Interactive Question-Posing System for Robot-Assisted Reminiscence From Personal Photographs

Commonsense knowledge in cognitive robotics: a systematic literature review

“…Why did the human want the juice and what is a fitting alternative?) • Location Detection (Welke et al, 2013): Categorize the location based on the recognized objects (e.g., the robot detects milk and juice and concludes that the location is a fridge) • Navigation (Shylaja et al, 2013;Li et al, 2022): Navigate to a specific location • Object Delivery (Lam et al, 2012;Riazuelo et al, 2013;Mühlbacher and Steinbauer, 2014;Al-Moadhen et al, 2015;Zhang and Stone, 2015;Wang et al, 2019;Yang et al, 2019): Finding the requested object and delivering it to a specific location • Object Localization (Varadarajan and Vincze, 2012b;Zhou et al, 2012;Kaiser et al, 2014;Riazuelo et al, 2015;Jebbara et al, 2018;Daruna et al, 2019;Zhang et al, 2019;Chernova et al, 2020): Finding a specific object in an (unknown) environment • Object Recognition (Daoutis et al, 2012;Pratama et al, 2014;Kümpel et al, 2020;Chiatti et al, 2022): Recognize a specific object based on its properties • Pick and Place (Al-Moadhen et al, 2013;Javia and Cimiano, 2016;Mitrevski et al, 2021): Pick an object up and place it at a different location • Reminiscence Therapy (Wu et al, 2019): Asking questions about provided pictures to get the human to remember and socialize • Table Setting (Salinas Pinacho et al, 2018;Haidu and Beetz, 2019): Set the table for a meal scenario (and maybe also clean up afterwards) • Tidy Up (Aker et al, 2012;Skulkittiyut et al, 2013): Bring a specified part of the environment in order by removing unusual objects • Tool Substitution (Zhu et al, 2015;Thosar et al, 2020;2021;…”

A Feasibility Study of a Data-Driven Human-Robot Conversational Interface for Reminiscence Therapy

“…However, the usability of the system was not evaluated in further stages. Similarly, Wu et al [19] developed an interactive questioning system for robot-assisted reminiscence. The main contributions of the study included the development of a data-driven algorithm for event recognition in images, a concept interference model (i.e., a model in charge of creating appropriate topics for the robot, considering the observable entities in the images), and an end-to-end robotic system to perform the interaction.…”

“…These challenges can be overcome with technology-based solutions that allow for the practical delivery of RT to a greater number of people [16], as well as contribute to increased engagement and personalisation [17]. Some examples are, Computer Interactive Reminiscence and Conversation Aid (CIRCA) [18] which is able to support RT by creating a natural and relaxing interaction environment, and the system presented by Wu et al [19], that uses a social robot that guides an RT session supported by intelligent interaction implemented with Convolutional Neural Networks and a Knowledge Graph.…”