Alle Publikationen
- <<
- <
- 1
2018
-
(2018): Long-term cohabitation with a social robot: A case study of the influence of human attachment patterns. In: International Journal of Social Robotics 10 (1), S. 163-176. DOI: 10.1007/s12369-017-0439-2
DOI: https://doi.org/10.1007/s12369-017-0439-2 Abstract: This paper presents the methodology, setup and results of a study involving long-term cohabitation with a fully autonomous social robot. During the experiment, three people with different attachment styles (as defined by John Bowlby) spent ten days each with an EMYS type robot, which was installed in their own apartments. It was hypothesized that the attachment patterns represented by the test subjects influence the interaction. In order to provide engaging and non-schematic actions suitable for the experiment requirements, the existing robot control system was modified, which allowed EMYS to become an effective home assistant. Experiment data was gathered using the robot’s state logging utility (during the cohabitation period) and in-depth interviews (after the study). Based on the analyzed data, it was concluded that the satisfaction stemming from prolonged cohabitation and the assessment of robot’s operation depend on the user’s attachment style. Results lead to first robot’s behavior personalization guidelines for different user’s attachment patterns. The study confirmed readiness of a EMYS robot for satisfying, autonomous, and long-term cohabitation with users. (PsycINFO Database Record (c) 2019 APA, all rights reserved)
2017
-
(2017): Communicating intent to develop shared situation awareness and engender trust in human-agent teams. In: COGNITIVE SYSTEMS RESEARCH 46, S. 26-39. DOI: 10.1016/j.cogsys.2017.02.002
DOI: https://doi.org/10.1016/j.cogsys.2017.02.002 Abstract: This paper addresses issues related to integrating autonomy-enabled, intelligent agents into collaborative, human-machine teams. Interaction with intelligent machine agents capable of making independent, goal-directed decisions in human-machine teaming operations constitutes a major change from traditional human-machine interaction involving teleoperation. Communicating the machine agent’s intent to human counterparts becomes increasingly important as independent machine decisions become subject to human trust and mental models. The authors present findings from their research that suggest existing user display technologies, tailored with context-specific information and the human’s knowledge level of the machine agent’s decision process, can mitigate misperceptions of the appropriateness of agent behavioral responses. This is important because misperceptions on the part of human team members increases the likelihood of trust degradation and unnecessary interventions, ultimately leading to disuse of the agent. Examples of possible issues associated with communicating agent intent, as well as potential implications for trust calibration are provided. (PsycINFO Database Record (c) 2019 APA, all rights reserved)
2016
-
(2016): Socially adaptive path planning in human environments using inverse reinforcement learning. In: International Journal of Social Robotics 8 (1), S. 51-66. DOI: 10.1007/s12369-015-0310-2
DOI: https://doi.org/10.1007/s12369-015-0310-2 Abstract: A key skill for mobile robots is the ability to navigate efficiently through their environment. In the case of social or assistive robots, this involves navigating through human crowds. Typical performance criteria, such as reaching the goal using the shortest path, are not appropriate in such environments, where it is more important for the robot to move in a socially adaptive manner such as respecting comfort zones of the pedestrians. We propose a framework for socially adaptive path planning in dynamic environments, by generating human-like path trajectory. Our framework consists of three modules: a feature extraction module, inverse reinforcement learning (IRL) module, and a path planning module. The feature extraction module extracts features necessary to characterize the state information, such as density and velocity of surrounding obstacles, from a RGB-depth sensor. The inverse reinforcement learning module uses a set of demonstration trajectories generated by an expert to learn the expert’s behaviour when faced with different state features, and represent it as a cost function that respects social variables. Finally, the planning module integrates a three-layer architecture, where a global path is optimized according to a classical shortest-path objective using a global map known a priori, a local path is planned over a shorter distance using the features extracted from a RGB-D sensor and the cost function inferred from IRL module, and a low-level system handles avoidance of immediate obstacles. We evaluate our approach by deploying it on a real robotic wheelchair platform in various scenarios, and comparing the robot trajectories to human trajectories. (PsycINFO Database Record (c) 2019 APA, all rights reserved)
- <<
- <
- 1