Mário Saleiro, J. M. F. Rodrigues, J. M. H. du Buf


The interest in cognitive robotics is still increasing, a major goal being to create a system which can adapt to dynamic environments and which can learn from its own experiences. We present a new cognitive SLAM architecture, but one which is minimalistic in terms of sensors and memory. It employs only one camera with pan and tilt control and three memories, without additional sensors nor any odometry. Short-term memory is an egocentric map which holds information at close range at the actual robot position. Long-term memory is used for mapping the environment and registration of encountered objects. Object memory holds features of learned objects which are used as navigation landmarks and task targets. Saliency maps are used to sequentially focus important areas for object and obstacle detection, but also for selecting directions of movements. Reinforcement learning is used to consolidate or enfeeble environmental information in long-term memory. The system is able to achieve complex tasks by executing sequences of visuomotor actions, decisions being taken by goal-detection and goal-completion tasks. Experimental results show that the system is capable of executing tasks like localizing specific objects while building a map, after which it manages to return to the start position even when new obstacles have appeared.


  1. Alami, R., Clodic, A., Montreuil, V., Sisbot, E. A., and Chatila, R. (2006). Toward human-aware robot task planning. Association for the Advancement of Artificial Intelligence Spring Symposia, AAAI, page 8pp.
  2. Brady, T., Konkle, T., Alvarez, G., and Oliva, A. (2008). Visual long-term memory has a massive storage capacity for object details. Proc. Nat. Acad. Scie., 105(38):14325-14329.
  3. Butko, N., Zhang, L., Cottrell, G., and Movellan, J. (2008). Visual salience model for robot cameras. Proc. 2008 IEEE. Int. Conf. on Rob. and Automation, pages 2398- 2403.
  4. Evans, C. (2009). Notes on the OpenSURF Library. Tech. Rep. CSTR-09-001. University of Bristol. URL
  5. Farrajota, M., Martins, J., Rodrigues, J., and du Buf, J. (2011). Disparity energy model with keypoint disparity validation. Accepted for 17th Portuguese Conf. on Pattern Recognition, Porto, Portugal.
  6. Itti, L., Koch, C., and Niebur, E. (1998). A model of saliency-based visual attention for rapid scene analysis. IEEE Trans. on Patt. Recog. and Mach. Intell., 20(11):1254-1259.
  7. José, J., Farrajota, M., Rodrigues, J., and du Buf, J. (2010). A vision system for detecting paths and moving ostacles for the blind. Proc. Int. Conf. on Software Development for Enhancing Accessibility and Fighting Info-exclusion, pages 175-182.
  8. Kawamura, K., Koku, A., Wilkes, D., Peters II, R., and Sekmen, A. (2002). Toward egocentric navigation. Int. J. Robotics and Automation, 17(4):135-145.
  9. Kleinmann, L. and Mertsching, B. (2011). Learning to adapt: Cognitive architecture based on biologically inspired memory. In Industrial Electronics and Applications (ICIEA), 2011 6th IEEE Conference on, pages 936 -941.
  10. Meger, D., Forssén, P., Lai, K., Helmer, S., McCann, S., Southey, T., Baumann, M., Little, J. J., and Lowe, D. G. (2008). Curious George: An attentive semantic robot. Rob. Aut. Sys., 56(6):503-511.
  11. Meinert, P. (2008). The impact of previous life experience on cognitive structure changes and knowledge acquisition of nursing theory and clinical skills in nontraditional nursing students. PhD Thesis, Kent State Univ., College of Education, Health and Human Services, USA, page 173.
  12. Milford, M. and Wyeth, G. (2010). Persistent navigation and mapping using a biologically inspired slam system. Int. J. Robotics Res., 29(9):1131-1153.
  13. Montemerlo, M., Thrun, S., Koller, D., and Wegbreit, B. (2002). Fastslam: A factored solution to the simultaneous localization and mapping problem. Proc. AAAI. Nat. Conf. Art. Int., pages 593-598.
  14. Papauschek, C. and Zillich, M. (2010). Biologically inspired navigation on a mobile robot. In IEEE Int. Conf. Robotics and Biomimetics, pages 519 -524.
  15. Patnaik, S. (2007). Robot Cognition and Navigation: An Experiment with Mobile Robots. Springer, 1st edition.
  16. Ratanaswasd, P., Gordon, S., and Dodd, W. (2005). Cognitive control for robot task execution. Proc. IEEE Int. Work. Rob. Hum. Int. Com., (5):440-445.
  17. Rensink, R. (2000). The dynamic representation of scenes. Visual Cogn., 7(1-3):17-42.
  18. Rodrigues, J. and du Buf, J. (2006). Multi-scale keypoints in V1 and beyond: object segregation, scale selection, saliency maps and face detection. BioSystems, pages 75-90.
  19. Rodrigues, J. and du Buf, J. M. H. (2009). Multi-scale lines and edges in V1 and beyond: Brightness, object categorization and recognition, and consciousness. Biosystems, 95(3):206-226.
  20. Saleiro, M., Rodrigues, J., and du Buf, J. (2009). Automatic hand or head gesture interface for individuals with motor impairments, senior citizens and young children. Proc. Int. Conf. Soft. Dev. for Enhancing Accessibility and Fighting Info-Exclusion, pages 165- 171.

Paper Citation

in Harvard Style

Saleiro M., M. F. Rodrigues J. and M. H. du Buf J. (2012). MINIMALISTIC VISION-BASED COGNITIVE SLAM . In Proceedings of the 4th International Conference on Agents and Artificial Intelligence - Volume 1: SSIR, (ICAART 2012) ISBN 978-989-8425-95-9, pages 614-623. DOI: 10.5220/0003881306140623

in Bibtex Style

author={Mário Saleiro and J. M. F. Rodrigues and J. M. H. du Buf},
booktitle={Proceedings of the 4th International Conference on Agents and Artificial Intelligence - Volume 1: SSIR, (ICAART 2012)},

in EndNote Style

JO - Proceedings of the 4th International Conference on Agents and Artificial Intelligence - Volume 1: SSIR, (ICAART 2012)
SN - 978-989-8425-95-9
AU - Saleiro M.
AU - M. F. Rodrigues J.
AU - M. H. du Buf J.
PY - 2012
SP - 614
EP - 623
DO - 10.5220/0003881306140623