The Perceptual Belief Problem

Abstract

The explainability of robotic systems depends on people’s ability to reliably attribute perceptual beliefs to robots, i.e., what robots know (or believe) about objects and events in the world based on their perception. However, the perceptual systems of robots are not necessarily well understood by the majority of people interacting with them. In this article, we explain why this is a significant, difficult, and unique problem in social robotics. The inability to judge what a robot knows (and does not know) about the physical environment it shares with people gives rise to a host of communicative and interactive issues, including difficulties to communicate about objects or adapt to events in the environment. The challenge faced by social robotics researchers or designers who want to facilitate appropriate attributions of perceptual beliefs to robots is to shape human–robot interactions so that people understand what robots know about objects and events in the environment. To meet this challenge, we argue, it is necessary to advance our knowledge of when and why people form incorrect or inadequate mental models of robots’ perceptual and cognitive mechanisms. We outline a general approach to studying this empirically and discuss potential solutions to the problem.

How to Communicate Robot Motion Intent: A Scoping Review

“…We excluded another 220 system design papers that focused on aspectus such as aesthetics, mathematical models of motion planning, or definitions (e.g., Girard et al [50]). Eventually, we removed four papers where no approach or prototype was developed and reported (e.g., Thellman and Ziemke [118]).…”

How to Communicate Robot Motion Intent: A Scoping Review

“…We excluded another 220 system design papers that focused on aspectus such as aesthetics, mathematical models of motion planning, or definitions (e.g., Girard et al [51]). Eventually, we removed four papers where no approach or prototype was developed and reported (e.g., Thellman and Ziemke [119]).…”

Social Robots as Intentional Agents

“…In recent years, there has been increasing interest in the human tendency and ability to treat robots as intentional agents (Perez-Osorio & Wykowska, 2020;Schellen & Wykowska, 2019;Papagni & Koeszegi, 2021, see also Paper VI of this thesis for a systematic review of the empirical literature). Researchers have investigated some of the determinants of the human tendency to attribute intentional (and other mental) states to robots, including factors such as a person's age (Manzi et al, 2020;Okanda, Taniguchi, Wang, & Itakura, 2021), various motivational determinants (Waytz et al, 2010;Perez-Osorio, Marchesi, Ghiglino, Ince, & Wykowska, 2019;Złotowski et al, 2018), robot appearance (Martini, Gonzalez, & Wiese, 2016;Abubshait, Momen, & Wiese, 2020), and robot behavior (Wallkötter, Stower, Kappas, & Castellano, 2020;Abubshait & Wiese, 2017;Terada & Yamada, 2017). Other research focused on some of the effects of attributing intentional states, including trust in robots (Mou, Ruocco, Zanatto, & Cangelosi, 2020), social attention (Wiese, Wykowska, Zwickel, & Müller, 2012;Wykowska, Wiese, Prosser, & Müller, 2014), cognitive performance (Wiese, Mandell, Shaw, & Smith, 2019), and the abuse of robots (Keijsers & Bartneck, 2018), and on what types of intentional states (and other mental states) people ascribe to robots as compared to other agents, such as humans or computers (Levin, 3For example, nations are commonly referred to as wanting to reach an agreement or as believing that a potential enemy is planning an attack, and some have even been described as "autistic" on account of their limited interaction with other states (Buzan, 1993).…”