Automation, Volume 6, Issue 4 (December 2025) – 12 articles

This study compares the mapping accuracy of a non-RTK ultra-lightweight drone (DJI Mini2) with two survey-grade RTK-enabled drones (DJI Mavic3E and Phantom4) in three different sites. Flight parameters and weather conditions were the same on each site. The outputs were orthomosaics and digital surface models, whose accuracies were inspected by descriptive statistics and variance analysis tools. The data of the ultralight drone on the first site could not be processed due to strong wind, but its results for the second site (11 hectares) were comparable to those of survey-grade drones, i.e., the range and average of checkpoint errors for Mini2 were 0.17 m and 0.04 m, respectively, while those were 0.10 m and 0.02 m for Phantom4 and Mavic3E. In the third site (34 hectares), survey-grade drones produced accurate results with a checkpoint error range of 0.26 m, while that was 0.87 m for the ultralight drone, implying lower accuracy results. The results obtained suggest that ultralight drones under certain circumstances can produce reliable mapping products depending on weather conditions, the number and distribution of ground control points, and area size. Their biggest drawback is their vulnerability to wind, and in calm weather conditions, due to non-RTK error accumulation, their mapping accuracy degenerates as the area size increases. Full article

Bone drilling is a widely encountered process in orthopedic surgeries and keyhole neuro surgeries. We are developing a sensor-integrated smart end-effector for drilling for robotic surgical applications. In manual surgeries, surgeons assess tool wear based on experience and force perception. In this work, we propose a machine-learning (ML)-based tool condition monitoring system based on multi-sensor data to preempt excessive tool wear during drilling in robotic surgery. Real-time data is acquired from the six-component force sensor of a collaborative arm along with the data from the temperature and multi-axis vibration sensor mounted on the bone specimen being drilled upon. Raw data from the sensors may have noises and outliers. Signal processing in the time- and frequency-domain are used for denoising as well as to obtain additional features to be derived from the raw sensory data. This paper addresses the challenging problem of identification of the most suitable ML algorithm and the most suitable features to be used as inputs to the algorithm. While dozens of features and innumerable machine learning and deep learning models are available, this paper addresses the problem of selecting the most relevant features, the most relevant AI models, and the optimal hyperparameters to be used in the AI model to provide accurate prediction on the tool condition. A unique framework is proposed for classifying tool wear that combines machine learning-based modeling with multi-sensor data. From the raw sensory data that contains only a handful of features, a number of additional features are derived using frequency-domain techniques and statistical measures. Using feature engineering, we arrived at a total of 60 features from time-domain, frequency-domain, and interaction-based metrics. Such additional features help in improving its predictive capabilities but make the training and prediction complicated and time-consuming. Using a sequence of techniques such as variance thresholding, correlation filtering, ANOVA F-test, and SHAP analysis, the number of features was reduced from 60 to the 4 features that will be most effective in real-time tool condition prediction. In contrast to previous studies that only examine a small number of machine learning models, our approach systematically evaluates a wide range of machine learning and deep learning architectures. The performances of 47 classical ML models and 6 deep learning (DL) architectures were analyzed using the set of the four features identified as most suitable. The Extra Trees Classifier (an ML model) and the one-dimensional Convolutional Neural Network (1D CNN) exhibited the best prediction accuracy among the models studied. Using real-time data, these models monitored the drilling tool condition in real-time to classify the tool wear into three categories of slight, moderate, and severe. Full article

The utilization of robots has become an integral aspect of industrial operations. In this particular context, the study of the interaction of humans and robots aims to integrate their relevant capabilities with the intention of attaining maximum efficiency. Moreover, in the private sector, interaction with robots is already common in many places. Acceptance, trust, and perceived emotions vary widely depending on specific contexts. This highlights the necessity for adequate training to mitigate fears and enhance trust and acceptance. Currently, no such training is available. Virtual realities have frequently proven to be helpful platforms for the implementation of training. This study aims to evaluate the suitability of virtual realities for training in this specific application area. For this purpose, simple object handovers were performed in three different scenarios (reality, virtual reality, and hybrid reality). Subjective evaluations of the participants were extended by psychophysiological (ECG and EDA) and performance measures. In most cases, the results show no significant differences between the scenarios, indicating that personal perception during interaction is transferable to a virtual reality. This demonstrates the general suitability of virtual realities in this context. Full article

Hierarchical Reinforcement Learning (HRL) for UAV Coverage Path Planning (CPP) is hindered by the “subgoal space explosion”, causing inefficient exploration. To address this, we propose a two-stage framework, Hierarchical Reinforcement Learning Guided by Landmarks (HRGL), which synergistically combines HRL with a multi-scale observation space. The framework provides a low-resolution global map for the high-level policy’s strategic planning and a high-resolution local map for the low-level policy’s execution. To bridge the information gap between these hierarchical views, the first stage, ACHMP, introduces a learned Adjacency Network. This network acts as an efficient proxy for local feasibility by mapping coordinates to an embedding space where distances reflect true reachability, allowing the high-level policy to select feasible subgoals without processing complex local data. The second stage, HRGL, further introduces a landmark-guided global guidance mechanism to overcome local myopia. Extensive experiments on a variety of simulated grid-world maps demonstrate that HRGL significantly outperforms baseline methods in terms of both convergence speed and final coverage rate. Full article

This paper presents a hybrid reinforcement learning framework for trajectory tracking control of a 5-degree-of-freedom (DOF) Mitsubishi RV-2AJ robotic arm by integrating model-free deep reinforcement learning (DRL) algorithms with classical control strategies. A novel hybrid PID + TD3 agent is proposed, combining a Proportional–Integral–Derivative (PID) controller with the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm, and is compared against standalone TD3 and PID controllers. In this architecture, the PID controller provides baseline stability and deterministic disturbance rejection, while the TD3 agent learns residual corrections to enhance tracking accuracy, robustness, and control smoothness. The robotic system is modeled in MATLAB/Simulink with Simscape Multibody, and the agents are trained using a reward function inspired by artificial potential fields, promoting energy-efficient and precise motion. Extensive simulations are performed under internal disturbances (e.g., joint friction variations, payload changes) and external disturbances (e.g., unexpected forces, environmental interactions). Results demonstrate that the hybrid PID + TD3 approach outperforms both standalone TD3 and PID controllers in convergence speed, tracking precision, and disturbance rejection. This study highlights the effectiveness of combining reinforcement learning with classical control for intelligent, robust, and resilient robotic manipulation in uncertain environments. Full article

Facing the diversity of the market, the industry has to move towards Industry 4.0, and smart manufacturing based on cyber-physical systems is the only way to move towards Industry 4.0. However, there are two key concepts in Industry 4.0: cyber-physical systems (CPSs) and digital twins (DTs). In the paper, we propose a smart manufacturing system suitable for stamping press processes based on the CPS concept and use DT to establish a manufacturing-end robot guidance generation model. In the smart manufacturing system of stamping press processes, fog nodes are used to connect three major architectures, including device health diagnosis, manufacturing device, and material traceability. In addition, a special hook end point is designed, and its lightweight visual guidance generation model is established to improve the production efficiency of the manufacturing end in product manufacturing. Full article

The increasing capabilities of Unmanned Aerial Vehicles (UAVs) or drones are opening up diverse business opportunities. Innovations in drones, U-space, and UTM systems are driving the rapid development of new air mobility applications, often outpacing current regulatory frameworks. These applications now span multiple sectors, from infrastructure monitoring to urban parcel delivery, resulting in a projected increase in drone traffic within shared airspace. This growth introduces significant safety concerns, particularly in managing the separation between drones and manned aircraft. Although various research efforts have addressed this deconfliction challenge, a critical need remains for improved automated solutions at both strategic and tactical levels. In response, our SESAR-funded initiative, AI4HyDrop, investigates the application of machine learning to develop an intelligent system for UAV deconfliction. As part of this effort, we conducted a comprehensive literature review to assess the application of Artificial Intelligence (AI) in this domain. The AI algorithms used in drone deconfliction can be categorized into three types: deep learning, reinforcement learning, and bio-inspired learning. The findings lay a foundation for identifying the key requirements of an AI-based deconfliction system for UAVs. Full article

Typical fertilizer applicators are often restricted in performance due to non-uniformity in distribution, required labor and time intensiveness, high discharge rate, chemical input wastage, and fostering weed proliferation. To address this gap in production agriculture, an automated variable-rate fertilizer applicator was developed for the cotton crop that is based on deep learning-initiated electronic control unit (ECU). The applicator comprises (a) plant recognition unit (PRU) to capture and predict presence (or absence) of cotton plants using the YOLOv7 recognition model deployed on-board Raspberry Pi microprocessor (Wale, UK), and relay decision to a microcontroller; (b) an ECU to control stepper motor of fertilizer metering unit as per received cotton-detection signal from the PRU; and (c) fertilizer metering unit that delivers precisely metered granular fertilizer to the targeted cotton plant when corresponding stepper motor is triggered by the microcontroller. The trials were conducted in the laboratory on a custom testbed using artificial cotton plants, with the camera positioned 0.21 m ahead of the discharge tube and 16 cm above the plants. The system was evaluated at forward speeds ranging from 0.2 to 1.0 km/h under lighting levels of 3000, 5000, and 7000 lux to simulate varying illumination conditions in the field. Precision, recall, F1-score, and mAP of the plant recognition model were determined as 1.00 at 0.669 confidence, 0.97 at 0.000 confidence, 0.87 at 0.151 confidence, and 0.906 at 0.5 confidence, respectively. The mean absolute percent error (MAPE) of 6.15% and 9.1%, and mean absolute deviation (MAD) of 0.81 g/plant and 1.20 g/plant, on application of urea and Diammonium Phosphate (DAP), were observed, respectively. The statistical analysis showed no significant effect of the forward speed of the conveying system on fertilizer application rate (p > 0.05), thereby offering a uniform application throughout, independent of the forward speed. The developed fertilizer applicator enhances precision in site-specific applications, minimizes fertilizer wastage, and reduces labor requirements. Eventually, this fertilizer applicator placed the fertilizer near targeted plants as per the recommended dosage. Full article

The A* algorithm is a cornerstone in mobile robot navigation. However, the traditional A* suffers from key limitations such as poor path smoothness, lack of adaptability to dynamic environments, and high computational costs in large-scale maps. This review presents a comprehensive analysis of 20 recent studies (2020–2025) on improved A* variants and their hybrid integrations with complementary algorithms. The improvements are categorized into two core strategies: (i) geometric and structural optimization, heuristic weighting and adaptive search schemes in A* algorithm, and (ii) hybrid models combining A* with local planners such as Dynamic Window Approach (DWA), Artificial Potential Field (APF), and Particle Swarm Optimization (PSO). For each group, the mathematical formulations of evaluation functions, smoothing techniques, and constraint handling mechanisms are detailed. Notably, hybrid frameworks demonstrate improved robustness in dynamic or partially known environments by leveraging A* for global optimality and local planners for real-time adaptability. Case studies with simulated grid maps and benchmark scenarios show that even marginal improvements in path length can coincide with substantial gains in safety and directional stability. This review not only synthesizes the state of the art in A*-based planning but also outlines design principles for building intelligent, adaptive, and computationally efficient navigation systems. Full article

This study presents the design and evaluation of AquaSignalNet, a deep learning-based system for recognizing underwater visual commands to enable the autonomous navigation of a Remotely Operated Vehicle (ROV). The system is built on a ResNet50 V2 architecture and trained with a custom dataset, UVSRD, comprising 33,800 labeled images across 12 gesture classes, including directional commands, speed values, and vertical motion instructions. The model was deployed on a Raspberry Pi 4 integrated with a TIVA C microcontroller for real-time motor control, a PID-based depth control loop, and an MPU9250 sensor for orientation tracking. Experiments were conducted in a controlled pool environment using printed signal cards to define two autonomous trajectories. In the first trajectory, the system achieved 90% success, correctly interpreting a mixed sequence of turns, ascents, and speed changes. In the second, more complex trajectory, involving a rectangular inspection loop and multi-layer navigation, the system achieved 85% success, with failures mainly due to misclassification resulting from lighting variability near the water surface. Unlike conventional approaches that rely on QR codes or artificial markers, AquaSignalNet employs markerless visual cues, offering a flexible alternative for underwater inspection, exploration, and logistical operations. The results demonstrate the system’s viability for real-time gesture-based control. Full article

This paper introduces a new quadruped spider robot platform specializing in environmental reconnaissance and mapping. The robot measures 180 mm × 180 mm × 95 mm and weighs 385 g, including the battery, providing a compact yet capable platform for reconnaissance missions. The robot consists of an ESP32 microcontroller and eight servos that are disposed in a biomimetic layout to achieve the biological gait of an arachnid. One of the major design revolutions is in the power distribution network (PDN) of the robot, in which two DC-DC buck converters (LM2596M) are used to isolate the power domains of the computation and the mechanical subsystems, thereby enhancing reliability and the lifespan of the robot. The theoretical analysis demonstrates that this dual-domain architecture reduces computational-domain voltage fluctuations by 85.9% compared to single-converter designs, with a measured voltage stability improving from 0.87 V to 0.12 V under servo load spikes. Its proprietary Bluetooth protocol allows for both the sending and receiving of controls and environmental data with fewer than 120 ms of latency at up to 12 m of distance. The robot’s mapping system employs a novel motion-compensated probabilistic algorithm that integrates ultrasonic sensor data with IMU-based motion estimation using recursive Bayesian updates. The occupancy grid uses 5 cm × 5 cm cells with confidence tracking, where each cell’s probability is updated using recursive Bayesian inference with confidence weighting to guide data fusion. Experimental verification in different environments indicates that the mapping accuracy (92.7% to ground-truth measurements) and stable pattern of the sensor reading remain, even when measuring the complex gait transition. Long-range field tests conducted over 100 m traversals in challenging outdoor environments with slopes of up to 15° and obstacle densities of 0.3 objects/m² demonstrate sustained performance, with 89.2% mapping accuracy. The energy saving of the robot was an 86.4% operating-time improvement over the single-regulator designs. This work contributes to the championing of low-cost, high-performance robotic platforms for reconnaissance tasks, especially in search and rescue, the exploration of hazardous environments, and educational robotics. Full article

This paper presents a comprehensive overview of permanent magnet synchronous motors (PMSMs), including their classifications, applications, and vector control strategies. It explores various control techniques, including maximum torque per ampere (MTPA), maximum current (MC), field weakening (FW), maximum torque per voltage (MTPV), sensorless control, and parameter identification, as discussed in this paper. These methods address key challenges in PMSM control, such as improving motor efficiency and accurately estimating rotor position and speed. Additionally, this paper presents the PMSM parameters due to many factors such as electric current, phase angle, saturation, and temperature. The survey findings provide a deeper understanding of PMSMs’ control strategies, aiding in the more efficient and reliable motor studies. Full article