United States

Making an agent’s intentions clear from its observed behavior is crucial for seamless human-agent interaction and for increased transparency and trust in AI systems. Existing methods that address this challenge and maximize legibility of
behaviors are limited to deterministic domains. We develop a technique for maximizing legibility in stochastic environments and illustrate that using legibility as an objective improves interpretability of agent behavior in several scenarios. We provide initial empirical evidence that human subjects can better interpret legible behavior.

IEEE RO-MAN 2021

A Virtual Reality-Based Framework for Enhancing Walking Abilities Using Exoskeleton

legibility

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. 

panel

This trial tested a social robot to help deliver a low-intensity problem-solving session for students around study-related issues. In the trial, 72 students reported good ratings for emotional reaction to the robot, perceived utility, intention to use the robot again, confidence to use the robot, and perceived helpfulness from the robot. One week later, most students reported that the robot session helped them to fix their chosen issue, and that they used at least one idea from the session.

A Robot-Delivered Program for Low-Intensity Problem-Solving Therapy for Students in Higher Education

In this paper, we report that how much the presence of a robot increases the rate of valid responses in a questionnaire survey. We conducted a field experiment in which two conditions were compared: one with a robot and one without a robot. 
The result shows the potential that a robot can attract people’s attention and increase the response rates. However, the effect was small and short-term.


Hierarchical Motion Planning Framework for Manipulators in Human-Centered Environments

This project aims at designing a Series Elastic Actuator for an active upper limb exoskeleton to be used directly in the workplace. The design we studied is based on linear springs and developed a theoretical method that allowed us to select the springs based on the application requirements. The higher purpose is to prevent work-related musculoskeletal diseases by assisting workers in their daily job, reducing muscular fatigue in the upper limb when performing tasks involving arm elevation and weight-lifting.

Tell me more! A Robot’s Struggle to Achieve Artificial Awareness

We propose a systematic approach to regularize RNN-based sequential prediction by incorporating domain knowledge with logic constraints. We apply two methods - adding a layer after the hidden unit and combining class probabilities to improve the standard sequential prediction model. We confirm the effectiveness of our methods on surgical activity detection.

Physiological Data-Based Evaluation of a Social Robot Navigation System

Real world environments require us to consider the possibility of deception when evaluating human intent. We propose an end-to-end system which uses changes in facial expressions to predict deceptive intent and show that it matches human performance on the task.



Social norms and cooperation in a collective-risk social dilemma:comparing reinforcement learning and norm-based approaches

While VR is a useful evaluation tool for HRI, it has been concerned that the human behavior may differ between VR and real environments due to the differences in cognitive characteristics. We investigated the differences of human behavior in real and VR condition for searching of hidden objects and precious manipulation. We found that precious manipulation task requires longer time in VR condition, and subjects tend to change their head posture during object search and manipulation. We also discuss the feasibility to use the findings in robot competitions.

A Two-Layered Approach to Adaptive Dialogues for Robotic Assistance

Faces are important in any interaction. It is the focal point of the interaction. In the experiment with interactive robotic art installation, we found no significant differences between distance mode, animacy, likeability, and safety before and after the interaction across the three conditions. The findings necessitate further consideration of the currently widely held belief on the utility of robot faces for successful HRI, particularly when the robot can generate attention-driven motion primitives.

Usability Test of Master Devices for Robotic Vascular Intervention Procedure

Novel framework to create legible movements in multi-party interactions

Human robot skill transfer systems for mobile robot based on multi sensor fusion

We present Cozmo behaviors that could function as the action space of a future robot learning strategy, evaluated via an online video-based study with N = 113 participants. Participants' ratings generally match the intended valence and energy level, and valence strongly affects interaction appeal, trustworthiness, and safety. Facial expression and loudness acted as important covariates, which may help generalize these results to other behaviors and robots. These results can benefit those who are interested in robot emotional expression and assistive robots.

Designing and Validating Expressive Cozmo Behaviors for Accurately Conveying Emotions

This study proposes a novel measurement of the perceived assertiveness of a robot using both objective assessment of a person’s compliance to a robot’s suggestions in a math quiz task and subjective assessments of a person’s perception and expectation of a robot in different hypothetical scenarios. The proposed measurement evaluates perceived assertiveness of a robot in three dimensions
inspired by social behavioral studies on human-human interaction, namely social assertiveness, directiveness, and independence.


Premium content

A Virtual Reality-Based Framework for Enhancing Walking Abilities Using Exoskeleton

Downloads

Next from IEEE RO-MAN 2021

A Robot-Delivered Program for Low-Intensity Problem-Solving Therapy for Students in Higher Education

Similar lecture

Analysis on interaction experiences with intelligent technology and preference of technology use in nursing care

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES