3D Recognition Based on Sensor Modalities for Robotic Systems: A Survey

Robust three-dimensional (3D) recognition across different viewing angles is crucial for dynamic applications such as autonomous navigation and augmented reality; however, the application of the technology remains challenging owing to factors such as orientation, deformation, and noise. Wave-based analogous computing, particularly diffraction neural networks (DNNs), constitutes a scan-free, energy-efficient means of mitigating these issues with strong resilience to environmental disturbances. Herein, we present a real-time all-directional 3D object recognition and distortion correction system using a deep knowledge prior DNN. Our approach effectively addressed complex two-dimensional (2D) and 3D distortions by optimizing the metasurface parameters with minimal training data and refining them using DNNs. Experimental results demonstrate that the system can effectively rectify distortions and recognize objects in real time, even under varying perspectives and multiple complex distortions. In 3D recognition, the prior DNN reliably identifies both dynamic and static objects, maintaining stable performance despite arbitrary orientation changes, highlighting its adaptability to complex and dynamic environments. Our system can function either as a preprocessing tool for imaging platforms or as a stand-alone solution, facilitating 3D recognition tasks such as motion sensing and facial recognition. It offers a scalable solution for high-speed recognition tasks in dynamic and resource-constrained applications.

Enhancing Humans Trust in Robots through Explanations

The decisions made by social robots while they fulfill their tasks have a strong influence on their performance. In these contexts, autonomous social robots must exhibit adaptive and social-based behavior to make appropriate decisions and operate correctly in complex and dynamic scenarios. This paper presents a Decision-Making System for social robots working on long-term interactions like cognitive stimulation or entertainment. The Decision-making System employs the robot’s sensors, user information, and a biologically inspired module to replicate how human behavior emerges in the robot. Besides, the system personalizes the interaction to maintain the users’ engagement while adapting to their features and preferences, overcoming possible interaction limitations. The system evaluation was in terms of usability, performance metrics, and user perceptions. We used the Mini social robot as the device where we integrated the architecture and carried out the experimentation. The usability evaluation consisted of 30 participants interacting with the autonomous robot in 30 min sessions. Then, 19 participants evaluated their perceptions of robot attributes of the Godspeed questionnaire by playing with the robot in 30 min sessions. The participants rated the Decision-making System with excellent usability (81.08 out of 100 points), perceiving the robot as intelligent (4.28 out of 5), animated (4.07 out of 5), and likable (4.16 out of 5). However, they also rated Mini as unsafe (security perceived as 3.15 out of 5), probably because users could not influence the robot’s decisions.

A wearable sensor vest for social humanoid robots with GPGPU, IoT, and modular software architecture

Motivated by the need of the numerous real-world applications, 3D object recognition has become an active research field. The representation describes the sensed data and the object models, and it is a key issue in the recognition process, which decides the match strategy and the effectiveness and robustness of the recognition system. In this paper, we propose an improved 3D object representation first, which computes the local signatures of a given basis polygon on the surface mesh, and converts the signatures to a 2D array called the distance-angle (DA) images by weighted bilinear interpolation. This representation is adaptive to free-form objects and resistant to occlusion and clutter. Compared with the original representation, it has a more distinct meaning, easier operation, and adaptation to different resolutions and irregular triangle meshes. Secondly, based on the improved representation, a novel 3D recognition algorithm is presented, which has multiresolution mesh based, coarse-to-fine recognition. By matching the DA image of a polygon in the scene surface mesh with the DA images of models at low resolution, a model candidate set is obtained. The set is filtered in the neighborhood of the matched polygons in a high-resolution mesh and verified by the model candidate sets of other polygons. Experiments show that this algorithm needs less computation and is very accurate and robust.

This article provides a comprehensive and comparative overview of the main types of robots, including social, educational, entertainment, industrial, collaborative, mobile, service, and humanoid robots, focusing on their technical, functional, and social characteristics. A key objective is to explore how anthropomorphic design, through human-like appearance, voice, and behavior, affects robot classification and shapes humanrobot interaction in different domains, including healthcare, education, retail, and entertainment. The study utilizes a structured literature review methodology that integrates recent peer-reviewed research in engineering, human-computer interaction, and the behavioral sciences. Through a comparative analysis, the paper identifies overarching topics such as the merging of technology capabilities, the increasing fluidity of robot classifications, and the ethical implications of emotional engagement with robots. Factors related to user trust, perceived agency, and consumer acceptance such as emotional intelligence, contextual adaptability, design aesthetics, and interaction intensity are examined. The results show that the increasing anthropomorphism of robots can significantly enhance user engagement, emotional attachment, and acceptance. However, it also raises important ethical challenges. These include the risks of emotional manipulation, stereotype reinforcement, and psychological dependence. The paper highlights that successful robot integration depends not only on technical efficiency, but also on ethical considerations, context-aware design, and the alignment of robot behavior with human social expectations. This paper provides original value by connecting technical classifications with socio-psychological dimensions of human-robot interaction, offering a conceptual framework for understanding how design elements and application context interact to influence societal acceptance.

The topic of human robot interaction (HRI) is an important part of human computer interaction (HCI). Robots are more and more used in a social context, and in this paper we try to formulate a research agenda concerning ethical issues around social HRI in order to be prepared for future scenarios where robots may be a naturally integrated part of human society. We outline different paradigms to describe the role of social robots in communication processes with humans, and connect HRI with the topic of persuasive technology in health care, to critically reflect the potential benefits of using social robots as persuasive agents. The ability of a robotic system to conform to the demands (behaviors, understanding, roles, and tasks) that arise from the place the robot is designed to perform, affect the user and his/er sense of place attachment. Places are constantly changing, and so do interactions, thus robotic systems should continually adjust to change by modifying their behavior accordingly.Keywordshuman-robot interactionpersuasive agentsocial robotsethicsplace attachment

The United States Department of Defense (DoD) designs, constructs, and deploys social and autonomous robots and robotic weapons systems. Military robots are designed to follow the rules and conduct of the professions or roles they emulate, and it is expected that ethical principles are applied and aligned with such roles. The application of these principles appear paramount during the COVID-19 global pandemic, wherein substitute technologies are crucial in carrying out duties as humans are more restrained due to safety restrictions. This article seeks to examine the ethical implications of the utilization of military robots. The research assesses ethical challenges faced by the United States DoD regarding the use of social and autonomous robots in the military. The authors provide a summary of the current status of these lethal autonomous and social military robots, ethical and moral issues related to their design and deployment, a discussion of policies, and the call for an international discourse on appropriate governance of such systems.

Recent advances in robotics and artificial intelligence have made it necessary or desired for humans to get involved in interactions with social robots. A key factor for the human acceptance of these robots is their awareness of environmental and social norms. In this paper, we introduce SONAR (for SOcial Norm Aware Robots), a novel robot-agnostic control architecture aimed at enabling social agents to autonomously recognize, act upon, and learn over time social norms during interactions with humans. SONAR integrates several state-of-the-art theories and technologies, including the belief-desire-intention (BDI) model of reasoning and decision making for rational agents, fuzzy logic theory, and large language models, to support adaptive and norm-aware autonomous decision making. We demonstrate the feasibility and applicability of SONAR via real-life experiments involving human-robot interactions (HRI) using a Nao robot for scenarios of casual conversations between the robot and each participant. The results of our experiments show that our SONAR implementation can effectively and efficiently be used in HRI to provide the robot with environmental and social and norm awareness. Compared to a robot with no explicit social and norm awareness, introducing social and norm awareness via SONAR results in interactions that are perceived as more positive and enjoyable by humans, as well as in higher perceived trust in the social robot. Moreover, we investigate, via computer-based simulations, the extent to which SONAR can be used to learn and adapt to the social norms of different societies. The results of these simulations illustrate that SONAR can successfully learn adequate behaviors in a society from a relatively small amount of data. We publicly release the source code of SONAR, along with data and experiments logs.

A wider incorporation of robots into classrooms is hampered by current technological limitations on full autonomy in social robots. Automated speech recognition, for example, a key enabler for vocal communication, is still unable to perform with sufficient accuracy. Past studies have shown that humans adjust their speech patterns to accommodate less skilled interlocutors. If such a response holds in human-robot interactions as well, we may be able to exploit it to lessen the burden on social robots and enable rich, autonomous vocal communication. In this paper we explore whether a robot's speaking ability could have an impact on children's speech patterns, learning, and engagement by designing an interaction where a child and a robot collaborate on a Tower of Hanoi puzzle. Sixteen children aged 7-14 completed this collaborative task partnered with a social robot that communicated with either high verbal (full sentences), low verbal (short phrases or single words), or nonverbal (sound-based utterances) vocalization. While we found no significant impact on children's speech patterns or learning due to the robot's method of vocalization, children in the non-verbal condition had a significantly lower perception of the robot's intelligence along with higher rates of providing feedback and more instances of undoing its moves. This suggests that a link may exist between a robot's perceived speaking ability and children's confidence in that robot's overall intelligence and capability in a collaborative task, as well as their empathy towards a peer they perceive as less skilled in the task.

Recognition of single 3D curved objects using 2D cross-sectional slice shapes

The discriminative power of modern deep learning models for 3D human action recognition is growing ever so potent. In conjunction with the recent resurgence of 3D human action representation with 3D skeletons, the quality and the pace of recent progress have been significant. However, the inner workings of state-of-the-art learning based methods in 3D human action recognition still remain mostly black-box. In this work, we propose to use a new class of models known as Temporal Convolutional Neural Networks (TCN) for 3D human action recognition. TCN provides us a way to explicitly learn readily interpretable spatio-temporal representations for 3D human action recognition. Through this work, we wish to take a step towards a spatio-temporal model that is easier to understand, explain and interpret. The resulting model, Res-TCN, achieves state-of-the-art results on the largest 3D human action recognition dataset, NTU-RGBD.

Modern robotics seems to have taken root from the theories of Isaac Asimov, in 1941. One area of research that has become increasingly popular in recent decades is the study of artificial intelligence or A.I., which aims to use machines to solve problems that, according to current opinion, require intelligence. This is related to the study on “Social Robots”. Social Robots are created in order to interact with human beings; they have been designed and programmed to engage with people by leveraging a "human" aspect and various interaction channels, such as speech or non-verbal communication. They therefore readily solicit social responsiveness in people who often attribute human qualities to the robot. Social robots exploit the human propensity for anthropomorphism, and humans tend to trust them more and more. Several issues could arise due to this kind of trust and to the ability of “superintelligence” to "self-evolve", which could lead to the violation of the purposes for which it was designed by humans, becoming a risk to human security and privacy. This kind of threat concerns social engineering, a set of techniques used to convince users to perform a series of actions that allow cybercriminals to gain access to the victims' resources. The Human Factor is the weakest ring of the security chain, and the social engineers exploit Human-Robots Interaction to persuade an individual to provide private information.An important research area that has shown interesting results for the knowledge of the possibility of human interaction with robots is "cyberpsychology". This paper aims to provide insights into how the interaction with social robots could be exploited by humans not only in a positive way but also by using the same techniques of social engineering borrowed from "bad actors" or hackers, to achieve malevolent and harmful purposes for man himself. A series of experiments and interesting research results will be shown as examples. In particular, about the ability of robots to gather personal information and display emotions during the interaction with human beings. Is it possible for social robots to feel and show emotions, and human beings could empathize with them? A broad area of research, which goes by the name of "affective computing", aims to design machines that are able to recognize human emotions and consistently respond to them. The aim is to apply human-human interaction models to human-machine interaction. There is a fine line that separates the opinions of those who argue that, in the future, machines with artificial intelligence could be a valuable aid to humans and those who believe that they represent a huge risk that could endanger human protection systems and safety. It is necessary to examine in depth this new field of cybersecurity to analyze the best path to protect our future. Are social robots a real danger? Keywords: Human Factor, Cybersecurity, Cyberpsychology, Social Engineering Attacks, Human-Robot Interaction, Robotics, Malicious Artificial Intelligence, Affective Computing, Cyber Threats

Recent, rapid advancements in technology have enabled the introduction and integration of robots into everyday life. Different from the traditional image of robots as cold and mechanical, social robots are designed to emulate human interaction patterns, improving the user experience and facilitating social interactivity. Thus, social robots represent a promising new care intervention. In this article, after defining social robots and explaining the factors influencing "human-robot interaction", the authors discuss the effectiveness of social robots in the context of providing care to patients with dementia and autism as well as to pediatric patients. Finally, current cases in which PARO, a social robot, has been used in nursing are described, and key challenges and suggestions for future social robot applications are given. Current evidence indicates social robots must be developed and designed to adhere to a people-centered approach to achieve better robot-assisted care outcomes, be better accepted by patients, and better enable patients to open up emotionally and maintain good physical, mental, and social well-being.

The future of AI-powered robotics promises a major transformation across various industries, offering remarkable potential to automate complex processes, boost human capabilities, and redefine numerous sectors. By utilizing machine learning, computer vision, and natural language processing, AI-driven robots can interact with their surroundings, make informed decisions, and learn from their experiences, all without direct human oversight. This fusion of robotics and AI enables machines to tackle delicate tasks such as performing surgeries in healthcare, as well as advancing manufacturing and logistics operations. In the near future, AI-powered robots are expected to become increasingly autonomous, adaptable, and proficient in managing tasks within ever-changing environments. Breakthroughs in machine perception will allow robots to better comprehend and respond to the world around them, enhancing safety and effectiveness. Furthermore, advancements in human-robot collaboration may lead to robots working alongside humans in sectors like education, hospitality, and services, improving productivity and user interactions. However, the rise of AI-powered robotics also raises important ethical, legal, and social concerns, such as job loss and privacy issues. To ensure these technologies benefit society, careful integration will be essential. Ultimately, AI-powered robots are set to play a crucial role in shaping the future, transforming how we live and work. Research significance: The future of AI-driven robotics has the potential to revolutionize various industries, including healthcare, manufacturing, logistics, and agriculture. Research in this area concentrates on improving robot autonomy, decision-making, and collaboration with humans through advanced AI technologies. As robots become smarter, they will be able to carry out intricate tasks with greater accuracy, flexibility, and efficiency, boosting productivity and safety. This research also tackles issues such as ethical concerns, reliability, and human-robot emotional interaction. Progress in AI robotics promises innovative, practical, and sustainable solutions, transforming industries and enhancing overall quality of life. Methodology: The approach to studying the future of AI-driven robotics focuses on exploring how artificial intelligence integrates with robotic systems. This involves examining progress in machine learning, computer vision, and natural language processing, which allow robots to complete intricate tasks independently. Researchers investigate technological innovations such as enhanced sensors, edge computing, and human-robot interactions. They also address ethical, societal, and economic implications, such as the effects of automation, labor markets, and safety. To forecast trends, challenges, and opportunities in AI robotics, experts use case studies, simulations, and interviews, offering a well-rounded view of its future potential Alternative: AI Algorithm Performance, Energy Efficiency, Human-Robot Interaction, Hardware Advancements, Regulation and Ethics Evaluation preference: AI Algorithm Performance, Energy Efficiency, Human-Robot Interaction, Hardware Advancements, Regulation and Ethics Results: Hardware advancements are rising to the top, while regulation and ethics are being pushed to the bottom