Title : Supporting Human-Robot Teams in Space Missions using ePartners and Formal Abstraction Hierarchies
| Presenter | Tibor Bosse |
| Abstract | In this WAI talk, I will present the results of a cool project (in the domain of space missions) in which I participated during my 6-month visit to TNO in 2015. The abstract is as follows: "Human space flight is a prototypical example of a complex, dynamic, and safety-critical domain in which missions are performed by collaborative teams of humans and technical systems. In such domains, intelligent electronic partners (ePartners) can play a useful role in supporting human-robot teams in their problem solving process whenever a non-nominal situation is encountered. To enhance the supportive capabilities of such ePartners, this paper presents an approach to formally represent the functionality of human-robot teams in terms of different levels of abstraction. By establishing formal relations between domain knowledge at different abstraction levels and introducing reasoning rules to navigate through these relations, ePartners are endowed with a number of supportive functions, such as the ability to reason about the mission status, make suggestions in non-nominal situations, and provide explanations. The approach is applied to a use case in the context of a manned space mission to Mars. It has been implemented within a mobile application to assist robot-astronaut teams during space missions, and has been tested in a pilot experiment at the European Space Research and Technology Centre." |
Title : Knowledge-driven Paper Retrieval to support updating of Clinical Guidelines
| Presenter | Veruska Zamborlini |
| Abstract | I'll present about the joint work I've done with Qing (and supervisors) on using the knowledge model developed in my PhD research to support the Guideline Update task. Initial results were published in the workshop KR4HC 2016: Clinical Guidelines are important knowledge resources for medical decision making. They provide clinical recommendations based on a collection of research findings with respect to a specific disease. Since, new findings are regularly published, CGs are also expected to be regularly updated. However, selecting and analysing medical publications require a huge human efforts, even when these publications are mostly regrouped and into repositories (e.g., MEDLINE database) and accessible via a search engine (e.g PubMed). Automatically detecting those research findings from a medical search engine such as PubMed supports the guideline updating process. A simple search method is to select the medical terms that appear in the conclusions of the guideline to generate a query to search for new evidences. However, some challenges rise in this method: how to select the important terms, besides how to consider background knowledge that may be missing or not explicitly stated in those conclusions. In this paper we apply a knowledge model that formally describes elements such as actions and their effects to investigate (i) if it favors selecting the medical terms to compose queries and (ii) if a search enhanced with background knowledge can provide better result than other methods. This work explores a knowledge-driven approach for detecting new evidences relevant for the clinical guideline update process. Based on the outcomes of two experiments, we found that this approach can improve the recall by retrieving more relevant evidences than previous methods. |