Italy

Deep Learning (DL) based methods for object detection achieve remarkable performance at the cost of computationally expensive training and extensive data labeling. Robots embodiment can be exploited to 
mitigate this burden by acquiring automatically annotated training data via a natural interaction with a human showing the object of interest, handheld. However, learning solely from this data may introduce biases (the so-called domain shift), and prevents adaptation to novel tasks. While Weakly-supervised Learning offers a well-established set of techniques to cope with these problems in general-purpose Computer Vision, its adoption in challenging robotic domains is still at a preliminary stage. In this work, we target the scenario of a robot trained in a teacher-learner setting to detect handheld objects. The aim is to improve detection performance in different settings by letting the robot explore the environment with a limited human labeling budget. We compare several techniques for WSL in detection pipelines to reduce model re-training costs without compromising accuracy,
proposing solutions which target the considered robotic scenario. We show that the robot can improve adaptation to novel domains, either by interacting with a human teacher (Active Learning) or with an autonomous supervision (Semi-supervised Learning). We integrate our strategies into an on-line detection method, achieving efficient model update capabilities with few labels. We experimentally benchmark our method on challenging robotic object detection tasks under domain shift.

IEEE RO-MAN 2022

From Handheld to Unconstrained Object Detection: a Weakly-supervised On-line Learning Approach

**31st IEEE International Conference on Robot & Human Interactive Communication**
 This conference is a leading forum where state-of-the-art innovative results, the latest developments as well as future perspectives relating to robot and human interactive communication are presented and discussed.
 
 The conference covers a wide range of topics related to Robot and Human Interactive Communication, involving theories, methodologies, technologies, empirical and experimental studies. Papers related to the study of robotic technology, psychology, cognitive science, artificial intelligence, human factors, ethics and policies, interaction-based robot design and other topics related to human-robot interaction are welcome.
 
 **CONFERENCE THEME:**
 Social, asocial, and antisocial robots
 
 Robots are starting to populate our lives: at work, in our homes, hotels, shops. However, not everybody is comfortable with robots finding a place in society. For example, people may be afraid that robots will replace humans in their jobs. This belief is exacerbated by the media that, on one side, raise expectations of robots’ capabilities, while amplifying fears and worries on the other side.
 
 In the next years, due to the increasing request for interaction with people in social environments, academic research and market analyses predict that robots will become more and more “social”. But, at the same time, robots may incur the risk of being perceived as “asocial” as their pervasiveness in everyday environments may become an obstacle to social interaction between humans. Or they may even be rejected as “antisocial” if researchers do not take care to develop robots that behave according to the customs and habits of the communities where they are expected to operate.
 
 To prevent this from happening, robotic researchers can no longer take the luxury of being mere technicians. They must be capable of addressing all the challenges raised by future robot-populated communities in a multidisciplinary way. They need to share their knowledge with the public to make people aware of what robots really are, what expectations we can have from them, the risks we may incur, and the possible mitigation plans.
 
 While being open to any kind of contribution related to Human-Robot Interactive Communication, the RO-MAN 2022 conference will emphasize these aspects of robotic research. How can we create robots capable of being welcomed as our assistants and companions in society while, at the same time, not being perceived as “asocial” or “antisocial?” How can we create robots perceived as facilitators of the natural development of human beings and communities, rather than obstacles?
 
 Contributions from different disciplines, not exclusively related to technological development, will be welcomed as crucial to pave the way to global acceptance of future robots with an informed attitude.
 
 [![](https://assets.underline.io/uploads/markdown_image/1/image/af259abe105b3791c498ae1552d75710.png)](https://drive.google.com/file/d/18w73BZPB_JVOgcrcdZDqYpEupwVt4CnU/view?usp=sharing)

A registration is required to access this event page. If you have not already done so, please use the below link to register for the event. 

[Register Here](http://www.smile.unina.it/ro-man2022/welcome-to-ieee-ro-man-2022/)

Registration Is Required

31st IEEE International Conference on Robot & Human Interactive Communication
This conference is a leading forum where state-of-the-art innovative results, the latest developments as well as future perspectives relating to robot and human interactive communication are presented and discussed.

technical paper

The increasing growth of robots and other technological devices in homes makes it critical to understand child-device interactions within the home, especially given the real possibility of child aggression towards these devices. 
To explore factors that currently and will, in the future, shape child-robot interaction in the home related to children's aggressive behavior, we conducted a 2 x 3 x 3 between-subjects crowdsourced study (N = 332) that examined how parents would respond and perceive their child interacting with different technological devices. Participants were shown a video clip of a person interacting with a technological device (robot, smart speaker, or tablet), exhibiting either aggressive or neutral behavior, and interacting with the device in one of three interaction modalities (audio, physical, or audio+physical). Imagining that the person in the video was their child, parents who observed aggressive behavior compared with neutral behavior indicated greater concern, a higher likelihood to intervene, distinct intervention methods, a higher perception of device mistreatment, and greater sympathy for the device. Despite hypothesizing that the robot would be seen as the most anthropomorphic, animate and, warm device, participant ratings of the robot were no different than the smart speaker, however, both devices were rated more highly on those dimensions than the tablet.

The Effects of Interaction Strategy and Robot Intent on Shopping Behavior

Human-Robot Interfaces (HRIs) represent a crucial
component in telerobotic systems. Body-Machine Interfaces
(BoMIs) based on body motion can feel more intuitive than
standard HRIs for naive users as they leverage humans’ natural
control capability over their movements. Among the different
methods used to map human gestures into robot commands,
data-driven approaches select a set of body segments and
transform their motion into commands for the robot based
on the users’ spontaneous motion patterns. Despite being a
versatile and generic method, there is no scientific evidence
that implementing an interface based on spontaneous motion
maximizes its effectiveness. In this study, we compare a set
of BoMIs based on different body segments to investigate this
aspect. We evaluate the interfaces in a teleoperation task of a
fixed-wing drone and observe users’ performance and feedback.
To this aim, we use a framework that allows a user to control
the drone with a single Inertial Measurement Unit (IMU) and
without prior instructions. All the interfaces are entirely data-driven
and depend on the user’s spontaneous motion. We show
through a user study that selecting the body segment for a
BoMI based on spontaneous motion can lead to sub-optimal
performance. Based on our findings, we suggest additional
metrics based on biomechanical and behavioral factors that
might improve data-driven methods for the design of HRIs.

Parental Attitudes, Trust, and Comfort with Using Robots for Providing Care to Children with Developmental Disabilities

Using robot manipulators in contexts where it is undesirable or impractical for humans to physically intervene is crucial for several applications, from manufacturing to extreme environments. However, robots require a high degree of intelligence to operate in those environments, especially if they are not fully structured. 
Teleoperation compensates for this limitation by connecting the human operator to the robot using human-robot interfaces. The remotely operated sessions can also be used as demonstrations to program more powerful autonomous agents.
In this article, we report a thorough user study to characterise the effect of simple vibrotactile feedback on the performance and cognitive load of the human user in performing teleoperated. grasping and manipulation tasks. The experiments are performed using a portable and affordable bilateral teleoperation system that we designed, composed of a Leap Motion sensor and a custom-designed vibrotactile haptic glove to operate a 4-fingered robot hand equipped with 3-axis force sensors on the fingertips; the software packages we developed are open-source and
publicly available. Our results show that vibrotactile feedback improves teleoperation and reduces cognitive load, especially for complex in-hand manipulation tasks.

Creating Informative and Successful Human Robot Interaction in a Real-World Service Environment

In order to test how explanations affect a user working together with a collaborative robot, we created a test scenario where a user sorts trash together with a collaborative robot. Sometimes the robot is not able to fulfill its part of the task. Different modalities (textual, graphical, both) for explaining this error to the user are tested in a between subjects design and the effects on task performance, cognitive load and trust are analyzed.

Giving Social Robots a Conversational Memory for Motivational Experience Sharing

In health care, social care robots might approach humans more closely and sensitively than ever before. It is, therefore, essential to ensure that patients trust and accept them. Since hospital stays often offer only little time to gain experience interacting with a robot, it is important to identify strategies to strengthen the building of trust right from the first contact. One construct promoting trust in human-human interaction is self-disclosure. The aim of this study is to examine whether it also has a trust-promoting effect in human-robot interaction. Therefore, a study was conducted where subjects experienced a hospital scenario: A social care robot introduced itself, either just listing its tasks or additionally sharing personal information about itself. It was investigated whether a self-disclosing care robot is perceived as more trustworthy, anthropomorphic, likeable, and perceived as mindful, as well as more likely to be accepted than a robot that did not do so. A content analysis of the reasons for acceptance was conducted, as well as a semantic analysis of the adjectives used to describe the robot. 
The quantitative analysis revealed no significant difference between the introductions for the variables trust, acceptance, anthropomorphism, likeability, and mind perception. Descriptive data indicate a possible positive impact of self-disclosure on acceptance and likeability. In the self-disclosure condition, trust in technology was most often cited as a reason for accepting the robot. In the low self-disclosure condition, concerns about possible errors of the robot were mentioned most often. The most frequent reason for acceptance was a potential relief for nursing staff.

Exploring the influence of culture and gender on older adults’ perception of polite robots

This article analyzes various kinds of interactional trouble occurring in task-oriented human-robot interaction. We focus on users' repair strategies, typically used for maintaining communication in social interaction. We use an existing dataset consisting of 36 video-recordings of elderly people completing a lengthy health survey with a Pepper robot. Miscommunication was abundant in the data, with some types of repair being more common than others. These were mainly related to “hearing trouble” on the side of the robot, leading to participants’ repeats and rephrasings. Interactional trouble was also found to escalate, with multiple repair initiations, sometimes leading to “second best answers”. This appeared to be a strategy for participants to avoid repair in the service of progressivity. Overall, miscommunication and repair in these task-oriented human-robot interactions require substantial adaptation from the human.

Perception of Physical and Virtual Agents: Exploration of Factors Influencing the Acceptance of Intrusive Domestic Agents

Finding effective grasp strategies constitutes one of the main challenges in robotic manipulation, especially when
using soft, underactuated, and non-anthropomorphic hands.

Learning Grasping Strategies for a Soft Non-Anthropomorphic Hand from Human Demonstrations

We develop and evaluate two human-robot handover controllers that allow end-users to specify timing parameters for the robot reach motion, and that provide feedback if the robot cannot satisfy those constraints. 
End-user tuning with feedback is a useful controller feature in settings where robots have to be re-programmed for varying task requirements but end-users do not have programming knowledge. 
The two controllers we propose are both receding-horizon controllers that differ in their objective function, and their user specified parameters, and subsequently their user-interface: 
One controller uses a minimum cumulative jerk (MCJ) objective function, and the other a minimum cumulative error (MCE) objective function. 
We implemented the controllers on a collaborative robot and conducted two controlled experiments to compare the user experience and performance of these controllers vis-à-vis a baseline proportional velocity (PV) controller. 
In each experiment, participants ($n=30$) interactively tuned the controller parameters, and collaborated with a robot to perform a time-constrained repetitive task. 
We found that the timing controller with the MCE implementation can provide a better user experience, both while setting the parameters ($p=0.011$) and performing the handovers with the robot ($p<0.001$), and fewer failures ($p=0.016$) compared to the PV controller, however the MCJ implementation did not provide better user experience compared to the PV controller.
The MCJ controller also resulted in more failures than the PV controller.
These results could inform the design of usable and effective end-user configurable controllers for human-robot interaction.

Transparent Learning from Demonstration for Robot-Mediated Therapy

Humanoid robots provide a unique opportunity for personalized interaction using emotion recognition. However, emotion recognition performed by humanoid robots in complex social interactions is limited in the flexibility of interaction as well as personalization and adaptation in the responses. We designed an adaptive learning system for real-time emotion recognition that elicits its own ground-truth data and updates individualized models to improve performance over time. A Convolutional Neural Network based on off-the-shelf ResNet50 and Inceptionv3 are assembled to form an ensemble model which is used for real-time emotion recognition through facial expression. Two sets of robot behaviors, general and personalized, are developed to evoke different emotion responses. The personalized behaviors are adapted based on user preferences collected through a pre test survey. The performance of the proposed system is verified through a 2-stage user study and tested for the accuracy of the self-supervised retraining. We also evaluate the effectiveness of the personalized behavior of the robot in evoking intended emotions between stages using trust, empathy and engagement scales. The participants are divided into two groups based on their familiarity and previous interactions with the robot. The results of emotion recognition indicate a 12% increase in the F1 score for 7 emotions in stage 2 compared to pre-trained model. Higher mean scores for trust, engagement, and empathy are observed in both participant groups. The average similarity score for both stages was 82% and the average success rate of eliciting the intended emotion increased by 8.28% between stages, despite their differences in familiarity thus offering a way to mitigate novelty effect patterns among user interactions.

Premium content

From Handheld to Unconstrained Object Detection: a Weakly-supervised On-line Learning Approach

Downloads

Next from IEEE RO-MAN 2022

The Effects of Interaction Strategy and Robot Intent on Shopping Behavior

Similar lecture

Wizards in the Middle: An Approach to Comparing Humans and Robots