Department of Computer Graphics and Multimedia

SRS - Multi-Role Shadow Robotic System for Independent Living
Reseach leader:Smrž Pavel
Team leaders:Španěl Michal
Agency:EU-7FP-IST
Code:7E12056
Start:2011
End:2013
Keywords:assistive robotics, computer vision
Annotation:
SRS (Multi-Role Shadow Robotic System for Independent Living) focuses on the development and prototyping of remotely-controlled, semi-autonomous robotic solutions in domestic environments to support elderly people. SRS solutions are designed to enable a robot to act as a shadow of its controller. For example, elderly parents can have a robot as a shadow of their children or carers. In this case, adult children or carers can help them remotely and physically with daily living tasks as if the children or carers were resident in the house. Remote presence via robotics is the key to achieve targeted SRS goal. Based on the study of user requirements, the usability of the system can be improved by real-time 3D display on the client side. However, network communication poses serious problems due to limited and potentially unreliable communication channels. The proposed extension of the SRS project focuses on context-aware multimodal HRI support aimed at usability, safety and situation awareness for remote users. The new Context-Aware Virtual 3D Display will be able to cope with the project visualisation needs resulting from the existing requirement specifications. It will work on the client side based on predefined 3D maps. The Virtual map will be updated online employing a combination of real-time 3D robot perception, real-time 2D video processing and remote operator perception. The technical outcome will employ context detection based on visual clues, trajectory verification by means of video processing and object detection in images. Advanced fusion mechanisms will also be explored too. The addition of BUT to the consortium will allow optimizing the SRS HRI design and developing multimodal interfaces that are more appropriate for and attractive to the targeted user group. This will improve the end-user experience with the SRS robot and hence make the project more effective and more efficient. The extension will enable building better robots for personalized health care.

Publications

2013Ila Viorela S., Polok Lukáš, Smrž Pavel, Šolony Marek, Zemčík Pavel: Incremental Cholesky Factorization for Least Squares Problems in Robotics, In: Proceedings of The 2013 IFAC Intelligent Autonomous Vehicles Symposium, Gold Coast, AU, IEEE CS, 2013, p. 1-8, ISBN 978-1-00-000000-9
 Polok Lukáš, Ila Viorela S., Šolony Marek, Zemčík Pavel, Smrž Pavel: Efficient Implementation for Block Matrix Operations Nonlinear Least Squares Problems for Robotic Applications, In: Proceedings of 2013 IEEE International Conference on Robotics and Automation, Karlsruhe, DE, IEEE CS, 2013, p. 123-131, ISBN 0-7645-2641-3
2012Hulík Rostislav, Beran Vítězslav, Španěl Michal, Kršek Přemysl, Smrž Pavel: Fast and Accurate Plane Segmentation in Depth Maps for Indoor Scenes, In: IEEE/RSJ International Conference on Intelligent Robots and Systems, Vilamoura, Algarve, PT, UPGM FIT VUT, 2012, p. 1-6, ISBN 978-1-4673-1737-5

Your IPv4 address: 50.16.17.90
Switch to IPv6 connection

DNSSEC [dnssec]