Frontiers in Robotics and AI最新文献

Background: The Unified Theory of Acceptance and Use of Technology is a self-rated questionnaire to assess twelve constructs related to the level of acceptance of a robot, consisting of 41 items rated on a 5-point Likert scale. The aim of the study was to conduct a preliminary evaluation of the psychometric properties of the Italian version of the UTAUT (I-UTAUT) in a sample of Italian healthy subjects (HCs).

Materials and methods: 30 HCs underwent the I-UTAUT to assess its comprehensibility. Reliability and divergent validity of the I-UTAUT were evaluated in a sample of 121 HCs, who also underwent the Montreal Cognitive Assessment (MoCA).

Results: The final I-UTAUT version was easily comprehensible. There were no missing data, no floor and ceiling effects. Contrarily to the original version, the Principal Components Analysis suggested a seven-component structure; Cronbach's alpha was 0.94. The I-UTAUT score did not correlate with MoCA.

Conclusion: The I-UTAUT represented a reliable and valid questionnaire to identify the level of acceptance of robotics technology in Italian healthy sample.

This study examines the integration of Artificial Social Intelligence (ASI) into human teams, focusing on how ASI can enhance teamwork processes in complex tasks. Teams of three participants collaborated with ASI advisors designed to exhibit Artificial Theory of Mind (AToM) while engaged in an interdependent task. A profiling model was used to categorize teams based on their taskwork and teamwork potential and study how these influenced perceptions of team processes and ASI advisors. Results indicated that teams with higher taskwork or teamwork potential had more positive perceptions of their team processes, with those high in both dimensions showing the most favorable views. However, team performance significantly mediated these perceptions, suggesting that objective outcomes strongly influence subjective impressions of teammates. Notably, perceptions of the ASI advisors were not significantly affected by team performance but were positively correlated with higher taskwork and teamwork potential. The study highlights the need for ASI systems to be adaptable and responsive to the specific traits of human teams to be perceived as effective teammates.

Multi-robot systems exhibit different application forms in human life, among these, electric vehicles (EVs) at rest and in motion can be perceived as a specialized category of multi-robot systems with increasingly sophisticated vehicle functions and a certain degree of flexibility, and most notably, the ability to iteratively evolve. However, for EVs to evolve into the next-generation of multi-robot systems, more complex technical and operational mechanisms shall be fully cultivated in EVs to develop their evolutionary capabilities, including, but not limited to multimodal environmental sensing techniques, advanced telematics communication protocols such as 5G, Over-The-Air (OTA) upgrade functions, real-time backend data lake analytics, and user-centric marketing initiatives. As it stands, these mechanisms are evidently insufficient for realizing genuine evolutionary robots (ER), especially in unstructured environments. The overarching perspective of conceptualizing EV as ER is not always prominently featured in academic literature. This manuscript provides a succinct overview of the ongoing transition from Software-Defined Vehicles (SDV) to Artificial Intelligence-Defined Vehicles (AIDV), and examines the ongoing research focused on the utilization of electric vehicles as mobile edge computing platforms. Furthermore, it discusses the fundamental evolutionary competencies that define modern electric vehicles, establishing the core tenets upon which our analysis is predicated. To transcend the status quo, we underscore the imperative and pressing need for profound transformations across a spectrum of pivotal domains within the field. Furthermore, this endeavor aims to amplify the reach and influence of research on EVs as ERs, potentially catalyzing the emergence of several niche research areas.

Introduction: This paper addresses the critical need for adaptive formation control in Autonomous Underwater Vehicles (AUVs) without requiring knowledge of system dynamics or environmental data. Current methods, often assuming partial knowledge like known mass matrices, limit adaptability in varied settings.

Methods: We proposed two-layer framework treats all system dynamics, including the mass matrix, as entirely unknown, achieving configuration-agnostic control applicable to multiple underwater scenarios. The first layer features a cooperative estimator for inter-agent communication independent of global data, while the second employs a decentralized deterministic learning (DDL) controller using local feedback for precise trajectory control. The framework's radial basis function neural networks (RBFNN) store dynamic information, eliminating the need for relearning after system restarts.

Results: This robust approach addresses uncertainties from unknown parametric values and unmodeled interactions internally, as well as external disturbances such as varying water currents and pressures, enhancing adaptability across diverse environments.

Discussion: Comprehensive and rigorous mathematical proofs are provided to confirm the stability of the proposed controller, while simulation results validate each agent's control accuracy and signal boundedness, confirming the framework's stability and resilience in complex scenarios.

This paper presents a mini-review of the current state of research in mobile manipulators with variable levels of autonomy, emphasizing their associated challenges and application environments. The need for mobile manipulators in different environments, especially hazardous ones such as decommissioning and search and rescue, is evident due to the unique challenges and risks each presents. Many systems deployed in these environments are not fully autonomous, requiring human-robot teaming to ensure safe and reliable operations under uncertainties. Through this analysis, we identify gaps and challenges in the literature on Variable Autonomy, including cognitive workload and communication delays, and propose future directions, including whole-body Variable Autonomy for mobile manipulators, virtual reality frameworks, and large language models to reduce operators' complexity and cognitive load in some challenging and uncertain scenarios.

Robotic burrowing holds promise for applications in agriculture, resource extraction, and infrastructure development, but current approaches are ineffective, inefficient, or cause significant environmental disruption. In contrast, natural burrowers penetrate substrates with minimal disturbance, providing biomechanical principles that could inspire more efficient and sustainable mechanisms. A notable feature of many natural burrowers is their reliance on soft body compositions, raising the question of whether softness contributes to their burrowing success. This review explores the role of soft materials in biological burrowing and their implications for robotic design. We examine the mechanisms that soft-bodied organisms and soft robots employ for submerging and subterranean locomotion, focusing on how softness enhances efficiency and adaptability in granular media. We analyze the gaps between the capabilities of natural burrowers and soft robotic burrowers, identify grand challenges, and propose opportunities to enhance robotic burrowing performance. By bridging biological principles with engineering innovation, this review aims to inform the development of next-generation burrowing robots capable of operating with the efficiency and efficacy seen in nature.

For smooth human-robot cooperation, it is crucial that robots understand social cues from humans and respond accordingly. Contextual information provides the human partner with real-time insights into how the robot interprets social cues and what action decisions it makes as a result. We propose and implement a novel design for a human-robot cooperation framework that uses augmented reality and user gaze to enable bidirectional communication. Through this framework, the robot can recognize the objects in the scene that the human is looking at and infer the human's intentions within the context of the cooperative task. We proposed three levels of exchange of explicit information designs, each providing increasingly more information. These designs enable the robot to offer contextual information about what user actions it has identified and how it intends to respond, which is in line with the goal of cooperation. We report a user study (n = 24) in which we analyzed the performance and user experience with the three different levels of exchange of explicit information. Results indicate that users preferred an intermediate level of exchange of information, in which users knew how the robot was interpreting their intentions, but where the robot was autonomous to take unsupervised action in response to gaze input from the user, needing a less informative action from the human's side.

The automatic synthesis of policies for robotics systems through reinforcement learning relies upon, and is intimately guided by, a reward signal. Consequently, this signal should faithfully reflect the designer's intentions, which are often expressed as a collection of high-level requirements. Several works have been developing automated reward definitions from formal requirements, but they show limitations in producing a signal which is both effective in training and able to fulfill multiple heterogeneous requirements. In this paper, we define a task as a partially ordered set of safety, target, and comfort requirements and introduce an automated methodology to enforce a natural order among requirements into the reward signal. We perform this by automatically translating the requirements into a sum of safety, target, and comfort rewards, where the target reward is a function of the safety reward and the comfort reward is a function of the safety and target rewards. Using a potential-based formulation, we enhance sparse to dense rewards and formally prove this to maintain policy optimality. We call our novel approach hierarchical, potential-based reward shaping (HPRS). Our experiments on eight robotics benchmarks demonstrate that HPRS is able to generate policies satisfying complex hierarchical requirements. Moreover, compared with the state of the art, HPRS achieves faster convergence and superior performance with respect to the rank-preserving policy-assessment metric. By automatically balancing competing requirements, HPRS produces task-satisfying policies with improved comfort and without manual parameter tuning. Through ablation studies, we analyze the impact of individual requirement classes on emergent behavior. Our experiments show that HPRS benefits from comfort requirements when aligned with the target and safety and ignores them when in conflict with the safety or target requirements. Finally, we validate the practical usability of HPRS in real-world robotics applications, including two sim-to-real experiments using F1TENTH vehicles. These experiments show that a hierarchical design of task specifications facilitates the sim-to-real transfer without any domain adaptation.

Purpose: This study aims to develop an autonomous robotic ultrasound scanning system (auto-RUSS) pipeline, comparing its reproducibility and observer consistency in image analysis with physicians of varying levels of expertise.

Design/methodology/approach: An auto-RUSS was engineered using a 7-degree-of-freedom robotic arm, with real-time regulation based on force control and ultrasound visual servoing. Two phantoms were employed for the human-machine comparative experiment, involving three groups: auto-RUSS, non-expert (4 junior physicians), and expert (4 senior physicians). This setup enabled comprehensive assessment of reproducibility in contact force, image acquisition, image measurement and AI-assisted classification. Radiological feature variability was measured using the coefficient of variation (COV), while performance and reproducibility assessments utilized mean and standard deviation (SD).

Findings: The auto-RUSS had the potential to reduce operator-dependent variability in ultrasound examinations, offering enhanced repeatability and consistency across multiple dimensions including probe contact force, images acquisition, image measurement, and diagnostic model performance.

Originality/value: In this paper, an autonomous robotic ultrasound scanning system (auto-RUSS) pipeline was proposed. Through comprehensive human-machine comparison experiments, the auto-RUSS was shown to effectively improve the reproducibility of ultrasound images and minimize human-induced variability.

Traditional search and rescue methods in wilderness areas can be time-consuming and have limited coverage. Drones offer a faster and more flexible solution, but optimizing their search paths is crucial for effective operations. This paper proposes a novel algorithm using deep reinforcement learning to create efficient search paths for drones in wilderness environments. Our approach leverages a priori data about the search area and the missing person in the form of a probability distribution map. This allows the policy to learn optimal flight paths that maximize the probability of finding the missing person quickly. Experimental results show that our method achieves a significant improvement in search times compared to traditional coverage planning and search planning algorithms by over $160\%$ , a difference that can mean life or death in real-world search operations Additionally, unlike previous work, our approach incorporates a continuous action space enabled by cubature, allowing for more nuanced flight patterns.