Abstract : Autonomous agents have been increasingly used for military operations (e.g., casualty extraction, explosive detection and disposals, reconnaissance and surveillance, supply transportation, building clearing, and firefighting), search and rescue, transportation safety, space exploration, farming, and many other purposes yet to emerge (Barnes and Evans, 2010; Greenemeier, 2010; Jones and Schmidlin, 2011; Morals and the Machine, 2012; Murphy and Burke, 2010; Osborn, 2011; Purdy, 2008; Singer, 2010). As these agents become more sophisticated and independent, it is critical for their human counterparts to understand their behaviors, the reasoning process behind those behaviors, and the expected outcomes to properly calibrate their trust in the systems and make appropriate decisions (de Visser et al., 2014; Lee and See, 2004). Indeed, past studies have shown that human operators sometimes question the accuracy and effectiveness of agents actions due to the operators difficulties understanding the state/status of the agent (Bitan and Meyer, 2007; Seppelt and Lee, 2007; Stanton et al., 2007) and the rationales behind the behaviors (Linegang et al., 2006). These limitations can be substantial impediments to overall system and task performance.
Stored only when both papers are in the corpus — 296 citations exist upstream.