As one of the core applications of computer vision, object detection has become more important in scenarios requiring high accuracy but with limited computational resources such as robotics and autonomous vehicles. Object detection using machine learning running on embedded device such as Raspberry Pi provides the high possibility to detect any custom objects without the recalibration of camera. In this work, we developed a smart and lean object detection model for shipping containers by using the state-of-the-art deep learning TensorFlow model and deployed it to a Raspberry Pi. Using EfficientDet-Lite2, we explored the different cross-validation strategies (Hold-out and K-Fold). The experimental results show that compared with the baseline EfficientDet-Lite2 algorithm, our model improved the mean average precision (mAP) by 44.73% for the Hold-out dataset and 6.26% for K-Fold cross-validation. We achieved Average Precision (AP) of more than 80% and best detection scores of more than 93% for the Hold-out dataset. For the 5-Fold lean dataset, the results show the Average Precision across the three lightweight models are generally high as the models achieved more than 50% average precision, with YOLOv4 Tiny performing better than EfficientDet-Lite2 and Single Shot Detector (SSD) MobileNet V2 Feature Pyramid Network (FPN) 320 as a lightweight model.

The increasing demand for lithium-ion batteries (LiBs) in electric vehicles, renewable energy storage and consumer electronics necessitates a transition towards high-performance, cost-effective, and sustainable manufacturing. Traditional manufacturing methods rely heavily on empirical trial-and-error approaches, leading to inefficiencies such as process variability, material waste and increased production costs. Recent advancements in digitalization, particularly artificial intelligence (AI) driven digital twins, offer transformative solutions to these challenges. This review presents a systematic framework for integrating AI and digital twin technologies into battery manufacturing, emphasizing their role in predictive maintenance, quality control, and process optimization. Unlike existing reviews, which primarily focus on theoretical modelling, this work examines real-world industrial applications, discusses challenges in large-scale AI adoption, and provides a practical roadmap for implementation. Key contributions include an analysis of digital models, shadows and twins in optimizing battery manufacturing processes and defect detection. Additionally, we highlight the contributions of Raw Material Suppliers, Battery Manufacturers, Technology and Innovation Partners, Policymakers and Regulators, along with actionable plans in establishing a fully digitalized battery production ecosystem. By bridging conventional manufacturing with intelligent digital frameworks, this review outlines a path toward scalable, high-quality, and sustainable battery production.

Object detection for a pick-and-place system has been widely acknowledged as a significant research area in the field of computer vision. The integration of AI and machine vision with pick-and-place operations should be made affordable for Small and Medium Enterprises (SMEs) so they can leverage this technology. Therefore, the aim of this study is to develop a smart and lean pick-and-place solution for custom workpieces, which requires minimal computational resources. In this study, we evaluate the effectiveness of illumination and batch size to improve the Average Precision (AP) and detection score of an EfficientDet-Lite model. The addition of 8% optimized bright Alpha3 images results in an increase of 7.5% in AP and a 6.3% increase in F1-score as compared to the control dataset. Using a training batch size of 4, the AP is significantly improved to 66.8% as compared to a batch size of 16 at 57.4%. The detection scores are improved to 80% with a low variance of 1.65 using a uniform 135-angle lamp and 0 illumination level. The pick-and-place solution is validated using Single-Shot Detector (SSD) MobileNet V2 Feature Pyramid Network (FPN) Lite. Our experimental results clearly show that the proposed method has an increase of 5.19% in AP compared to SSD MobileNet V2 FPNLite.

Pick-and-place operations are an integral part of robotic automation and smart manufacturing. By utilizing deep learning techniques on resource-constraint embedded devices, the pick-and-place operations can be made more accurate, efficient, and sustainable, compared to the high-powered computer solution. In this study, we propose a new technique for object detection on an embedded system using SSD Mobilenet V2 FPN Lite with the optimisation of the hyperparameter and image enhancement. By increasing the Red Green Blue (RGB) saturation level of the images, we gain a 7% increase in mean Average Precision (mAP) when compared to the control group and a 20% increase in mAP when compared to the COCO 2017 validation dataset. Using a Learning Rate of 0.08 with an Edge Tensor Processing Unit (TPU), we obtain high real-time detection scores of 97%. The high detection scores are important to the control algorithm, which uses the bounding box to send a signal to the collaborative robot for pick-and-place operation.

This study presents a zero-shot object detection framework for corner casting detection in shipping container operations, leveraging edge computing for intelligent robotic perception and control. The proposed system integrates Grounding DINO on a Raspberry Pi, utilizing Referring Expression Comprehension (REC) and Additional Feature Keywords (AFKs) to enable precise corner casting localization without model retraining. This approach reduces computational overhead while ensuring real-time deployment suitability for robotics applications. A comparative evaluation against three SSD-based models—SSD320 MobileNet-V2 FPNLite, MobileNet-V2, and EfficientDet-Lite0—reveals that Grounding DINO achieves a 7.14% higher detection score. Furthermore, a statistical effect size analysis using Cohen’s d (d = 2.2) confirms a significant performance advantage, reinforcing Grounding DINO’s efficacy in zero-shot scenarios. These findings underscore the potential of LLM-driven object detection in resource-constrained environments, offering a scalable and adaptable solution for intelligent perception and control in robotics.

Optimising the learning rate is essential for efficient neural network training, but static methods can cause overshooting or undershooting, while adaptive techniques like ADAM often struggle to balance exploration and exploitation. We introduce the Polling Method, an ensemble-based optimisation approach that dynamically selects the most effective learning rate at each step, improving convergence and mitigating issues inherent in traditional optimisation strategies. By evaluating base models with varying learning rates at each epoch, the method adaptively balances exploration and exploitation without being constrained by predefined functions or gradient noise. This study details the theoretical foundation, implementation, and integration of the Polling Method with the ADAM optimiser, demonstrating its effectiveness in Artificial Neural Networks and Bayesian variational inference. The results demonstrate that Polling Method-ADAM reduces absolute error by 50% compared to ADAM alone, while also accelerating convergence. In Bayesian optimisation, it reduces the mean gradient shift from 0.85 to 0.7835 over 500 iterations, indicating improved stability in high-dimensional problems. By introducing adaptive learning rate selection within training, the Polling Method enhances optimisation efficiency while mitigating noise accumulation. This framework provides a computationally efficient, flexible alternative for deep learning applications, offering significant improvements over traditional optimisers and a potential breakthrough in neural network training strategies.