Caraian, S, Kirchner, N & Colborne-Veel, P 2015, 'Moderating a Robot's Ability to Influence People Through its Level of Sociocontextual Interactivity', Proceedings of the Tenth Annual ACM/IEEE International Conference on Human-Robot Interaction, Annual ACM/IEEE International Conference on Human-Robot Interaction (HRI), ACM, Portland, Oregon, pp. 149-156.View/Download from: Publisher's site
© 2015 ACM. A range of situations exist in which it would be useful to influence people's behavior in public spaces, for example to improve the efficiency of passenger flow in congested train stations. We have identified our previously developed Robot Centric paradigm of Human-Robot Interaction (HRI), which positions robots as Interaction Peers, as a potentially suitable model to achieve more effective influence through defining and exploiting the interactivity of robots (that is, their ability to moderate their issued sociocontextual cues based on the behavioral information read from humans). In this paper, we investigate whether increasing a robot's interactivity will increase the effectiveness of its influence on people in public spaces. A two-part study (total n = 273) was conducted in both a major Australian public train station (n = 84 + 105) and a university (n = 84) where passersby encountered a robot, designed with various levels of interactivity, which attempted to influence their passage. The findings suggest that the Robot Centric HRI paradigm generalizes to other robots and application spaces, and enables deliberate moderation of a robot's interactivity, facilitating more nuanced, predictable and systematic influence, and thus yielding greater effectiveness.
Kirchner, NG, Caraian, S, Colborne-Veel, P & Zeibots, M 2015, 'Influencing Passenger Egress to Reduce Congestion at Rail Stations', Online Proceedings of the Australasian Transport Research Forum 2015, Australasian Transport Research Forum, ATRF, Sydney, Australia.
As rail station patronage levels increase, so too does the load on the entire railway system.
The higher passenger densities exacerbate local egress issues and thus adversely affect
dwell time and subsequently punctuality, along with the passenger experience. Devices such
as barriers are regularly used to influence passenger egress. However, their use is typically
limited to special events; where perhaps a single influence-objective is intended on a
relatively uniform passenger demographic. This limitation precludes such devices usefulness
for daily operations; where potentially multiple influence-objectives, which potentially change
regularly, exists. Furthermore, it is reasonable to expect a considerably less uniform
passenger demographic which perhaps includes passengers that are less receptive to
particular influence strategies.
This paper presents an exploration of components of a robotic system that is responsive to
real time person behaviours and operator’s needs. Specifically, details of our methods for
identification of the passenger demographic groups and passenger egress influencing are
presented along with results from two studies. The first study was conducted at Townhall
Station Sydney and explored our robotic system’s ability to reliably identify the passenger
demographic of individual passengers in real time. The ability of our robotic system to
influence real time egress of real in-transit passengers in situ, and the ability to responsively
moderate influence-objective based on observed characteristics was explored in the second
study which was co-located at Perth Station Perth and the University of Technology Sydney.
Finally, this paper discusses how this predictable influence of passenger egress can
potentially be leveraged to benefit operations.
Caraian, SA & Kirchner, NG 2014, 'Head Pose Behavior in the Human-Robot Interaction Space', ACM/IEEE International Conference on Human-Robot Interaction, Annual ACM/IEEE International Conference on Human-Robot Interaction (HRI), ACM, Bielefeld, Germany, pp. 132-133.View/Download from: UTS OPUS or Publisher's site
Visual Focus of Attention is an important mechanism to support successful interactions. In order to communicate effectively and intentionally (issuing cues when a person is paying attention, for example), a robot must have an understanding of this Visual Focus of Attention behavior in the Human-Robot Interaction space. A real-world interaction study was conducted with 24 unsolicited participants to explore attention behavior towards robots in this space. The results suggest there is no generalizable attention pattern between people, and thus that online, in situ Visual Focus of Attention estimation would be advantageous to Human-Robot Interaction.
Caraian, SA & Kirchner, NG 2013, 'Influence of robot-issued joint attention cues on gaze and preference', ACM/IEEE International Conference on Human-Robot Interaction, Annual ACM/IEEE International Conference on Human-Robot Interaction (HRI), IEEE, Tokyo, Japan, pp. 95-96.View/Download from: UTS OPUS or Publisher's site
If inadvertently perceived as Joint Attention, a robot's incidental behaviors could potentially influence preferences of observing humans. A study was conducted with 16 robot-näive participants to explore the influences of robot-issued Joint Attention cu
Caraian, SA & Kirchner, NG 2010, 'Robust Manipulability-Centric Object Detection in Time-of-Flight Camera Point Clouds', Proceedings of the Australasian Conference on Robotics and Automation 2010 (ACRA 2010), Proceedings of the Australasian Conference on Robotics and Automation, Australasian Conference on Robotics and Automation, Brisbane, Queensland, Australia, pp. 1-9.View/Download from: UTS OPUS
This paper presents a method for robustly identifying the manipulability of objects in a scene based on the capabilities of the manipulator. The method uses a directed histogram search of a time-of-flight camera generated 3D point cloud that exploits the logical connection between objects and the respective supporting surface to facilitate scene segmentation. Once segmented the points above the supporting surface are searched, again with a directed histogram, and potentially manipulatable objects identified. Finally, the manipulatable objects in the scene are identied as those from the potential objects set that are within the manipulators capabilities. It is shown empirically that the method robustly detects the supporting surface with +15mm accuracy and successfully discriminates between graspable and non-graspable objects in cluttered and complex scenes.
Kirchner, NG, Alempijevic, A, Caraian, SA, Fitch, R, Hordern, DL, Hu, G, Paul, G, Richards, D, Singh, SP & Webb, SS 2010, 'RobotAssist - a Platform for Human Robot Interaction Research', Proceedings of the Australasian Conference on Robotics and Automation 2010 (ACRA 2010), Proceedings of the Australasian Conference on Robotics and Automation, Australasian Conference on Robotics and Automation, Brisbane, pp. 1-10.View/Download from: UTS OPUS
This paper presents RobotAssist, a robotic platform designed for use in human robot interaction research and for entry into Robocup@Home competition. The core autonomy of the system is implemented as a component based software framework that allows for integration of operating system independent components, is designed to be expandable and integrates several layers of reasoning. The approaches taken to develop the core capabilities of the platform are described, namely: path planning in a social context, Simultaneous Localisation and Mapping (SLAM), human cue sensing and perception, manipulatable object detection and manipulation.