Cameras are one of the most relevant sensors in autonomous robots. However, two of their challenges are to extract useful information from captured images, and to manage the small field of view of regular cameras. This paper proposes implementing a dynamic visual memory to store the information gathered from a moving camera on board a robot, followed by an attention system to choose where to look with this mobile camera, and a visual localization algorithm that incorporates this visual memory. The visual memory is a collection of relevant task-oriented objects and 3D segments, and its scope is wider than the current camera field of view. The attention module takes into account the need to reobserve objects in the visual memory and the need to explore new areas. The visual memory is useful also in localization tasks, as it provides more information about robot surroundings than the current instantaneous image. This visual system is intended as underlying technology for service robot applications in real people’s homes. Several experiments have been carried out, both with simulated and real Pioneer and Nao robots, to validate the system and each of its components in office scenarios.
References
[1]
Hurtley, R.; Zisserman, A. Multiple View Geometry in Computer Vision; Cambridge University Press: Cambridge, UK, 2003.
[2]
Itti, L.; Koch, C. Computational Modelling of Visual Attention. Nat. Rev. Neurosci. 2001, 2, 194–203.
[3]
Zaharescu, A.; Rothenstein, A.L.; Tsotsos, J.K. Towards a biologically plausible active visual search model. Proceedings of International Workshop on Attention and Performance in Computational Vision, Prague, Czech Republic, 15 May 2004; pp. 133–147.
[4]
Remazeilles, A.; Chaumette, F.; Gros, P. 3D navigation based on a visual memory. Proceedings of 2006 IEEE International Conference on Robotics and Automation, Orlando, FL, USA, 15–19 May 2006.
[5]
Srinivasan, V.; Thurrowgood, S.; Soccol, D. An Optical System for Guidance of Terrain Following in UAVs. Proceedings of the IEEE International Conference on Video and Signal Based Surveillance (AVSS), Sydney, Australia, 22–24 November 2006; pp. 51–56.
[6]
Badal, S.; Ravela, S.; Draper, B.; Hanson, A. A Practical Obstacle Detection and Avoidance System. Proceedings of 2nd IEEE Workshop on Applications of Computer Vision, Sarasota, FL, USA, 5–7 December 1994; pp. 97–104.
[7]
Goldberg, S.B.; Maimone, M.W.; Matthies, L. Stereo Vision and Rover Navigation Software for Planetary Exploration. IEEE Aerosp. Conf. Proc. 2002, 5, 2025–2036.
[8]
Gartshore, R.; Aguado, A.; Galambos, C. Incremental Map Buildig Using an Occupancy Grid for an Autonomous Monocular Robot. Proceedings of Seventh International Conference on Control, Automation, Robotics and Vision, Singapore, 2–5 December 2002; pp. 613–618.
[9]
Itti, L.; Koch, C. A model of saliency-based visual attention for rapid scene analysis. IEEE Trans. Patt. Anal. Mach. Intell. 2005, 20, 1254–1259.
Marocco, D.; Floreano, D. Active vision and feature selection in evolutionary behavioral systems. Proceedings of 7th International Conference on Simulation of Adaptive Behavior (SAB-7), Edinburgh UK, 5–9 August 2002; pp. 247–255.
[12]
Ca？as, J.M.; Martínez de la Casa, M.; González, T. Overt visual attention inside JDE control architecture. Int. J. Intell. Comput. Med. Sci. Image Proces. 2008, 2, 93–100.
[13]
Hulse, M.; McBride, S.; Lee, M. Implementing inhibition of return; Embodied visual memory for robotic systems. Proceedings of the 9th International Conference on Epigenetic Robotics: Modeling Cognitive Development in Robotic Systems, Venice, Italy, 12–14 November 2009; pp. 189–190.
Burgard, W.; Fox, D. Active mobile robot localization by entropy minimization. Proceedings of the Euromicro Workshop on Advanced Mobile Robots, Los Alamitos, CA, USA, 22–24 October 1997; pp. 155–162.
[17]
Dellaert, F.; Burgard, W.; Fox, D.; Thrun, S. Using the CONDENSATION algorithm for robust, vision-based mobile robot localization. Proceedings of the Conference on Computer Vision and Pattern Recognition, Fort Collins, CO, USA, 23–25 June 1999; pp. 588–594.
[18]
Newcombe, R.A.; Davison, A.J. Live Dense Reconstruction with a Single Moving Camera. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA, 13–18 June 2010; pp. 1498–1505.
[19]
Carrera, G.; Angeli, A.; Davison, A.J. Lightweight SLAM and Navigation with a Multi-Camera Rig. Proceedings of the 5th European Conference on Mobile Robots, ？rebro, Sweden, 7–9 September 2011; pp. 77–82.
[20]
Tong, F.; Meng, M.Q.-H. Genetic algorithm based visual localization for a robot pet in home healthcare system. Int. J. Inform. Acquisit. 2007, 4, 141–160.
[21]
Duckett, T. A Genetic Algorithm for Simultaneous Localization and Mapping. Proceedings of the IEEE International Conference on Robotics and Automation, Taipei, Taiwan, 14–19 September 2003.
[22]
Moreno, L.; Armingol, J.M.; Garrido, S.; De la Escalera, A.; Salichs, M.A. A Genetic Algorithm for Mobile Robot Localization Using Ultrasonic Sensors. J. Intell. Robot. Syst. 2002, 34, 135–154.
[23]
Mariottini, G.L.; Roumeliotis, S.I. Active Vision-Based Robot Localization and Navigation in a Visual Memory. Proceedings of 2011 IEEE International Conference on Robotics and Automation, Shanghai, China, 9–13 May 2011.
[24]
Jensfelt, P.; Kristensen, S. Active global localization for a mobile robot using multiple hypothesis tracking. IEEE Trans. Robot. Automat. 2001, 17, 748–760.
[25]
Solis, A.; Nayak, A.; Stojmenovic, M.; Zaguia, N. Robust Line Extraction Based on Repeated Segment Directions on Image Contours. Proceedings of the IEEE Symposium on Computational Intelligence for Security and Defence Applications, Ottawa, Canada, 8–10 July 2009.
[26]
Fox, D.; Burgard, W.; Dellaert, F.; Thrun, S. Monte Carlo Localization: Efficient Position Estimation for Mobile Robots. Proceedings of the National Conference on Artificial Intelligence, Orlando, FL, USA, 18–22 July 1999.
