Personal tools
You are here: Home Results PDFs of PUBLIC Year 2 deliverables
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. 

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


PDFs of PUBLIC Year 2 deliverables

PDFs of all the NIFTi deliverables due in Year 2. The versions are PUBLIC. In some deliverables, not-yet-published work may not be concluded. Please contact the authors should you be interested.

File DR8.1.3: Proceedings of NJEx 2011, NID 2011
DR8.1.3 describes two dissemination events, organized back-to-back at the FDDO training center in July 2011: The NIFTi Joint Exercises 2011 (NJEx 2011), and the NIFTi Industry Day 2011.
File NIFTi Year 2 summary
Provides a summary of the results achieved in NIFTi in Year 2. The project focused on "human-assisted joint exploration" of a tunnel accident disaster site. We approached the problem from the viewpoint of a human-robot team, involving several humans at a remote command post, one in-field human to pilot a UAV, and a UGV (operated from the remote command post).
File DR 4.2.1: Validated task load, attention and user model patterns that specify the relationship between task demands and user properties
This report presents the results of WP4 for the first year of NIFTi. The overall objective of WP4 is to improve the effectiveness and efficiency of joint exploration by dynamic task load allocation to the human workers and robots. This objective will result in core UI design and evaluation activities aiming at the theoretical and empirical founded solutions to support shared situation awareness and prevent cognitive overload. In year 1 the work in WP4 focused on the determination of cognitive task load and selectional attention based on knowledge and context factors.
File 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.
File DR 2.2: Stereo- and omni-directional vision for human- assisted exploration
Vision plays an essential role in the robot perception and also serves as the primary source of information for robot tele-operation. There are many possible disaster scenarios, where knowledge about the presence or absence of specific types of objects is useful. We present the results of WP2 on visual-conceptual modeling for situation awareness during the second year of NIFTi. We focused on vision for human assisted exploration (MS2.2). We contributed in device calibration, machine learning for image understanding, car detection, terrain classification, navigation and orientation and human body part localization.
File DR 3.2.2: Adaptive situated HRI for human-assisted navigation
This report presents the results of WP 3 for the second year of NIFTi. The overall objective of WP3 is to facilitate communication between the humans and robots, while jointly exploring a disaster area. In Year 2, WP 3 focused on communication to support human-assisted exploration in the context of a human-robot team, thus going beyond the originally envisioned setup of a single operator working with a single robot. The physical setting for the interaction remained such that most of the human team is located at a remote command post, outside of visible range of the robot operating in the hotzone. In Year 2 WP3 developed multi-view user interfaces to facilitate different views on information in the human-robot team, to help support different roles in the team. The interfaces provided multiple modes of communication, including touch and spoken dialogue. This setup was deployed during the end user evaluations at SFO in December 2011.
File DR 5.2.3: Hierarchical Structure of Learned Skills, Scan-paths, Saliency Map of Activities and Commu- nication Interfaces
This document describes the progress status of the research on Hierarchi- cal Structure of Learned Skills, Scan-paths, Saliency Map of Activities and Communication Interfaces performed by the NIFTi Consortium. As per the description of work, the research reported in this document concerns the WP5 for the Year 2 of the NIFTi project. Planned work is introduced and the actual work is discussed, highlighting the relevant achievements, how these contribute to the current state of the art and to the aims of the project.
File DR 6.2.3: Trajectory analysis: principle and evalua- tion
One of the main objectives of NIFTi is to have an Unmanned Ground Vehicle (UGV) explore a disaster area. This requires specific motion capabilities around which the NIFTi UGV has been designed. Additionally to these physical capabilities, controlling robot motion in unstructured and uneven terrain implies powerful analysis and control algorithms. This report presents the results of WP6, focusing on trajectory analysis during year 2. First, we investigated the kinematic model of the robot, which is the relationship between the desired motion and control variables on one hand, and between the actual motion and sensor measurement on the other hand. Then we propose a method for gap detection and traversal. Finally we present a complete framework for 3D navigation.
File DR 7.2.4: Integration and end-user evaluation for human-assisted exploration
This document describes the integration of the second prototype of the NIFTi robot and its evaluation performed at SFO Montelibretti, Italy.
File DR 8.2.4: Proceedings of the First NIFTi Autumn School on ‘Human-Robot Cooperation’ 2011
DR8.2.4 describes the eration’. The NIFTi Autumn School was organized by TNO and consisted of 5 days, from November 7th until November 11th, 2011. The goal of this autumn school was two-fold. First, students are intro- duced to theories and technology related to different aspects of human-robot interaction and cooperation. Lectures will be given by leading scientists working in human-robot interaction and robotics. The lecturers have been chosen because of their interest in advanced interaction technologies, user interface design, computer vision, human factors, strategies for adaptive mul- timodal team communication, flexible robot planning, and spatio-temporal models for situation awareness. Second, the students gain hands-on expe- rience with project components, and integration methodology, by working in multi-disciplinary teams on assignments. About 30 phd-students from all around Europe attended the autumn school.
Document Actions