Artificial social intelligence (ASI) agents have great potential to aid the success of individuals, human–human teams, and human–artificial intelligence teams. To develop helpful ASI agents, we created an urban search and rescue task environment in Minecraft to evaluate ASI agents’ ability to infer participants’ knowledge training conditions and predict participants’ next victim type to be rescued. We evaluated ASI agents’ capabilities in three ways: (a) comparison to ground truth—the actual knowledge training condition and participant actions; (b) comparison among different ASI agents; and (c) comparison to a human observer criterion, whose accuracy served as a reference point. The human observers and the ASI agents used video data and timestamped event messages from the testbed, respectively, to make inferences about the same participants and topic (knowledge training condition) and the same instances of participant actions (rescue of victims). Overall, ASI agents performed better than human observers in inferring knowledge training conditions and predicting actions. Refining the human criterion can guide the design and evaluation of ASI agents for complex task environments and team composition.
The goal of the Space Challenge project is to identify the challenges faced by teams in space operations and then represent those challenges in a distributed human-machine teaming scenario that resembles typical space operations and to measure the coordination dynamics across the entire system. Currently, several challenges have been identified through semi-structured interviews with nine subject matter experts (SMEs) who were astronauts or those who have experienced or have been involved with interplanetary space exploration. We conducted a thematic analysis on the interviews through an iterative process. Challenges were categorized into four categories, including, communication, training, distributed teaming, and complexity. Based on the findings, challenges and key teamwork characteristics of space operations were integrated into the initial scenario development. In addition to the scenario, we plan to use dynamical system methods to analyze team activity in real time.
This study reports the current perceived use of available sources of drug information for general medical practitioners. The sample frame, of 463 GPs practising in Derbyshire, England, on January 1, 1990, provided a 74 per cent response rate to a pre‐piloted questionnaire. Two printed sources, the Monthly Index of Medical Specialities and the British National Formulary (BNF) plus one personal service, fellow colleagues, were by far the most frequently used. The estimated average minimum number of days per year on which personal information services were consulted was 28.51 days compared with 63.83 days for non‐personal, printed sources. Thus, if GPs are to be guided by independent sources then the BNF must be considered a prime vehicle. Drug information centres (DICs) were ranked last with 56 per cent of GPs having consulted such a source within the previous year. Use of DICs could not be predicted from GPs' characteristics or demographic data. Interviews with 101 of 106 randomly selected GPs generally confirmed questionnaire findings. However, only 41 per cent perceived themselves as users of DICs. Collation of queries from two local centres showed 25 per cent were known to be users. From interviews, discrepancies were seen to arise from accessing DICs outside the sample frame boundary plus confusion of DICs with poisons centres and hospital pharmacy departments. Thus, for use of DICs, questionnaire techniques may be unreliable unless source definition is considered. If using DICs, GPs very significantly had lower concurrent use of community pharmacists, GP colleagues and hospital consultants for general drug information
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.