Advanced Autonomous Systems and the Artificial Intelligence Stage

Abstract

This Editorial presents an integrative overview of the Special Issue “Advanced Autonomous Systems and Artificial Intelligence Stage”, which assembles fifteen peer-reviewed articles dedicated to the recent evolution of AI-enabled and autonomous systems. The contributions span a broad spectrum of domains, including renewable energy and power systems, intelligent transportation, agricultural robotics, clinical and assistive technologies, mobile robotic platforms, and space robotics. Across these diverse applications, the collection highlights core research themes such as robust perception and navigation, semantic and multi modal sensing, resource-efficient embedded inference, human–machine interaction, sustainable infrastructures, and validation frameworks for safety-critical systems. Several articles demonstrate how physical modeling, hybrid control architectures, deep learning, and data-driven methods can be combined to enhance operational robustness, reliability, and autonomy in real-world environments. Other works address challenges related to fall detection, predictive maintenance, teleoperation safety, and the deployment of intelligent systems in large-scale or mission-critical contexts. Overall, this Special Issue offers a consolidated and rigorous academic synthesis of current advances in Autonomous Systems and Artificial Intelligence, providing researchers and practitioners with a valuable reference for understanding emerging trends, practical implementations, and future research directions.

1. Introduction

Over the past decade, automation and autonomy have shifted from the realm of “promising technologies” to that of critical infrastructure across industrial production, transportation, energy, agriculture, healthcare, and space applications. The integration of advanced mechanical and mechatronic systems with Artificial Intelligence (AI) defines a new development stage in which autonomous systems become not only more performant, but also safer, more adaptable, and increasingly user-centric [1,2].

In particular, the rapid evolution of AI in safety-critical domains such as medicine and healthcare has highlighted both the potential and the challenges associated with algorithmic decision-making, explainability, and trust [1,2,3]. At the same time, advances in sensing, smart materials, and embedded systems further strengthen the technological foundation for autonomous platforms operating in complex environments [4,5,6,7].

The Special Issue “Advanced Autonomous Systems and Artificial Intelligence Stage” gathers 15 contributions that capture this multidimensional evolution, illustrating how AI [8,9,10,11] and autonomy [9,12] intersect in real-world systems, from robotics and space applications to agriculture, renewable energy, assistive technologies, and human–machine interaction.

2. Advanced Autonomy in Robotics and Space Applications

A central focus of this Special Issue is autonomous robotics for hard-to-access environments, with a particular emphasis on space applications. Several contributions address real-time autonomous methods for center-of-mass localization and inertia identification in robotic platforms, in both single-spacecraft scenarios and grappling operations involving large structures. These works are closely aligned with the broader international effort to achieve robust and verifiable AI-enabled decision-making in safety-critical systems [1,10,11].

In parallel, other papers examine mobile robotics for terrestrial monitoring and indoor inspection, including advanced soil parameter monitoring systems and intelligent indoor inspection platforms. They demonstrate how robust perception, data fusion, and intelligent control can be tailored for planetary-like terrains, precision agriculture, or industrial environments, drawing on the same methodological foundations that underpin modern AI applications in sensing and monitoring [7,9].

3. Perception, Computer Vision, and Semantic Navigation

A second major pillar of this Special Issue is advanced perception, achieved through the integration of computer vision and LiDAR in autonomous architectures. The contributions include the following:

• Neural–geometric methods for ground segmentation in LiDAR point clouds, designed to support safe navigation in structured and unstructured environments.
• Deep-learning-based semantic navigation for mobile robots, where object detection and scene understanding are essential for reliable mapping and path planning.
• Mobile implementations of computer vision in Android applications, including real-time image processing scenarios, thereby connecting high-performance perception algorithms with widely available computational platforms.
• These works resonate with broader trends in AI and machine learning, where real-time, resource-constrained inference is increasingly deployed on embedded and wearable devices [7,8,9]. For example, recent advances in real-time sign-language recognition [8] and wearable fall-detection systems [9] highlight how vision and sensor-based AI can be deployed in everyday environments, extending beyond traditional laboratory settings. The contributions in this Special Issue thus reinforce the importance of perception as a core enabler of autonomy in both mobile and stationary systems.

4. Human–Machine Interaction, BCI, and Social Robotics

A defining feature of the current stage in autonomous systems is user centrality. It is not sufficient for systems to be accurate and fast; they must also be interpretable, intuitive, and aligned with human needs [2,3]. Two main directions in the Special Issue illustrate this shift:

1.

Brain–Computer Interfaces (BCIs) based on EEG signals and deep learning for the control of mobile robots. These systems combine advanced neural architectures with real-time control frameworks, reflecting a broader movement toward human-in-the-loop AI and assistive robotics [1,7].

2.

Social robots in pediatric diabetes education, where robot-assisted interventions are assessed in terms of knowledge acquisition and metabolic control in children. This area is closely connected to the more general landscape of AI in healthcare, where issues of explainability, safety, and clinical integration are widely discussed [1,2,3,10,11].

Together, these studies underscore the transition from purely performance-driven autonomy to empathetic, human-centered autonomy, with tangible clinical and assistive benefits.

5. Precision Agriculture, Renewable Energy, and Smart Infrastructure

Intelligent autonomy is also a key enabler in agriculture, energy, and infrastructure, domains that are central to sustainable development. The Special Issue includes the following:

• An IoT-enhanced decision support system for real-time greenhouse microclimate monitoring and control, which leverages wireless sensor networks and cloud-based analytics for precision agriculture.
• A low-cost passive solar tracker with a guide-slot mechanism, optimized for developing countries and designed to maximize energy capture with minimal actuation.
• A comprehensive review of vision-based monitoring and fault detection techniques for solar plants, highlighting the role of computer vision and AI in predictive maintenance and fault diagnosis.

These contributions are situated within a broader technological context where advanced materials, micro- and nano-engineered structures, and additive manufacturing technologies (such as electrospun fibers and 3D printing) are increasingly integrated into smart energy and environmental systems [4,5,6,12]. The convergence of AI, advanced sensing, and novel materials paves the way for more efficient, resilient, and adaptive infrastructures.

6. Safety, Reliability, and Social Perception

A mature autonomous system must be safe, reliable, explainable, and socially accepted. This Special Issue includes contributions that explicitly address these dimensions. For instance, one study focuses on the fast detection of the stick–slip phenomenon in wheel–rail interactions using acceleration sensors, enabling early intervention in critical traction scenarios. This type of work reflects the importance of high-fidelity sensing and robust signal processing in safety-critical transport systems [7,9].

Another contribution offers a decadal analysis of public discourse on autonomous vehicle accidents, using a transformer-based language model (roBERTa) to examine sentiment and perception on social media. This aligns with the growing literature on the societal and ethical implications of AI, where public trust, transparency, and accountability are key themes [2,3,10,11].

In this context, explainable AI (XAI) and interpretable models are not simply desirable features, but necessary conditions for responsible deployment in domains such as healthcare, mobility, and public safety [2,3,10,11].

7. Teleoperation, Virtual Reality, and Human–Robot Collaboration

In parallel with fully autonomous systems, teleoperation and human–robot collaboration remain indispensable for scenarios where full autonomy is either infeasible or undesirable. This Special Issue features:

• A virtual teleoperation framework for mobile manipulator robots, developed in Unity, which integrates kinematic and dynamic models to enable realistic simulation and control in virtual environments. Such frameworks support safe experimentation, training, and validation before real-world deployment.
• An application integrating advanced information capture and AI-assisted transfer modules for robotic control during dental implant surgery, illustrating how virtual planning, 3D modeling, and intelligent guidance can enhance precision and safety in medical procedures.

These developments are consonant with broader trends in AI-enabled medical imaging and synthetic data generation [11], as well as with the integration of sensing and actuation in wearable and ambient devices [7,9]. They highlight how human–robot collaboration and extended reality (XR) technologies can bridge the gap between autonomous decision-making and clinical or industrial practice.

8. Conclusions and Perspectives

The Special Issue “Advanced Autonomous Systems and Artificial Intelligence Stage” brings together 15 articles that collectively offer a coherent picture of how autonomy and AI intersect in contemporary engineering and science. Across diverse domains, three core trends emerge:

1.

Integration of physical models and AI, where domain knowledge in mechanics, mechatronics, and materials is combined with modern machine learning and deep learning approaches [1,2,3,5,6,7,12].

2.

Human-centered interaction, illustrated by BCI-controlled robots, social robots in healthcare, and systems explicitly designed around user needs and human factors [1,2,3,7,8,9,10].

3.

Sustainability, safety, and societal acceptance, underlined by contributions on renewable energy, precision agriculture, transport safety, and social perceptions of autonomous vehicles [2,3,4,8,9,10,11].

Taken together, these contributions confirm that advanced autonomous systems and AI are no longer confined to laboratory prototypes, but are increasingly embedded in real-world, safety-critical, and socially impactful applications.