Personal tools
You are here: Home Results PDFs of PUBLIC year 4 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 4 deliverables

File DR 1.4.4: Spatio-temporally grounded situation awareness using a-priori information
Search and Rescue tasks are tackled in NIFTi with a team of robots and human operators. They take place in specific environments outside of research laboratories and require good communication between robots and users. This relies on a common understanding of space. This report presents the results of year 4 development in work package 1 on spatio-temporal modeling for situation awareness and, more specifically, the work, following DR1.3.3, to achieve spatio-temporally grounded conceptual descriptions of USAR sites (MS1.5). We notably continued to integrate multi-modal sensory information both for data fusion and efficient transmission and building up traversability maps for rescue environments. Finally, we worked on functional and conceptual mapping to aid collaborative exploration in unstructured environments with adaptive spatial beliefs.
File DR 4.4.4: Summative evaluation and theory of the setting-up and usage of adaptive HRI
WP4 aims at enhanced effectiveness and efficiency of joint human-robot exploration by dynamic task load distribution among rescuers and robots, preventing overload and optimizing attention allocation. In year 4, we focused on the integration of the prototype components into an integrated, operational system. The cognitive task load model and the team awareness display were integrated into the NIFTi system, providing the (adaptive) working agreement policies, personalized views on the current (shared) knowledge-base (i.e. supporting situation and team awareness), and context- sensitive information exchanges (e.g., ”smart questions”). In addition, 3D eye-tracking experiments were conducted to further develop computational visual attention models aimed at solving top-down search tasks. We applied the methodology for situated Cognitive Engineering (sCE) during the 4 years of the NIFTi project to establish a requirements baseline with a sound and practical design rationale. Over the years, NIFTi-robots’ level of autonomy, user model, and team membership were enhanced for disaster management scenarios with increasing scale and complexity (from tunnel and train accident to earth quake). The current requirements baseline, with its design rationale, provides a sound basis for (1) implementing state-of-the-art collaborative rescue robots, and (2) further developing of such robots with higher levels of persistence. The last year, we extended the sCE-methodology by incorporating interaction design patterns that provide a structured format to capture and share design knowledge on the communication level (i.e. the shape of the interaction).
File DR 8.4.6: Updated market analysis for USAR robots with HRI
This report serves for orientation on the current robotics market, with a specific focus on the USAR-relevant segment. It helps us to place the NIFTi UGV and UAV prototypes and the end user requirements it is based on, relative to potential competitors. Regarding UGVs, this reports provides an update of the market analysis of USAR robots with HRI which we conducted in Year 1. We again focus on man-portable robots, suitable for reconnaissance & mapping missions in Urban Search & Rescue. We also elaborate on the HRI interfaces. Additionally we provide a survey of UAVs suitable for search&rescue. We close with a discussion of what benefits the features of the NIFTi UGV and UAV had in the Mirandola 2012 deployment.
File DR 5.4.6: Mixed initiative planning and user requests subsumption. Adaptable strategies for complying to robot-team and users requests
This document describes the progress status of the research on mixed initiative planning and user requests subsumption, focusing on the development of adaptable strategies to comply with robot-team and users requests, performed by the NIFTi Consortium. The research reported in this document concerns the WP5 for the Year 4 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 2.4.4: Scaling the functionalities of vision subsystem with the complexity of the environment
This report presents the results of WP2 for the fourth year of NIFTi.
File DR 6.4.5: Trajectory planning in dynamic unstructured environment based on 3D perceptual data: principle and evaluation
One main objective of NIFTi is to explore a disaster area using the NIFTi UGV. This robot hardware has been designed to fulfill this task. Autonomous navigation has been previously developed, but real life environment is not static and automatic re-planning in case dynamic changes should be studied and implemented. This is presented in this report, as well as the autonomous control of the UAV.
File DR 7.4.6: Integration and end-user evaluation for sharing situation awareness
This document describes the updates and integration of the fourth prototype of the NIFTi system and its evaluation performed at the training centre of VVF in Prato, Italy, for an earthquake scenario.
File DR 8.4.7: Proceedings of the NIFTi school Yr4
DR 8.4.7 describes the third NIFTi school, which was a joint event with the Rescue Camp of the 11th IEEE International Symposium on Safety Security and Rescue Robotics (SSRR). The whole symposium lasted from Oct 21st to Oct 26th and the school was its first part from Oct 21st to Oct 23rd. The school was about “perception and navigation in challenging 3D environments.” There were two goals for this school. The first was to give students state-of-the-art lectures on both perception and navigation in 3D for ground robots by invited experts. The second goal was to have students actually apply this knowledge to implement a full navigation solution on real robots in a real environment. Around 35 international students participated in this school. The participants were divided into 4 teams with a robot each (two NIFTi robots and two MESA Element robots). The teams were tasked to autonomously traverse a red-level NIST arena. Most teams were able to successfully complete the task.
File DR 3.4.4: Adaptive situated HRI for in-field joint exploration
This report presents the results of WP3 for NIFTi Year 4. We continued developing the mobile interfaces to facilitate multi-modal communication in the setup including two robots and a human team member in the field and the rest of the remotely located human team members. Based on exereince from previous experiments we extended the support for sharing pictures taken by the in-field rescuer across the whole system. We also developed an adaptive system allowing the robot to modify its spatial belief model and therefore its behavior due to violations of user expectations. We furthermore continued our work on detection and classification of stress and cognitive load in speech using data from our earlier experiments. The NIFTi multi-modal operational interfaces were used in experiments in the setting of human-assisted exploration of an earthquake site in Prato, Italy.
File DR 8.4.8: Public release of the open source NIFTi software
This document describes the project website which lists all the tools that have been developed in the project, with pointers to the background papers relative to each tool, the contact person for each tool, licensing requirements for using the tool, whether the tool is undergoing further development, and how a researcher can access code for that tool.
File NIFTi project summary
File DR 4.4.3: Validated intelligent working agreement mechanism to set-up adaptive HRI
Document Actions