Personal tools
You are here: Home Results PDFs of PUBLIC Year 2 deliverables DR 1.2.2: Acquisition of spatio-temporal maps and place topologies of semi-structured environments
About NIFTi
NIFTi is about human-robot cooperation. About teams of robots and humans doing tasks together, interacting together to try and reach a shared goal. NIFTi looks at how the robot could bear the human in mind. Literally. When determining what to do or say next in human-robot interaction; when, and how. NIFTi puts the human factor into cognitive robots, and human-robot team interaction in particular.   Each year, NIFTi evaluates its systems together with several USAR organizations. Rescue personnel teams up with NIFTi robots to carry out realistic missions, in real-life training areas. 
Impressum

This site uses Google Analytics to record statistics on site visits - see Legal information.

 

DR 1.2.2: Acquisition of spatio-temporal maps and place topologies of semi-structured environments

Urban Search and Rescue scenarios require specific mapping processes for two different reasons. First, the environments are usually semi-structured or even sometimes unstructured. This calls for a full 3D representation of the environment as a 2D extrapolation is unsuitable. Second, as the robot is but an agent in a team, spatial information gathered must be communicated to human users. Additionally to these specific requirements, real environments imply to handle changes. In this report, following on last year DR1.1.1, we present the results of WP1 on spatio-temporal modeling for situation awareness during the second year of NIFTi. The objectives were to provide consistent spatio-temporal representations of a USAR site (MS1.2) as well as spatio-temporally grounded place topologies (MS1.3). We developed a hybrid mapping and localization system, based on state-of-the-art 2D SLAM, an incremental topological segmentation, and 3D ICP registration. We also tackle the issue of spatio-temporal mapping with dynamic scene analysis as well as continuous mapping of the environment according to last year reviewers suggestion. Finally we present advances on bi-directional inference for functional mapping including robot morphology.

m24-DR1.2.2-PUBLIC.pdf — PDF document, 12114Kb

Document Actions