United States

This work investigates how trust, understanding between a human operator and a robot, and the Locus of Control personality trait, evolve and affect Human-Robot Interaction in mixed-initiative robotic systems. We present the results from an experiment in which operators remotely controlled a mobile robot in navigation tasks, switching dynamically between two different levels of autonomy. Evidence suggests that operators trusted and developed an understanding of the robotic systems in mixed-initiative control, where trust and understanding increased over time.

IEEE RO-MAN 2021

Trust, Shared Understanding and Locus of Control in Mixed-Initiative Robotic Systems

locus of control

mixed-initiative

human-robot teaming

human-robot interaction

trust

RO-MAN 2021's theme is trustworthiness and cooperation. We chose this term well before the pandemic put the world on edge and added a new reason for us to question our own personal safety when in the company of others. But what about in the company of social robots? What would cause us to trust, or not trust, them? How do we as researchers create that feeling, that critical component of any relationship? With social robots, it is of course largely in our power to design the physical form, the control code and the interface software to maximize trustworthiness, facilitate cooperation and enhance the quality of human-robot interaction. This theme also touches upon people's expectations and perceptions of robots, as well as other social, cognitive and cultural factors that will influence human-robot interactions. We will have a special session/track on this topic, invite targeted submissions and include plenary speakers who are specialist in this area. We sincerely hope that this focus will help enlighten the design-thinking of all of us as we fabricate and program our own various systems.

To access RO-MAN Virtual 2021, [please register here.](https://ro-man2021.org/registration/)

RO-MAN 2021's theme is trustworthiness and cooperation. We chose this term well before the pandemic put the world on edge and added a new reason for us to question our own personal safety when in the company of others. But what about in the company of social robots? What would cause us to trust, or not trust, them? How do we as researchers create that feeling, that critical component of any relationship? With social robots, it is of course largely in our power to design the physical form, the control code and the interface software to maximize trustworthiness, facilitate cooperation and enhance the quality of human-robot interaction. 

technical paper

We focused on neonatal resuscitation, which is difficult to train clinically, and our long- term goal is a neonatal resuscitation training system that can simulate cases and can feedback interactively based on quantitative evaluation of the procedures. In this study, we developed the neonatal simulator that has a respiratory movement simulating mechanism and a chest compression measurement mechanism. Through an interview with neonatologists, the fidelity of respiratory movements and the possibility of evaluating chest compression with the developed simulator were assessed.

Robocentric Conversational Group Discovery

For remote telesurgery, the bandwidth requirement can be reduced by transferring atomic surgical actions (“surgemes") instead of the low-level kinematic information. However, such a policy requires accurate recognition of these surgemes. Surgeme recognition requires the surgical data for training the classifier. In this paper, we employ transfer learning to reduce the data requirement by transferring knowledge from training task (peg-transfer) to a surgical task (debridement). With different ablations we demonstrate that tranfer learning requires 40% less data than with no-transfer.

Dexterous Skill Transfer between Surgical Procedures for Teleoperated Robotic Surgery

In a world where applications of human-robot interaction are beneficial for our society in many aspects, robots sometimes need to mimic our behavior and body expressions. To achieve this, we present a novel framework for motion retargeting (i.e., transferring human motion) to humanoid robots by implementing pose estimation, an efficient and practical method of motion capture from just videos of the human based on computer vision and deep learning approaches.

A Bistable Soft Gripper with Mechanically Embedded Sensing and Actuation for Fast Grasping

This paper argues for the possibility of e-friendship, a form of friendship between humans and silicon-based electronic agents, with a focus on sociable robots. Section I introduces the topic. Section II defines "e-friendship." Sections III and IV identify qualities humans and silicon-based systems require for e-friendship. Section V defends the proposal against objections.

Exercising with an “Iron Man”: Design for a Robot Exercise Coach for Persons with Dementia

In this paper we analyze the text of 20000+ technical robotics papers in order to identify the visions and values that are embedded in our papers. We identify themes of visions, the relative presence of different visions and values - taking care to consider explicitness, language strategies and relevant literature in STS and HRI. We draw several paths forward and discussions from these insights.

Normative roboticists: the visions and values of technical robotics papers

In this study, we examined whether the likelihood of attributing intentionality to robots is influenced by the human-likeness of errors during HRI. To this end, we designed an experimental protocol in which users performed a melody in a joint task with the iCub robot. We programmed the iCub robot to make an error in 60% of the repetitions. Before and after the joint musical task, we administered the InStance Test to evaluate the likelihood of treating the robot as an intentional agent. Results showed that mechanical errors during HRI reduced intentionality attribution toward the robot.

Effects of Erring Behavior in a Human-Robot Joint Musical Task on Adopting Intentional Stance Toward the iCub Robot

We aim to improve the believability of virtual players by incorporating personalities, moods, and emotions for them. We propose a novel framework for a multi-player VR Volleyball game by integrating various behavioral changes during gameplay. This is achieved by simulating player reactions and rendering changes in the player's body postures, which are dependent on game environment parameters and scenarios. We showcase visual analysis of individual players' mood changes during gameplay to further corroborate the presented VR framework. Incorporating the proposed model, we exhibit the progression and variations in moods for players with different personalities when presented with varied game situations.

Rate My Robot: The effect of Word-of-Mouth (WOM) on perceptions of a social robot’s teaching performance

Within the present research, nine different communication strategies were examined for a service robot. The communication style (humanlike friendly, humanlike professional, machinelike) and modality (auditive male, auditive female, visual) of communication was varied and their influence on system evaluation regarding competence, warmth, discomfort, embodiment and preferences were investigated in an online study. The results of the study indicate that a humanlike communication is rated more competent, warmer, less discomforting, and is generally preferred.

“Oh no, my instructions were wrong!” An Exploratory Pilot Towards Children’s Trust in Social Robots

Respecting personal spaces of other people is something we also expect from robots. But what if robots need to invade our personal space, for example when several people are talking and there is no way for the robot to get around them? In a user study, we investigated the influence of different behaviors of a robot of traversing these people on the perception of the participants.

Do You Mind if I Pass Through? Studying the Appropriate Robot Behavior when Traversing two Conversing People in a Hallway Setting

We tested a new method for presenting natural materials using an electrostatic tactile texture display. In this method, we combined Coulomb friction as physical model for low frequency friction and texture-induced vibration model for high frequency friction. In a condition where only the low-frequency friction force components were rendered, the materials were correctly recognized at 70%. In contrast, when the high-frequency components were superposed, this rate increased to 80%. Therefore, Coulomb friction model plus fine texture improves material discrimination accuracy.

Downloads

Next from IEEE RO-MAN 2021

Robocentric Conversational Group Discovery

Similar lecture

Goal Density-based Hindsight Experience Prioritization for Multi-Goal Robot Manipulation Reinforcement Learning

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from IEEE RO-MAN 2021

Robocentric Conversational Group Discovery

Similar lecture

Goal Density-based Hindsight Experience Prioritization for Multi-Goal Robot Manipulation Reinforcement Learning

Downloads