Hold My Hand: Development of a Force Controller and System Architecture for Joint Walking with a Companion Robot

In recent years, there has been a growing interest in the development of robotic systems for improving the quality of life of individuals of all ages. Specifically, humanoid robots offer advantages in terms of friendliness and ease of use in such applications. This article proposes a novel system architecture that enables a commercial humanoid robot, specifically the Pepper robot, to walk side-by-side while holding hands, and communicating by responding to the surrounding environment. To achieve this control, an observer is required to estimate the force applied to the robot. This was accomplished by comparing joint torques calculated from the dynamics model to actual current measurements. Additionally, object recognition was performed using Pepper's camera to facilitate communication in response to surrounding objects. By integrating these components, the system has demonstrated its capability to achieve its intended purpose.

Deep-Learning-Based Context-Aware Multi-Level Information Fusion Systems for Indoor Mobile Robots Safe Navigation

Hazardous object detection (escalators, stairs, glass doors, etc.) and avoidance are critical functional safety modules for autonomous mobile cleaning robots. Conventional object detectors have less accuracy for detecting low-feature hazardous objects and have miss detection, and the false classification ratio is high when the object is under occlusion. Miss detection or false classification of hazardous objects poses an operational safety issue for mobile robots. This work presents a deep-learning-based context-aware multi-level information fusion framework for autonomous mobile cleaning robots to detect and avoid hazardous objects with a higher confidence level, even if the object is under occlusion. First, the image-level-contextual-encoding module was proposed and incorporated with the Faster RCNN ResNet 50 object detector model to improve the low-featured and occluded hazardous object detection in an indoor environment. Further, a safe-distance-estimation function was proposed to avoid hazardous objects. It computes the distance of the hazardous object from the robot's position and steers the robot into a safer zone using detection results and object depth data. The proposed framework was trained with a custom image dataset using fine-tuning techniques and tested in real-time with an in-house-developed mobile cleaning robot, BELUGA. The experimental results show that the proposed algorithm detected the low-featured and occluded hazardous object with a higher confidence level than the conventional object detector and scored an average detection accuracy of 88.71%.

Field Trial of a Shopworker Robot with Friendly Guidance and Appropriate Admonishments

We developed an admonishing service for a shopworker robot and conducted a field trial to investigate the impressions of a shop’s staff and customers. Applying the admonishing service in a real-world robot is difficult due to the high risk of rejection by society. We wanted to achieve an acceptable admonishing service while simultaneously avoiding the impression of a forceful request from a machine. We proposed a harmonized design that provided friendly and admonishing services. First, we interviewed a shop’s staff to learn their strategies for both friendly and admonishing services. From our evaluation of the interview results, we derived three design principles: friendly impressions, zero erroneous admonishments, and polite requests. Based on the design principles, we implemented our harmonized design on a social robot that guides customers to product locations and admonishes those who are not wearing face masks. We conducted a 13-day field trial in a retail shop and interviewed the customers and shopworkers to learn their impressions of our robot. The results of the field trial imply that our harmonized design approach is successful. Both the customers and the shop staff had overall positive impressions of the robot, its admonishing and friendly services, and expressed an intention to use it in the future. Furthermore, we studied the robot’s autonomous service-providing capability in the field and conducted an evaluation with hired participants to deepen our study of the robot’s mask recognition capability.

The Influence of Robot Designs on Human Compliance and Emotion: A Virtual Reality Study in the Context of Future Public Transport

As robots enter everyday environments, they start performing tasks originally performed by humans. One field of application is the public transport sector. The deployment of autonomous transport systems comes with a lack of human contact persons for help, guidance, and crowd management. This elicits challenges regarding redirecting and managing passengers. Current solutions on platforms can be replaced or enriched with service robots whose task includes crowd management as well as social interaction. This study investigates how the human-likeness of a robot influences the compliance and emotions of public transport users. A Virtual Reality experiment was conducted (N=33) to evaluate two different robot designs in a bus stop boarding scenario. The two robot designs differ in terms of humanoid appearance. In different experimental trials, participants had to perform a given task that was nullified by instructions from one of the two robots. Additionally, the dissonance of the situation was altered so that the environment either justified the robot's interference or not. Compliant behavior, pleasure, and arousal ratings, as well as task processing times were recorded. The experiment included an individual interview and a post-study questionnaire. The results suggest that future deployment of service robots has the potential to redirect passengers. In dissonant situations, clear reasoning must be given to make the robot effective. However, the robot's visual appearance has a more substantial impact on arousal and subjective preferences than on evoked behavior. The study implies that the presence of a service robot can influence peoples’ choices and gives hints about the importance of giving a reason. However, objectively, the level of the robot's humanoid appearance did not make a difference.

Alignment of the attitude of teleoperators with that of a semi-autonomous android

Studies on social robots that can communicate with humans are increasingly important. In particular, semi-aautonomous robots have shown potential for practical applications in which robot autonomy and human teleoperation are jointly used to accomplish difficult tasks. However, it is unknown how the attitude represented in the autonomous behavior of the robots affects teleoperators. Previous studies reported that when humans play a particular role, their attitudes align with that role. The teleoperators of semi-autonomous robots also play the role given to the robots and may assimilate their autonomous expression. We hypothesized that the attitude of teleoperators may align with that of robots through teleoperation. To verify this, we conducted an experiment with conditions under which a participant operated a part of the body of an android robot that autonomously expressed a preferential attitude toward a painting and a condition under which they did not. Experimental results demonstrated that the preferential attitude of participants who teleoperated the android aligned statistically significantly more with that of the robot in comparison to those who did not teleoperate it, thereby supporting our hypothesis. This finding is novel regarding attitude change in teleoperators of semi-autonomous robots and can support the implementation of effective human-robot collaboration systems.

Understanding Impacts of Service Robots with the Revised Gap Model

The service quality gap model, which identifies the antecedents of SERVQAUL, reveals that service quality depends on the gap between customer perceived and expected service (Gap 5), which can be caused by other gaps in the service process (Gaps 1–4). The emergence of service robots has affected the quality of services provided; however, little is known about how these impacts happen. Thus, this paper aims to explore the impacts of service robots on service quality by revising the original gap model in the context of robot service. This paper reviews and analyzes the literature related to service robots and develops a revised gap model for robot service by integrating the existing research on the impacts of service robots. By introducing the roles of robots and robot manufacturers into the original gap model, the revised gap model adds three new gaps: Gap 6 (manufacturers’ understanding gap), Gap 7 (technical gap), and Gap 8 (service coordination gap). Based on the revised gap model, the impacts of service robots on service quality are expounded (i.e., Gap 5 can be affected by not only Gaps 1–4 but also Gaps 6–8), and several propositions are introduced. This paper is the first to consider robot manufacturers as part of the service quality gap model, and the first to use a dynamic model to explore the impacts of service robots on service quality. This paper not only supplements the service robot and gap model literature but also provides service companies with a meaningful framework to improve service quality when using robots to provide service.

Laser-Based People Detection and Obstacle Avoidance for a Hospital Transport Robot

This paper describes the development of a laser-based people detection and obstacle avoidance algorithm for a differential-drive robot, which is used for transporting materials along a reference path in hospital domains. Detecting humans from laser data is an important functionality for the safety of navigation in the shared workspace with people. Nevertheless, traditional methods normally utilize machine learning techniques on hand-crafted geometrical features extracted from individual clusters. Moreover, the datasets used to train the models are usually small and need to manually label every laser scan, increasing the difficulty and cost of deploying people detection algorithms in new environments. To tackle these problems, (1) we propose a novel deep learning-based method, which uses the deep neural network in a sliding window fashion to effectively classify every single point of a laser scan. (2) To increase the speed of inference without losing performance, we use a jump distance clustering method to decrease the number of points needed to be evaluated. (3) To reduce the workload of labeling data, we also propose an approach to automatically annotate datasets collected in real scenarios. In general, the proposed approach runs in real-time and performs much better than traditional methods. Secondly, conventional pure reactive obstacle avoidance algorithms can produce inefficient and oscillatory behaviors in dynamic environments, making pedestrians confused and possibly leading to dangerous reactions. To improve the legibility and naturalness of obstacle avoidance in human crowded environments, we introduce a sampling-based local path planner, similar to the method used in autonomous driving cars. The key idea is to avoid obstacles by switching lanes. We also adopt a simple rule to decrease the number of unnecessary deviations from the reference path. Experiments carried out in real-world environments confirmed the effectiveness of the proposed algorithms.