance, i.e. in a particular instance, a GPU implementation is almost 90 times faster than a single-core one.

Keywords

Obstacle detectionAutonomous navigationStereo visionGraphics processing unit (GPU)

Information

Type
Articles
Information
Robotica , Volume 35 , Issue 1 , January 2017 , pp. 85 - 100
Copyright
Copyright © Cambridge University Press 2015 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Article purchase

Temporarily unavailable

References

1. Hadsell, R., Sermanet, P., Ben, J., Erkan, A., Scoffier, M., Kavukcuoglu, K., Muller, U. and Le, Y.Cun, “Learning long-range vision for autonomous off-road driving,” J. Field Robot. 26 (2), 120–144 (2009).Google Scholar
2. Konolige, K., Agrawal, M., Blas, M. R., Bolles, R. C., Gerkey, B., Solà, J. and Sundaresan, A., “Mapping, navigation, and learning for off-road traversal,” J. Field Robot. 26 (1), 88–113.Google Scholar
3. Broggi, A., Caraffi, C., Fedriga, R. and Grisleri, P., “Obstacle Detection with Stereo Vision for Off-Road Vehicle Navigation,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition – Workshops, San Diego, California, USA (2005) p. 65.Google Scholar
4. Caraffi, C., Cattani, S. and Grisleri, P., “Off-road path and obstacle detection using decision networks and stereo vision,” IEEE Trans. Intell. Transp. Syst. 8 (4), 607–618 (2007).Google Scholar
5. Kolter, J., Rodgers, M. and Ng, A., “A Control Architecture for Quadruped Locomotion Over Rough Terrain,” IEEE International Conference on Robotics and Automation, Pasadena, California, USA (2008) pp. 811–818.Google Scholar
6. Lacroix, S., Mallet, A., Bonnafous, D., Bauzil, G., Fleury, S., Herrb, M. and Chatila, R., “Autonomous Rover Navigation on Unknown Terrains Functions and Integration,” In:Experimental Robotics VII, Lecture Notes in Control and Information Sciences, vol. 271 (Springer, Berlin Heidelberg, 2001) pp. 501–510.Google Scholar
7. Talukder, A., Manduchi, R., Rankin, A. and Matthies, L., “Fast and Reliable Obstacle Detection and Segmentation for Cross-Country Navigation,” IEEE Intelligent Vehicles Symposium, Versailles, France (2002) pp. 610–618.Google Scholar
8. Broggi, A., Buzzoni, M., Felisa, M. and Zani, P., “Stereo Obstacle Detection in Challenging Environments: The viac Experience,” IEEE/RSJ International Conference on Intelligent Robots and Systems, San Francisco, California, USA (2011) pp. 1599–1604.Google Scholar
9. van der Mark, W., van den Heuvel, J. and Groen, F., “Stereo Based Obstacle Detection with Uncertainty in Rough Terrain,” IEEE Intelligent Vehicles Symposium, Istanbul, Turkey (2007) pp. 1005–1012.Google Scholar
10. Santana, P., Santos, P., Correia, L. and Barata, J., “Cross-Country Obstacle Detection: Space-Variant Resolution and Outliers Removal,” IEEE/RSJ International Conference on Intelligent Robots and Systems, Nice, France (2008) pp. 1836–1841.Google Scholar
11. Mendes, C. C. T., Osorio, F. S. and Wolf, D. F., “An Efficient Obstacle Detection Approach for Organized Point Clouds,” IEEE Intelligent Vehicles Symposium (IV), Gold Coast City, Australia (2013) pp. 1203–1208. Available at: http://dx.doi.org/10.1109/IVS.2013.6629630 doi:10.1109/IVS.2013.6629630.Google Scholar
12. Manduchi, R., Castano, A., Talukder, A. and Matthies, L., “Obstacle detection and terrain classification for autonomous off-road navigation,” Auton. Robots 18 (1), 81–102 (2005).Google Scholar
13. NVIDIA, OpenCL Programming Guide for the CUDA Architecture (May 2010). Available at: http://developer.download.nvidia.com/compute/cuda/3_1/toolkit/docs/NVIDIA_OpenCL_ProgrammingGuide.pdf Google Scholar
14. Xiao, S. and chun Feng, W., “Inter-Block GPU Communication Via Fast Barrier Synchronization,” IEEE International Symposium on Parallel Distributed Processing, Atlanta, Georgia, USA (2010) pp. 1–12.Google Scholar
15. AMD, AMD Accelerated Parallel Processing OpenCL Programming Guide (Jul 2013). Available at: http://developer.amd.com/tools/hc/AMDAPPSDK/assets/AMD_Accelerated_Parallel_Processing_OpenCL_Programming_Guide.pdf.Google Scholar
16. Hirschmuller, H., “Accurate and Efficient Stereo Processing by Semi-Global Matching and Mutual Information,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, San Diego, California, USA (2005) pp. 807–814.Google Scholar