检索结果-内蒙古大学图书馆

Pallet Detection from Synthetic Data using Game Engines

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Naidoo, Jouveer Bates, Nicholas Gee, Trevor Nejati, Mahla Centre for Automation and Robotic Engineering Science The University of Auckland New Zealand

This research sets out to assess the viability of using game engines to generate synthetic training data for machine learning in the context of pallet segmentation. Using synthetic data has been proven in prior research to be a viable means of training neural networks, and saves hours of manual labour due to the reduced need for manual image annotation. Machine vision for pallet detection can benefit from synthetic data as the industry increases the development of autonomous warehousing technologies. As per our methodology, we developed a tool capable of automatically generating large amounts of annotated training data from 3D models at pixel-perfect accuracy and a much faster rate than manual approaches. Regarding image segmentation, a Mask R-CNN pipeline was used, which achieved an AP50 of 86% for individual pallets. Copyright © 2023, The Authors. All rights reserved.

关键词： Pallets

Racing Towards Reinforcement Learning based control of an Autonomous Formula SAE Car

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Salvaji, Aakaash Taylor, Harry Valencia, David Gee, Trevor Williams, Henry Centre for Automation and Robotic Engineering Science The University of Auckland New Zealand

With the rising popularity of autonomous navigation research, Formula Student (FS) events are introducing a Driverless Vehicle (DV) category to their event list. This paper presents the initial investigation into utilising Deep Reinforcement Learning (RL) for end-to-end control of an autonomous FS race car for these competitions. We train two state-of-the-art RL algorithms in simulation on tracks analogous to the full-scale design on a Turtlebot2 platform. The results demonstrate that our approach can successfully learn to race in simulation and then transfer to a real-world racetrack on the physical platform. Finally, we provide insights into the limitations of the presented approach and guidance into the future directions for applying RL toward full-scale autonomous FS racing. © 2023, CC BY-NC-SA.

关键词： Reinforcement learning

Visual based Tomato Size Measurement System for an Indoor Farming Environment

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Kweon, Andy Hu, Vishnu Lim, Jong Yoon Gee, Trevor Liu, Edmond Williams, Henry MacDonald, Bruce A. Nejati, Mahla Sa, Inkyu Ahn, Ho Seok Centre for Automation and Robotic Engineering Science The University of Auckland New Zealand

As technology progresses, smart automated systems will serve an increasingly important role in the agricultural industry. Current existing vision systems for yield estimation face difficulties in occlusion and scalability as they utilize a camera system that is large and expensive, which are unsuitable for orchard environments. To overcome these problems, this paper presents a size measurement method combining a machine learning model and depth images captured from three low cost RGBD cameras to detect and measure the height and width of tomatoes. The performance of the presented system is evaluated on a lab environment with real tomato fruits and fake leaves to simulate occlusion in the real farm environment. To improve accuracy by addressing fruit occlusion, our three-camera system was able to achieve a height measurement accuracy of 0.9114 and a width accuracy of 0.9443. Copyright © 2023, The Authors. All rights reserved.

关键词： Fruits

Utilising Explainable Techniques for Quality Prediction in a Complex Textiles Manufacturing Use Case

学校读者我要写书评

暂无评论

Utilising Explainable Techniques for Quality Prediction in a...

IEEE International Conference on automation science and engineering (CASE)

作者： Briony Forsberg Henry Williams Bruce MacDonald Tracy Chen Reza Hamzeh Kirstine Hulse Centre for Automation and Robotic Engineering Science The University of Auckland New Zealand Bremworth Ltd Auckland New Zealand

ISBN: (数字)9798350358513

ISBN: (纸本)9798350358520

This paper develops an approach to classify instances of product failure in a complex textiles manufacturing dataset using explainable techniques. The dataset used in this study was obtained from a New Zealand manufacturer of woollen carpets and rugs. In investigating the trade-off between accuracy and explainability, three different tree-based classification algorithms were evaluated: a Decision Tree and two ensemble methods, Random Forest and XGBoost. Additionally, three feature selection methods were also evaluated: the SelectKBest method, using chi-squared as the scoring function, the Pearson Correlation Coefficient, and the Boruta algorithm. Not surprisingly, the ensemble methods typically produced better results than the Decision Tree model. The Random Forest model yielded the best results overall when combined with the Boruta feature selection technique. Finally, a tree ensemble explaining technique was used to extract rule lists to capture necessary and sufficient conditions for classification by a trained model that could be easily interpreted by a human. Notably, several features that were in the extracted rule lists were statistical features and calculated features that were added to the original dataset. This demonstrates the influence that bringing in additional information during the data preprocessing stages can have on the ultimate model performance.

关键词： Radio frequency Correlation coefficient Data preprocessing Feature extraction Data models Classification algorithms Manufacturing Decision trees Ensemble learning Random forests

Textile Anomaly Detection: Evaluation of the State-of-the-Art for Automated Quality Inspection of Carpet

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Forsberg, Briony Williams, Henry MacDonald, Bruce Chen, Tracy Hulse, Kirstine Centre for Automation and Robotic Engineering Science The University of Auckland New Zealand Bremworth Ltd Auckland New Zealand

In this study, state-of-the-art unsupervised detection models were evaluated for the purpose of automated anomaly inspection of wool carpets. A custom dataset of four unique types of carpet textures was created to thoroughly test the models and their robustness in detecting subtle anomalies in complex textures. Due to the requirements of an inline inspection system in a manufacturing use case, the metrics of importance in this study were accuracy in detecting anomalous areas, the number of false detections, and the inference times of each model for real-time performance. Of the evaluated models, the student-teacher network based methods were found on average to yield the highest detection accuracy and lowest false detection rates. When trained on a multi-class dataset the models were found to yield comparable if not better results than single-class training. Finally, in terms of detection speed, with exception to the generative model, all other evaluated models were found to have comparable inference times on a GPU, with an average of 0.16s per image. On a CPU, most of these models typically produced results between 1.5 to 2 times the respective GPU inference times. © 2024, CC BY-NC-SA.

关键词： Textures

Utilising Explainable Techniques for Quality Prediction in a Complex Textiles Manufacturing Use Case

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Forsberg, Briony Williams, Henry MacDonald, Bruce Chen, Tracy Hamzeh, Reza Hulse, Kirstine Centre for Automation and Robotic Engineering Science The University of Auckland New Zealand Bremworth Ltd Auckland New Zealand

关键词： Random forests

Development of a Novel Multipurpose robotic End Effector for Fruitlet Thinning and Fruit Harvesting of Apples

学校读者我要写书评

暂无评论

Development of a Novel Multipurpose Robotic End Effector for...

IEEE International Conference on automation science and engineering (CASE)

作者： Rahul Jangali Ben McGuinness Hin Lim Henry Williams Ans H. Qureshi David Smith Bruce A. MacDonald Mike Duke School of Engineering University of Waikato Hamilton New Zealand Centre for Automation and Robotic Engineering Science The University of Auckland New Zealand

ISBN: (数字)9798350358513

ISBN: (纸本)9798350358520

This paper presents a novel multipurpose end effector for robotic applications, characterised by its vacuum suction, rotation capabilities, modular design, and versatility in both apple thinning and harvesting. The key feature is enabling interchangeable suction cups by isolating the rotation mechanism from the suction mechanism. The suction cups sizes can then be changed based on the target fruit or fruitlet diameter sizes and damage protection requirement of the target. This end effector was first evaluated in both laboratory settings and real-world commercial apple orchards for apple fruitlets. In laboratory evaluation, the best performance occurred when its rotation axis was closely aligned with the fruit’s calyx-stem axis. The increased deviation between the two axes results in slippage and obstruction from surrounding fruits or fruitlets. Field tests in commercial orchards yielded a 66.1% success rate for apple thinning, and the main limitation was also due to the misalignment between the two axes. The end effector was also successfully preliminary field tested for apple harvesting, showing promise of its feasibility.

关键词： Computer aided software engineering automation End effectors Protection Robots

The Barracuda: A Novel Cutting Mechanism for Pruning Canes Wrapped around Wires

学校读者我要写书评

暂无评论

The Barracuda: A Novel Cutting Mechanism for Pruning Canes W...

IEEE International Conference on automation science and engineering (CASE)

作者： Henry Williams Scott Harvey Ben McGuinness David Smith Hin Lim Mike Duke Centre for Automation and Robotic Engineering Science The University of Auckland New Zealand School of Engineering University of Waikato Hamilton New Zealand

ISBN: (数字)9798350358513

ISBN: (纸本)9798350358520

This paper presents the design and evaluation of the Barracuda, a novel pruning tool for robotic automation to cut grapevine canes tightly wrapped around wires. The Barracuda’s anvil has specially designed grooves that allow the wire to move passively out of the way while the blade completes the cut on the cane. The intention is to enable a robotic cane pruning platform to prune canes on wires without precise positioning of the device or manipulation of the wires. The device was extensively tested in real-world commercial vineyards to evaluate how effectively it can produce clean cuts suitable for pruning. Cutting performance showed a successful cut rate of 94.5% with negligible wire damage on over 300 cuts. Evaluations on the robotic platform showed it could successfully prune 71.1% of canes while utilising this design.

关键词： Performance evaluation automation Computer aided software engineering Blades Wires Pipelines Robots

Archie Jnr: A robotic Platform for Autonomous Cane Pruning of Grapevines

学校读者我要写书评

暂无评论

Archie Jnr: A Robotic Platform for Autonomous Cane Pruning o...

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Henry Williams David Smith Jalil Shahabi Trevor Gee Ans Qureshi Ben McGuinness Scott Harvey Catherine Downes Rahul Jangali Kale Black Hin Lim Mike Duke Bruce A. MacDonald Centre for Automation and Robotic Engineering Science The University of Auckland New Zealand School of Engineering University of Waikato Hamilton New Zealand

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Cane pruning grapevines is a complex manual task requiring expert vine assessment to determine which canes to prune. This paper presents Archie Jnr, which was developed to autonomously assess the structure of the vine and prune the lower-quality canes as an expert pruner would. The platform has been extensively evaluated in a real-world commercial vineyard using a three-cane pruning method. The results show the effectiveness of the vision system for generating accurate assessments of a vine’s canes. The platform is also shown to be capable of successfully pruning 71.1% of the 311 total canes that required pruning across 25 vines.

关键词： Measurement Cutting tools Accuracy Machine vision Pipelines Refining Manuals Intelligent robots Dolphins