Automation

A method for cooperative transportation, which required formation change in a traveling environment, is gaining interest. Deep reinforcement learning is used in formation changes for multi-robot cases. The MADDPG (Multi-Agent Deep Deterministic Policy Gradient) method is popularly used for recognized environments. On the other hand, re-learning may be required in unrecognized circumstances by using the MADDPG method. Although the development of MADDPG using model-based learning and imitation learning has been applied to reduce learning time, it is unclear how the learning results are transferred when the number of robots changes. For example, in the GASIL-MADDPG (Generative adversarial self-imitation learning and Multi-agent Deep Deterministic Policy Gradient) method, how the results of three robot training can be transferred to the four robots’ neural networks is uncertain. Nowadays, Scaled Dot Product Attention (SDPA) has attracted attention and is highly impactful for its speed and accuracy in natural language processing. When transfer learning is combined with fast computation, the efficiency of edge-level re-learning is improved. This paper proposes a formation change algorithm that allows easy and fast multi-robot knowledge transfer using SDPA combined with MAPPO (Multi-Agent Proximal Policy Optimization), compared to other methods. This algorithm applies SDPA to multi-robot formation learning and performs fast learning by transferring the acquired knowledge of formation changes to a certain number of robots. The proposed algorithm is verified by simulating the robot formation change and was able to achieve dramatic high-speed learning capabilities. The proposed SDPA-MAPPO (Scaled Dot Product Attention-Multi-Agent Proximal Policy Optimization) learned 20.83 times faster than the Deep Dyna-Q method. Furthermore, using transfer learning from a three-robot to five-robot case, the method shows that the learning time can be reduced by about 56.57 percent. A scenario of three-robot to five-robot is chosen based on the number of robots often used in cooperative robots. Full article

Detecting cracks in cylinder heads traditionally relies on manual inspection, which is time-consuming and susceptible to human error. As an alternative, automated object detection utilizing computer vision and machine learning models has been explored. However, these methods often face challenges due to a lack of sufficiently annotated training data, limited image diversity, and the inherently small size of cracks. Addressing these constraints, this paper introduces a novel automated crack-detection method that enhances data availability through a synthetic data generation technique. Unlike general data augmentation practices, our method involves copying cracks from one location to another, guided by both random and informed engineering decisions about likely crack formations due to cyclic thermomechanical loads. The innovative aspect of our approach lies in the integration of domain-specific engineering knowledge into the synthetic generation process, which substantially improves detection accuracy. We evaluate our method’s effectiveness using two metrics: the F2 score, which emphasizes recall to prioritize detecting all potential cracks, and mean average precision (MAP), a standard measure in object detection. Experimental results demonstrate that, without engineering insights, our method increases the F2 score from 0.40 to 0.65, while maintaining a stable MAP. Incorporating detailed engineering knowledge further enhances the F2 score to 0.70 and improves MAP to 0.57, representing increases of 63% and 43%, respectively. These results confirm that our approach not only mitigates the limitations of traditional data augmentation but also significantly advances the reliability and precision of crack detection in industrial settings. Full article

Automated driving (AD) is a new technology that aims to mitigate traffic accidents and enhance driving efficiency. This study presents a deep reinforcement learning (DRL) method for autonomous vehicles that can safely and efficiently handle highway overtaking scenarios. The first step is to create a highway traffic environment where the agent can be guided safely through surrounding vehicles. A hierarchical control framework is then provided to manage high-level driving decisions and low-level control commands, such as speed and acceleration. Next, a special DRL-based method called deep deterministic policy gradient (DDPG) is used to derive decision strategies for use on the highway. The performance of the DDPG algorithm is compared with that of the DQN and PPO algorithms, and the results are evaluated. The simulation results show that the DDPG algorithm can effectively and safely handle highway traffic tasks. Full article

The increasing adoption of Deep Learning (DL)-based Object Detection (OD) models in smart manufacturing has opened up new avenues for optimizing production processes. Traditional industries facing capacity constraints require noninvasive methods for in-depth operations analysis to optimize processes and increase revenue. In this study, we propose a novel framework for capacity constraint analysis that identifies bottlenecks in production facilities and conducts cycle time studies using an end-to-end pipeline. This pipeline employs a Convolutional Neural Network (CNN)-based OD model to accurately identify potential objects on the production floor, followed by a CNN-based tracker to monitor their lifecycle in each workstation. The extracted metadata are further processed through the proposed framework. Our analysis of a real-world manufacturing facility over six months revealed that the bottleneck station operated at only 73.1% productivity, falling to less than 40% on certain days; additionally, the processing time of each item increased by 53% during certain weeks due to critical labor and materials shortages. These findings highlight significant opportunities for process optimization and efficiency improvements. The proposed pipeline can be extended to other production facilities where manual labor is used to assemble parts, and can be used to analyze and manage labor and materials over time as well as to conduct audits and improve overall yields, potentially transforming capacity management in smart manufacturing environments. Full article

In this paper, the performance of three model-free control approaches on a multi-input, multi-output (MIMO) nonlinear system with constant and time-varying references is compared. The first control algorithm is model-free adaptive control (MFAC). The second is a modified version of MFAC (MMFAC) designed to handle delays in the system by incorporating the output error difference (over two sample time steps) in the control input. The third approach, model-free adaptive predictive control (MFAPC) with a one-step-ahead forecast of the system input, is obtained by using predictions of the outputs based on the data-based linear model. The experimental device used is an MIMO three-tank system (3TS) assumed to be an interconnected system with multiple coupled single-input, single-output (SISO) subsystems with unmeasurable couplings. The novelty of this contribution is that each coupled SISO partition is assumed to be controlled independently using a decoupled control algorithm, leading to fewer control parameters compared to a centralized MIMO controller. Additionally, both parameter tuning for each controller and performance evaluation are conducted using an evaluation criterion considering energy consumption and accumulated tracking error. The results demonstrate that almost all the proposed model-free controllers effectively control an MIMO system by controlling its SISO subsystems individually. Moreover, the predictive features in the decoupled MFAPC contribute to more accurate tracking of time-varying references. The utilization of tracking error differences helps in reducing energy consumption. Full article

The integration of thermal imaging data with multimodal large language models (MLLMs) offers promising advancements for enhancing the safety and functionality of autonomous driving systems (ADS) and intelligent transportation systems (ITS). This study investigates the potential of MLLMs, specifically GPT-4 Vision Preview and Gemini 1.0 Pro Vision, for interpreting thermal images for applications in ADS and ITS. Two primary research questions are addressed: the capacity of these models to detect and enumerate objects within thermal images, and to determine whether pairs of image sources represent the same scene. Furthermore, we propose a framework for object detection and classification by integrating infrared (IR) and RGB images of the same scene without requiring localization data. This framework is particularly valuable for enhancing the detection and classification accuracy in environments where both IR and RGB cameras are essential. By employing zero-shot in-context learning for object detection and the chain-of-thought technique for scene discernment, this study demonstrates that MLLMs can recognize objects such as vehicles and individuals with promising results, even in the challenging domain of thermal imaging. The results indicate a high true positive rate for larger objects and moderate success in scene discernment, with a recall of 0.91 and a precision of 0.79 for similar scenes. The integration of IR and RGB images further enhances detection capabilities, achieving an average precision of 0.93 and an average recall of 0.56. This approach leverages the complementary strengths of each modality to compensate for individual limitations. This study highlights the potential of combining advanced AI methodologies with thermal imaging to enhance the accuracy and reliability of ADS, while identifying areas for improvement in model performance. Full article

The rapidly increasing adoption of electric vehicles (EVs) globally underscores the urgent need for effective management strategies for end-of-life (EOL) EV batteries. Efficient EOL management is crucial in reducing the ecological footprint of EVs and promoting a circular economy where battery materials are sustainably reused, thereby extending the life cycle of the resources and enhancing overall environmental sustainability. In response to this pressing issue, this review presents a comprehensive analysis of the role of artificial intelligence (AI) in improving the disassembly processes for EV batteries, which is integral to the practical echelon utilization and recycling process. This paper reviews the application of AI techniques in various stages of retired battery disassembly. A significant focus is placed on estimating batteries’ state of health (SOH), which is crucial for determining the availability of retired EV batteries. AI-driven methods for planning battery disassembly sequences are examined, revealing potential efficiency gains and cost reductions. AI-driven disassembly operations are discussed, highlighting how AI can streamline processes, improve safety, and reduce environmental hazards. The review concludes with insights into the future integration of electric vehicle battery (EVB) recycling and disassembly, emphasizing the possibility of battery swapping, design for disassembly, and the optimization of charging to prolong battery life and enhance recycling efficiency. This comprehensive analysis underscores the transformative potential of AI in revolutionizing the management of retired EVBs. Full article

The automatic detection of road surface cracks is a crucial task in road maintenance, but the complexity of crack topology and the susceptibility of detection results to environmental interference make it challenging. To address this issue, this paper proposes an automatic crack detection method based on density clustering using random forest. First, a shadow elimination method based on brightness division is proposed to address the issue of lighting conditions affecting detection results in road images. This method compensates for brightness and enhances details, eliminating shadows while preserving texture information. Second, by combining the random forest algorithm with density clustering, the impact of noise on crack extraction is reduced, enabling the complete extraction and screening of crack information. This overcomes the shortcomings of the random forest method, which only detects crack edge information with low accuracy. The algorithm proposed in this paper was tested on the CFD and Cracktree200 datasets, achieving precision of 87.4% and 84.6%, recall rates of 83.9% and 82.6%, and F-1 scores of 85.6% and 83.6%, respectively. Compared to the CrackForest algorithm, it significantly improves accuracy, recall rate, and F-1 score. Compared to the UNet++ and Deeplabv3+ algorithms, it also achieves better detection results. The results show that the algorithm proposed in this paper can effectively overcome the impact of uneven brightness and complex topological structures on crack target detection, improving the accuracy of road crack detection and surpassing similar algorithms. It can provide technical support for the automatic detection of road surface cracks. Full article

This paper introduces an innovative dual-path planning algorithm rooted in a topological three-dimensional Riemannian manifold (T3DRM) to optimize drone navigation in complex environments. It seamlessly integrates strategies for both discrete and continuous obstacles, employing spherical navigation for the former and hyperbolic paths for the latter. Serving as a transformative tool, the T3DRM facilitates efficient path planning by transitioning between discrete and continuous domains. In uncertain environments with unpredictable obstacle positions, our methodology categorizes these positions as discrete or continuous based on their distribution patterns. Discrete obstacles exhibit random distributions, while continuous obstacles display symmetrical patterns with continuity. Leveraging topological metrics, the T3DRM efficiently classifies these patterns for effective path planning. The findings of this research demonstrate the efficiency of path planning based on classified obstacle positions, enabling swift and efficient drone navigation. This research introduces a pioneering application of a T3DRM, accelerating drone navigation in uncertain environments through a dual approach that simultaneously transforms navigation in primal and dual domains. By enabling spherical and hyperbolic navigation concurrently, the T3DRM offers a comprehensive solution to discrete and continuous path planning challenges. The proposed approach can be used for various indoor applications, especially for warehouse management, surveillance and security, navigation in complex structures, indoor farming, site inspection, healthcare facilities, etc. Full article

As the number of end-of-life products multiplies, the issue of their efficient disassembly has become a critical problem that urgently needs addressing. The field of disassembly sequence planning has consequently attracted considerable attention. In the actual disassembly process, the complex structures of end-of-life products can lead to significant delays due to the interference between different tasks. Overlooking this can result in inefficiencies and a waste of resources. Therefore, it is particularly important to study the sequence-dependent disassembly sequence planning problem. Additionally, disassembly activities are inherently fraught with uncertainties, and neglecting these can further impact the effectiveness of disassembly. This study is the first to analyze the sequence-dependent disassembly sequence planning problem in an uncertain environment. It utilizes a stochastic programming approach to address these uncertainties. Furthermore, a mixed-integer optimization model is constructed to minimize the disassembly time and energy consumption simultaneously. Recognizing the complexity of the problem, this study introduces an innovative bees algorithm, which has proven its effectiveness by showing a superior performance compared to other state-of-the-art algorithms in various test cases. This research offers innovative solutions for the efficient disassembly of end-of-life products and holds significant implications for advancing sustainable development and the recycling of resources. Full article

This paper presents a UAV-based road illumination measurement system and evaluates its performance through experiments. The system employs a HUBSAN Zino 2+ UAV, STM32F103RCT6 microcontroller, BH1750 illuminance sensor, and GPS and integrates flight, processing, measurement, cloud platform, obstacle avoidance, communication, and power supply units via the OneNET cloud platform. Both hardware and software designs were implemented, using the Z-score algorithm to handle outliers in illumination data. The system showed a single-point measurement error rate of 1.14% and a MAPE of 5.08% for multi-point measurements. In experiments, the system’s horizontal and vertical illuminance RMSE were 1.92 lx and 1.75 lx, respectively. The real-time visualization interface improved operational efficiency, cutting labor costs by half and time costs by nearly four-fifths. UAV control and monitoring from the roadside ensured safety during measurements. The system’s efficiency and wide measurement range enabled extended experiments, collecting illuminance data across multiple horizontal and vertical planes. This resulted in the creation of both horizontal and innovative vertical-plane illuminance distribution maps. These findings provide valuable data for evaluating road lighting quality, enhancing road traffic safety, and improving road illumination design. Full article

Object detection is a crucial capability of autonomous agents for human–robot collaboration, as it facilitates the identification of the current processing state. In industrial scenarios, it is uncommon to have comprehensive knowledge of all the objects involved in a given task. Furthermore, training during deployment is not a viable option. Consequently, there is a need for a detector that is able to adapt to novel objects during deployment without the necessity of retraining or fine-tuning on novel data. To achieve this, we propose to exploit the ability of discriminative embeddings learned by an object re-identification model to generalize to unknown categories described by a few shots. To do so, we extract object crops with a class-agnostic detector and then compare the object features with the prototypes of the novel objects. Moreover, we demonstrate that the embedding is also effective for predicting regions of interest, which narrows the search space of the class-agnostic detector and, consequently, increases processing speed. The effectiveness of our approach is evaluated in an assembly scenario, wherein the majority of objects belong to categories distinct from those present in the training datasets. Our experiments demonstrate that, in this scenario, our approach outperforms the current best few-shot object-detection approach DE-ViT, which also does not perform fine-tuning on novel data, in terms of both detection capability and inference speed. Full article

A reformulation of the dynamical component analysis (DyCA) via an optimization-free approach is presented. The original cost function approach is converted into a numerical linear algebra problem, i.e., the computation of coupled singular-value decompositions. A simple algorithm is presented together with numerical experiments to document the feasability of the approach. This methodology is able to recover the mixing and state matrices of multivariate signals from high-dimensional measured data fully. Full article

This study addresses the integration of machine learning (ML) with supervisory control and data acquisition (SCADA) systems to enhance predictive maintenance and operational efficiency in oil well monitoring. We investigated the applicability of advanced ML models, including Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), and Momentum LSTM (MLSTM), on a dataset of 21,644 operational records. These models were trained to predict a critical operational parameter, FlowRate, which is essential for operational integrity and efficiency. Our results demonstrate substantial improvements in predictive accuracy: the LSTM model achieved an R² score of 0.9720, the BiLSTM model reached 0.9725, and the MLSTM model topped at 0.9726, all with exceptionally low Mean Absolute Errors (MAEs) around 0.0090 for LSTM and 0.0089 for BiLSTM and MLSTM. These high R² values indicate that our models can explain over 97% of the variance in the dataset, reflecting significant predictive accuracy. Such performance underscores the potential of integrating ML with SCADA systems for real-time applications in the oil and gas industry. This study quantifies ML’s integration benefits and sets the stage for further advancements in autonomous well-monitoring systems. Full article

In this paper, Nonlinear Model Predictive Control (NMPC) and Nonlinear Moving Horizon Estimator (NMHE) are combined to control, in a distributed way, a heterogeneous fleet composed of a steering car and a quadcopter. In particular, the ground vehicle in the role of the leader communicates its one-step future position to the drone, which keeps the formation along the desired trajectory. Inequality constraints are introduced in a switching control fashion to the leader’s NMPC formulation to avoid obstacles. In the literature, few works using NMPC and NMHE deal with these two vehicles together. Moreover, the presented scheme can tackle noisy, partial, and missing measurements of the agents’ state. Results show that the ground car can avoid detected obstacles, keeping the tracking errors of both robots in the order of a few centimeters, thanks to trustworthy NMHE estimates and NMPC predictions. Full article

Lane changing behavior (LCB) prediction is a crucial functionality of advanced driver-assistance systems and autonomous vehicles. Predicting whether or not the driver of a considered ego vehicle is likely to change lanes in the near future plays an important role in improving road safety and traffic efficiency. Understanding the underlying intentions behind the driver’s behavior is an important factor for the effectiveness of assistance and monitoring systems. Machine learning (ML) algorithms have been broadly used to predict this behavior by analyzing datasets of traffic and driving data related to the considered ego vehicle. However, this technology has not yet been widely adopted in commercial products. Further improvements in these algorithms are necessary to enhance their robustness and reliability. In some domains, receiver operating characteristic and precision-recall curves are commonly used to evaluate ML algorithms, not considering the effects of process parameters in the evaluation, while it might be necessary to access the performance of these algorithms with respect to such parameters. This paper proposes the use of deep autoencoders to extract multi-level features from datasets, which can then be used to train an ensemble of classifiers. This allows for taking advantage of high feature-extraction capabilities of deep learning models and improving the final result using ensemble learning techniques. The concept of probability of detection is used in combination with the networks employed here to evaluate which classifiers can detect the correct LCB better in a statistical sense. Applications on data acquired from a driving simulator show that the proposed method can be adopted to improve the reliability of the classifiers, and ensemble ANNs perform best in predicting the upcoming human behavior in this dynamical context earlier than 3 s before the event itself. Full article

This paper discusses the development of an automated sorting machine designed as a comprehensive mechatronics educational project. The project integrates mechanical and electrical design, incorporating a robot arm, a microcontroller, sensors, and actuators. The sorting machine uses color identification to sort wooden blocks of three different colors. The blocks are stacked and dropped onto a conveyor belt by a hopper system that employs a solenoid actuator and a servo to release one block at a time at specific intervals. As the belt runs continuously, each block passes under a color sensor, which monitors the color and signals one of three servo-powered mechanical arms to guide the block into the appropriate chute. Each chute is equipped with a capacitive proximity sensor that sends a voltage signal to the robot controller, queuing commands for the robot to pick up the blocks from the bottom of each chute and return them to the hopper to form a continuously running sorting system. This paper details the design and integration of the system’s various elements and the development of the control software. The designed system can drop blocks every 8.05 s, sort each block within 5 s of being sensed, and return them to the sorting system every 12 s. It has a color-sensing accuracy of 97%, with a failure rate of around 7%. The system achieved quick and reliable sorting using various low-cost, accessible, and open-source parts. The project exemplifies a cost-effective solution suitable for mechatronics education, demonstrating the numerous challenges involved in developing automated sorting systems. Full article

This paper presents a study on controlling a rotary inverted pendulum (RIP) system using a hierarchical sliding mode control (HSMC) approach. The objective is to swing up and stabilize the pendulum at a desired position. The proposed HSMC controller addresses the underactuation challenge through a hierarchical structure of sliding surfaces. The particle swarm optimization (PSO) algorithm is used to optimize the controller parameters. Simulations were performed to evaluate the performance of the HSMC controller at different initial pendulum angles, demonstrating its effectiveness in achieving swing-up and stabilization. The integration of the PSO algorithm enhances the controller’s adaptability and robustness, emphasizing the benefits of combining optimization algorithms with controller parameter tuning for underactuated systems like the RIP. Full article

This paper presents a method for learning world models for wheel loaders performing automatic loading actions on a pile of soil. Data-driven models were learned to output the resulting pile state, loaded mass, time, and work for a single loading cycle given inputs that include a heightmap of the initial pile shape and action parameters for an automatic bucket-filling controller. Long-horizon planning of sequential loading in a dynamically changing environment is thus enabled as repeated model inference. The models, consisting of deep neural networks, were trained on data from a 3D multibody dynamics simulation of over 10,000 random loading actions in gravel piles of different shapes. The accuracy and inference time for predicting the loading performance and the resulting pile state were, on average, 95% in 1.2 ms and 97% in 4.5 ms, respectively. Long-horizon predictions were found feasible over 40 sequential loading actions. Full article