Robot Behavior Research Articles

Designing Behaviors of Robots Based on the Artificial Emotion Expression Method in Human–Robot Interactions

How to express emotions through motion behaviors of robots (mainly for robotic arms) to achieve human–robot emotion interactions is the focus of this paper. An artificial emotion expression method that accords with human emotion that can deal with external stimuli and has the capability of emotion decision-making was proposed based on the motion behaviors of robot. Firstly, a three-dimensional emotion space was established based on the motion indexes (deviation coefficient, acceleration, and interval time). Then, an artificial emotion model, which was divided into three parts (the detection and processing of external events, the generation and modification of emotion response vectors, and the discretization of emotions) was established in the three-dimensional emotion space. Then emotion patterns (love, excited, happy, anxiety, hate) and emotion intensity were calculated based on the artificial emotion model in human–robot interaction experiments. Finally, the influence of motion behaviors of humanoid robot NAO on the emotion expression of experimenters was studied through human–robot emotion interaction experiments based on the emotion patterns and emotion intensity. The positive emotion patterns (love, excited, happy) and negative emotion patterns (anxiety, hate) of the experimenters were evaluated. The experimental results showed that the personalized emotion responses could be generated autonomously for external stimuli, and the change process of human emotions could be simulated effectively according to the established artificial emotion model. Furthermore, the experimenters could recognize the emotion patterns expressed by the robot according to the motion behaviors of the robot, and whether experimenters were familiar with robots did not influence the recognition of different emotion patterns.

High‐performance graphics processing unit‐based strategy for tuning a unmanned aerial vehicle controller subject to time‐delay constraints

AbstractRecently, high‐performance computing strategies have been implemented to improve performance analysis and reduce the development time of new solutions in robotic applications, such as path planning, machine learning, and vision, which require massive matrix computations. In this sense, this work aims to study the aerial robots' behavior during their mission execution. Due to the large search space in the set of parameter combinations and the high computational cost required to perform such an analysis after sequentially executing thousands of simulations, this work proposes an open‐source graphics processing unit (GPU)‐based implementation to simulate the robot behavior. A GPU‐accelerated flight route analysis for multi‐unmanned aerial vehicle (UAV) systems is proposed for the tuning control problem in the parameters‘ space considering the problem of delay in sending information to a ground control station. Considering our implementation, the experimental results show a speedup up to 325, 629, and 5959 in comparison to the parallel version with 16 threads, C coder converter, and native Matlab code, respectively. The implementation is available in the Colab Google platform and it can easily be expanded for analyses involving larger amounts of different parameters, robot models, strategies, and controllers.

Signal Communication for Collaborative Robot Behavior Control

Robots are increasingly required to work in close cooperation with humans and other robots, performing common tasks jointly, in collaboration. High-level decision making by an autonomous agent with such interactions require specific means of responding to the situation. This paper describes the implementation of the control system for a collaborative robot, based on the emotion-need architecture that provides reliable and interpretable interaction means of the robot with other agents. The robot is an autonomous device whose behavior is aimed at satisfying its current needs. The communication between the operator and the robot is based on signal communication: the operator’s signal ("command") activates an element of the emotion-need scheme — a gateway that implements the emotional feedback. Since the gateway connects the sensors and behavioral procedures, its activation starts the corresponding procedure, as if the sensory system had registered a real stimulus. The external signal of such indirect control can be represented in acoustic form or as the operator’s posture. The needs of the robot are aimed at both its physical survival (danger avoidance) and maintenance of the social connections (accompanying friendly agents). The robot recognizes external commands and activates the gateway associated with the highest priority action. The activity also gradually fades, which allows actions to be performed for some time even in the absence of an appropriate internal stimulus. The resulting robot is able to perform the simplest patrol tasks together with a human, acting in a predictable and understandable (interpretable) way for the human.

Perceptions of intelligence & sentience shape children’s interactions with robot reading companions

The potential for robots to support education is being increasingly studied and rapidly realised. However, most research evaluating education robots has neglected to examine the fundamental features that make them more or less effective, given the needs and expectations of learners. This study explored how children’s perceptions, expectations and experiences are shaped by aesthetic and functional features during interactions with different robot ‘reading buddies’. We collected a range of quantitative and qualitative measures of subjective experience before and after children read a book with one of three different robots. An inductive thematic analysis revealed that robots have the potential offer children an engaging and non-judgemental social context to promote reading engagement. This was supported by children’s perceptions of robots as being intelligent enough to read, listen and comprehend the story, particularly when they had the capacity to talk. A key challenge in the use of robots for this purpose was the unpredictable nature of robot behaviour, which remains difficult to perfectly control and time using either human operators or autonomous algorithms. Consequently, some children found the robots’ responses distracting. We provide recommendations for future research seeking to position seemingly sentient and intelligent robots as an assistive tool within and beyond education settings.

Effect of Different Listening Behaviors of Social Robots on Perceived Trust in Human-robot Interactions

With the increased use of social robots in prominence and beyond functional performance, they are expected to foster trust and confidence in people. Various factors involve providing social robots with more trustworthy behavior. This study investigated whether the listening behavior of a social robot can affect the perception of being trustworthy in human–robot interaction. Therefore, we designed four different listening behaviors, including nonactive listening, active listening, active empathic listening, and verbal-only empathic listening, for a social robot and evaluated the impact of each behavior on the participants’ likelihood of trusting the robot, using a between-subject design. Participants in the four conditions conversed with a robot that simulated one of the listening behaviors, and their general, cognitive and affective trust toward the robot was measured. The results indicated that active empathic listening behavior provided the participants with the highest impression of trustworthiness, specifically in affective trust. Both active listening and active empathic listening were evaluated higher than nonactive listening in general, affective, and cognitive trust. However, active empathic listening behavior was differentiated from active listening behavior only in terms of affective trust. For verbal and nonverbal dimensions of listening behaviors, it was confirmed that nonverbal behaviors such as nodding, body movement, and eye gaze along with verbal behaviors, had a significant effect in eliciting higher affective trust in human-robot interaction. Consequently, we concluded that designing social robots with active (empathic) listening behavior can enhance trust perception in human-robot interaction in different fields such as education, healthcare, and business.

Development of robust sensor packages for autonomous underwater vehicles

New generations of robots are designed to support humans with a variety of partially or fully automated services. Such flexible and mobile service robots cooperate with humans or even act completely independent. To achieve this, it is necessary to significantly improve their capabilities in terms of environment perception, data processing and movement. At the same time, they must meet the highest standards of reliability and safety. Innovative electronics enable the necessary improvements and thus appropriate robot behavior. The aim of the Bionic RoboSkin project is to enhance the possibilities of a robot platform that is capable of autonomously navigating its respective environment by means of a flexible bionic sensor skin. The sensor platform is an autonomous underwater vehicle [AUV] that is based on the bionic principles of a Manta Ray [1, 2, 3]. The newly developed sensor skin consists of a textile composite as a carrier for sensor elements and provides moisture-resistant electrical connections for energy supply and communication. The integrated sensor modules enable both the detection of touch and approach and the exploration of the environment. The functionality of the sensor skin is targeting two service robotics applications: autonomous surveying of underwater structures (e.g. inspection of pipelines) and semi-autonomous geo-exploration in difficult-to-access areas (e.g. monitoring in tunnel construction). As a result, the paper presents the concept of a modular packaging platform for the use in a harsh marine environment. The technologies used for the miniaturization of the sensor module by PCB embedding and for outer housing development will be discussed in detail and a strong focus is put on packaging material properties in sub-marine conditions.

Codifying Wildness: Wild Behaviour for Improving Human-Robot Interaction

Animals, even when domesticated, maintain a series of innate characteristics that humans perceive as wild. Human responses to animal behavior vary with many factors such as historical time and culture. Even after their domestication, humans perceive animals’ distinctive behavior patterns that are considered as being wild, even in pets. It is common understanding that these wild patterns are linked to the specific animal species but also that there is a common characteristic to wild behavior in general. In this paper, we present our work on coding such a quality, exemplified in an application to robot pets. We consider that an application of wild character in the behavior of the pet robot can improve its realism and make the human/robot social interaction more captivating. To this aim, we have designed and implemented a behavioral architecture to reproduce well-known behavioral patterns of domestic cats that might be considered wild and applied it to a commercial pet robot that then was used to assess human reaction to its behavior. We demonstrate the effectiveness of the proposed approach with experiments carried out with humans that found the robot cat “independent” and “unpredictable” to a significant degree, two distinctive features of the wild side of animals.

Digital Twin (DT)-CycleGAN: Enabling Zero-Shot Sim-to-Real Transfer of Visual Grasping Models

Deep learning has revolutionized the field of robotics. To deal with the lack of annotated training samples for learning deep models in robotics, Sim-to-Real transfer has been invented and widely used. However, such deep models trained in simulation environment typically do not transfer very well to the real world due to the challenging problem of “reality gap”. In response, this paper presents a conceptually new Digital Twin (DT)-CycleGAN framework by integrating the advantages of both DT methodology and the CycleGAN model so that the reality gap can be effectively bridged. Our core innovation is that real and virtual DT robots are forced to mimic each other in a way that the gaps or differences between simulated and realistic robotic behaviors are minimized. To effectively realize this innovation, visual grasping is employed as an exemplar robotic task, and the reality gap in zero-shot Sim-to-Real transfer of visual grasping models is defined as grasping action consistency losses and intrinsically penalized during the DT-CycleGAN training process in realistic simulation environments. Specifically, first, cycle consistency losses between real visual images and simulation images are defined and minimized to reduce the reality gaps in visual appearances during visual grasping tasks. Second, the grasping agent's action consistency losses are defined and penalized to minimize the inconsistency of the grasping agent's actions between the virtual states generated by the DT-CycleGAN generator and the real visual states. By jointly penalizing both the cycle consistency losses and the grasping agent's action consistency losses in DT-CycleGAN, the reality gaps in both visual appearance and grasping action states in simulated and real environments are minimized, thus significantly contributing to the effective and robust zero-shot Sim-to-Real transfer of the trained visual grasping models. Extensive experiments demonstrated the effectiveness and efficiency of our novel DT-CycleGAN framework for zero-shot Sim-to-Real transfer. Our code and models are released on GitHub to facilitate other researchers' works in this promising direction <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$^{4}$</tex-math></inline-formula> .

Face to Face with a Sexist Robot: Investigating How Women React to Sexist Robot Behaviors

Face to Face with a Sexist Robot: Investigating How Women React to Sexist Robot Behaviors

Sociable Robot ‘Lometh’: Exploring Interactive Regions of a Product-Promoting Robot in a Supermarket

The robot ‘Lometh’ is an information-presenting robot that naturally interacts with people in a supermarket environment. In recent years, considerable effort has been devoted to the implementation of robotic interfaces to identify effective behaviors of communication robots focusing only on the social and physical factors of the addresser and the hearer. As attention focus and attention target shifting of people differs based on the human visual focus and the spatiality, this study considered four interactive regions, considering the visual focus of attention as well as the interpersonal space between robot and human. The collected primary data revealed that 56% attention shifts occurred in near peripheral field of view regions and 44% attention shifts in far peripheral field of view regions. Using correspondence analysis, we identified that the bodily behaviors of the robot showed the highest success rate in the left near peripheral field of view region. The verbal behaviors of the robot captured human attention best in the right near peripheral field of view region. In this experiment of finding a socially acceptable way to accomplish the attention attracting goals of a communication robot, we observed that the robots’ affective behaviors were successful in shifting human attention towards itself in both left and right far- peripheral field of view regions, so we concluded that for far field of view regions, designing similar interaction interventions can be expected to be successful.

Can industrial robot applications help cross the middle-income trap? — Empirical evidence based on crossed-country panel data

What middle-income countries can draw from the experience of the countries that have successfully crossed the middle-income trap has become a theoretical and practical issue where an in-depth study is demanded as these countries account for a large proportion of the world's economy. There are many research studies on crossing the middle-income trap and artificial intelligence, but few studies have combined the two. This paper investigates the impact of industrial robot applications on the middle-income trap crossing at both theoretical and empirical levels. In theory, the scale effect and pricing behavior of robots are introduced into the task model proposed by Acemoglu and Restrepo (2018a) in this paper, which proves that robots can affect economic growth directly, and the greater the robot application, the greater the total output. In terms of empirical analysis, this paper draws on the classification criteria of Felipe et al. (2014) and adopts the absolute value method to classify economies into five groups: trapped, crossed, high-income, middle-income, and low-income group. Based on the panel data of 24 trapped and 37 leapfrogged economies from 1993 to 2019, we have empirically examined the effect of industrial robot application on crossing the middle-income trap. The results indicate that industrial robot applications facilitate economies to cross the middle-income trap through technological innovation, industrial structure and FDI, of which industrial structure includes both output structure and employment structure. This paper provides empirical facts and policy implications for developing economies to cross the middle-income trap through industrial applications.

Core Challenges of Social Robot Navigation: A Survey

Robot navigation in crowded public spaces is a complex task that requires addressing a variety of engineering and human factors challenges. These challenges have motivated a great amount of research resulting in important developments for the fields of robotics and human-robot interaction over the past three decades. Despite the significant progress and the massive recent interest, we observe a number of significant remaining challenges that prohibit the seamless deployment of autonomous robots in crowded environments. In this survey article, we organize existing challenges into a set of categories related to broader open problems in robot planning, behavior design, and evaluation methodologies. Within these categories, we review past work and offer directions for future research. Our work builds upon and extends earlier survey efforts by (a) taking a critical perspective and diagnosing fundamental limitations of adopted practices in the field and (b) offering constructive feedback and ideas that could inspire research in the field over the coming decade.

Integrating Virtual Reality and Robotic Operation System (ROS) for AGV Navigation

The use of AGVs (Automated Guided Vehicles) is rapidly expanding in various applications and industries, meeting the growing demand for automated material handling systems. However, AGV control and navigation remain a challenge. To address this issue, robotics simulators such as ROS (Robot Operating System) have become widely used, reducing the cost and time of checking robot performance. Furthermore, the integration of virtual reality technology into the robotics field has facilitated the study of various robot behaviors in realistic environments, replicating the robot’s real-life size and dimensions. In this study, the TurtleBot2i and RAZBOT AGV robot platforms were integrated into the 3D Unity environment and controlled using ROS. Using Unity as a simulator for the robot’s working environment offers several benefits, including high-quality graphics and a detailed examination of the robot’s behavior. The results of the study demonstrate the accurate simulation and control of the AGV platforms in both ROS and Unity environments.

ECR Spotlight – Talia Moore

ECR Spotlight is a series of interviews with early-career authors from a selection of papers published in Journal of Experimental Biology and aims to promote not only the diversity of early-career researchers (ECRs) working in experimental biology during our centenary year but also the huge variety of animals and physiological systems that are essential for the ‘comparative’ approach. Talia Moore is an author on ‘ Jumping over fences: why field- and laboratory-based biomechanical studies can and should learn from each other’, published in JEB. Talia is an Assistant Professor at the University of Michigan, USA, investigating bio-inspired robotic design, and biomechanics and behavior of unsteady terrestrial motion.

Kinetostatic Modeling of Soft Robots: Energy-Minimization Approach and 99-Line MATLAB Implementation.

Soft robots have received a great deal of attention from both academia and industry due to their unprecedented adaptability in unstructured environment and extreme dexterity for complicated operations. Due to the strong coupling between the material nonlinearity due to hyperelasticity and the geometric nonlinearity due to large deflections, modeling of soft robots is highly dependent on commercial finite element software packages. An approach that is accurate and fast, and whose implementation is open to designers, is in great need. Considering that the constitutive relation of the hyperelastic materials is commonly expressed by its energy density function, we present an energy-based kinetostatic modeling approach in which the deflection of a soft robot is formulated as a minimization problem of its total potential energy. A fixed Hessian matrix of strain energy is proposed and adopted in the limited memory Broyden-Fletcher-Goldfarb-Shanno (BFGS) algorithm, which significantly improves its efficiency for solving the minimization problem of soft robots without sacrificing prediction accuracy. The simplicity of the approach leads to an implementation of MATLAB with only 99-line codes, which provides an easy-to-use tool for designers who are designing and optimizing the structures of soft robots. The efficiency of the proposed approach for predicting kinetostatic behaviors of soft robots is demonstrated by seven pneumatic-driven and cable-driven soft robots. The capability of the approach for capturing buckling behaviors in soft robots is also demonstrated. The energy-minimization approach, as well as the MATLAB implementation, could be easily tailored to fulfill various tasks, including design, optimization, and control of soft robots.

Prediction of behavior of a noncommunicative robot based on observations of its movement

AbstractAn adversary robot can move around in a free space “patrolling an area” appearing to have a random “behavior” if observed through a “lens.” The “behavior” of the robot is associated with its observed/internal state. Stochastic techniques or machine learning techniques, which can be used to predict the future states of an adversary robot demand high computation and thus, power. Advanced RNN techniques like long short‐term memory, which can make predictions using long‐term dependencies of the sequence data, also have extremely high computing and memory requirements. Thus, the systems involved in using these former techniques are not appropriate to be deployed in fields which require inconspicuous monitoring. In this work, we present two novel methods using the “behavior” to predict the future states of an adversary robot which can be deployed using a low computing device/small single board computer/robot in a non‐GPS environment without any internet connection. The proposed two methods are based on a list and a graph, respectively. Unlike the most available literature, where the prediction is based on “time,” our model predicts the future state using the states of the system. These methods work for both single and multiple‐looped paths taken by the adversary robot. The results show that the prediction error which depends on the predicted move and the actual move taken by the robot decreases as a logarithmic function and is comparatively lower when the adversary robot follows a path having multiple loops.

From Inanimate Object to Agent: Impact of Pre-beginnings on the Emergence of Greetings with a Robot

The very first moments of co-presence, during which a robot appears to a participant for the first time, are often “off-the-record” in the data collected from human-robot experiments (video recordings, motion tracking, methodology sections, etc.). Yet, this “pre-beginning” phase, well documented in the case of human-human interactions, is not an interactional vacuum: It is where interactional work from participants can take place so the production of a first speaking turn (like greeting the robot) becomes relevant and expected. We base our analysis on an experiment that replicated the interaction opening delays sometimes observed in laboratory or “in-the-wild” human-robot interaction studies—where robots can require time before springing to life after they are in co-presence with a human. Using an ethnomethodological and multimodal conversation analytic methodology (EMCA), we identify which properties of the robot's behavior were oriented to by participants as creating the adequate conditions to produce a first greeting. Our findings highlight the importance of the state in which the robot originally appears to participants: as an immobile object or, instead, as an entity already involved in preexisting activity. Participants’ orientations to the very first behaviors manifested by the robot during this “pre-beginning” phase produced a priori unpredictable sequential trajectories, which configured the timing and the manner in which the robot emerged as a social agent. We suggest that these first instants of co-presence are not peripheral issues with respect to human-robot experiments but should be thought about and designed as an integral part of those.

Speed Control of Wheeled Mobile Robot by Nature-Inspired Social Spider Algorithm-Based PID Controller

Mobile robot is an automatic vehicle with wheels that can be moved automatically from one place to another. A motor is built in its wheels for mobility purposes, which is controlled using a controller. DC motor speed is controlled by the proportional integral derivative (PID) controller. Kinematic modeling is used in our work to understand the mechanical behavior of robots for designing the appropriate mobile robots. Right and left wheel velocity and direction are calculated by using the kinematic modeling, and the kinematic modeling is given to the PID controller to gain the output. Motor speed is controlled by the PID low-level controller for the robot mobility; the speed controlling is done using the constant values Kd, Kp, and Ki which depend on the past, future, and present errors. For better control performance, the integral gain, differential gain, and proportional gain are adjusted by the PID controller. Robot speed may vary by changing the direction of the vehicle, so to avoid this the Social Spider Optimization (SSO) algorithm is used in PID controllers. PID controller parameter tuning is hard by using separate algorithms, so the parameters are tuned by the SSO algorithm which is a novel nature-inspired algorithm. The main goal of this paper is to demonstrate the effectiveness of the proposed approach in achieving precise speed control of the robot, particularly in the presence of disturbances and uncertainties.

Robotic gaze and human views: A systematic exploration of robotic gaze aversion and its effects on human behaviors and attitudes.

Similar to human-human interaction (HHI), gaze is an important modality in conversational human-robot interaction (HRI) settings. Previously, human-inspired gaze parameters have been used to implement gaze behavior for humanoid robots in conversational settings and improve user experience (UX). Other robotic gaze implementations disregard social aspects of gaze behavior and pursue a technical goal (e.g., face tracking). However, it is unclear how deviating from human-inspired gaze parameters affects the UX. In this study, we use eye-tracking, interaction duration, and self-reported attitudinal measures to study the impact of non-human inspired gaze timings on the UX of the participants in a conversational setting. We show the results for systematically varying the gaze aversion ratio (GAR) of a humanoid robot over a broad parameter range from almost always gazing at the human conversation partner to almost always averting the gaze. The main results reveal that on a behavioral level, a low GAR leads to shorter interaction durations and that human participants change their GAR to mimic the robot. However, they do not copy the robotic gaze behavior strictly. Additionally, in the lowest gaze aversion setting, participants do not gaze back as much as expected, which indicates a user aversion to the robot gaze behavior. However, participants do not report different attitudes toward the robot for different GARs during the interaction. In summary, the urge of humans in conversational settings with a humanoid robot to adapt to the perceived GAR is stronger than the urge of intimacy regulation through gaze aversion, and a high mutual gaze is not always a signof high comfort, as suggested earlier. This result can be used as a justification to deviate from human-inspired gaze parameters when necessary for specific robot behavior implementations.

Liquid Metal Smart Materials toward Soft Robotics

Unlike conventional rigid machines, soft robots generally have unique operation styles that rely heavily on soft matter engineering and smart material systems. Owing to the superior merits of both metals and fluids, liquid metal smart materials are increasingly being innovatively used as soft actuators and sensors to construct soft robots. To promote further development and prosperity in this field, this review organizes and summarizes the typical progress in liquid metal smart materials, with a special focus on their robotic response behaviors. In particular, the article emphasizes the concept of smart composite systems consisting of liquid metals and synergistic substances (e.g., solutions, particles, and polymers). The response behaviors of liquid metal smart materials under the actions of external factors (electricity, magnetism, ultrasound, light, heat, etc.) are examined and the smart properties occurring during these responses, such as motion, transformation, self‐organization, adaptive healing, and autonomous sensing, are identified. Furthermore, soft actuators, control systems, and robots based on liquid metal smart materials are summarized and elaborated upon. Finally, the potential directions worth pursuing and challenges are outlined. It is expected that this review will stimulate further investigations into liquid metal smart materials with the aim of building a new generation of soft robots.