Over the last several decades, robotics has been a key technology for achieving high productivity and industrial competitiveness. Recently, robotics has begun expanding intensively outside of industrial settings, bringing robots closer to humans and into human environments. One of the main prerequisites for autonomous robot operation in unknown, highly dynamic environments populated by humans or other robots is to jointly perform (i) detection and tracking of moving objects (DATMO) and (ii) simultaneous localization and mapping (SLAM). The DATMO task is necessary due to the presence of a large number of moving objects, which should be avoided during navigation, but can also be used for the SLAM task, allowing the robot to infer its position and relate it to other objects of interest more efficiently, even in highly dynamic environments.
Both these tasks traditionally rely on stochastic estimation approaches, and recently the research community has begun investigating how these approaches can be applied to the geometry of non-Euclidean manifolds, such as special orthogonal and special Euclidean groups, for both planar and general 3D movement.
In order to be able to more efficiently execute the SLAM task, or to enable robots which have just started operating to immediately exploit the experience of veteran team members, multi-agent systems exploiting information sharing between team members and the cloud have also recently been proposed.
The International Workshop on Cooperative Dynamic Simultaneous Localization and Mapping aims to bring together leading international researchers to highlight state-of-the-art achievements in the DATMO and SLAM fields, discuss the work to date and the potential of the cooperative dynamic SLAM boosted by in-cloud technologies, both from the research and application prospective.
The workshop will be held at the Faculty of Electrical Engineering and Computer Engineering of the University of Zagreb, in Zagreb, Croatia, on Tuesday, September 19, 2017. The University of Zagreb (1669) is the oldest and biggest university in South-Eastern Europe with over 70,000 students, and the Faculty of Electrical Engineering and Computing, which is one of its leading constituent unit, is the largest technical faculty and leading educational and R&D institution in the fields of electrical engineering, information and communication technology and computing in the Republic of Croatia. The workshop will be hosted by the LAMOR laboratory (http://lamor.fer.hr/ ), supported in part by the CloudSLAM project (http://cloudslam.fer.hr/).