检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Yamani, Hoda Xing, Yuning Ong, Lee Violet C. MacDonald, Bruce A. Williams, Henry Centre for Automation and Robotic Engineering Science The University of Auckland New Zealand

Reinforcement Learning algorithms aim to learn optimal control strategies through iterative interactions with an environment. A critical element in this process is the experience replay buffer, which stores past experiences, allowing the algorithm to learn from a diverse range of interactions rather than just the most recent ones. This buffer is especially essential in dynamic environments with limited experiences. However, efficiently selecting high-value experiences to accelerate training remains a challenge. Drawing inspiration from the role of reward prediction errors (RPEs) in biological systems, where they are essential for adaptive behaviour and learning, we introduce Reward Predictive Error Prioritised Experience Replay (RPE-PER). This novel approach prioritises experiences in the buffer based on RPEs. Our method employs a critic network, EMCN, that predicts rewards in addition to the Q-values produced by standard critic networks. The discrepancy between these predicted and actual rewards is computed as RPE and utilised as a signal for experience prioritisation. Experimental evaluations across various continuous control tasks demonstrate RPE-PER’s effectiveness in enhancing the learning speed and performance of off-policy actor-critic algorithms compared to baseline approaches. Copyright © 2025, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

OrchardDepth: Precise Metric Depth Estimation of Orchard Scene from Monocular Camera Images

arXiv

引用

arXiv 2025年

作者： Zheng, Zhichao Williams, Henry MacDonald, Bruce A. Centre for Automation and Robotic Engineering Science New Zealand The University of Auckland New Zealand

Monocular depth estimation is a rudimentary task in robotic perception. Recently, with the development of more accurate and robust neural network models and different types of datasets, monocular depth estimation has significantly improved performance and efficiency. However, most of the research in this area focuses on very concentrated domains. In particular, most of the benchmarks in outdoor scenarios belong to urban environments for the improvement of autonomous driving devices, and these benchmarks have a massive disparity with the orchard/vineyard environment, which is hardly helpful for research in the primary industry. Therefore, we propose OrchardDepth, which fills the gap in the estimation of the metric depth of the monocular camera in the orchard/vineyard environment. In addition, we present a new retraining method to improve the training result by monitoring the consistent regularization between dense depth maps and sparse points. Our method improves the RMSE of depth estimation in the orchard environment from 1.5337 to 0.6738, proving our method’s validation. © 2025, CC BY-NC-ND.

关键词： Orchards

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Quality of Kiwifruit Pollinated with an Autonomous Robot

Field Robotics

引用

Field robotics 2025年 1卷 1-22页

作者： Henry Williams Jamie Bell Mahla Nejati Salome Hussein Nicky Penhall JongYoon Lim Mark Hedley Jones Ho Seok Ahn Stuart Bradley Peter Schaare Paul Martinsen Melissa Broussard Matthew Seabright Mike Duke Alistair Scarfe Bruce MacDonald Centre for Automation and Robotic Engineering Science University of Auckland Auckland New Zealand Plant and Food Research Waikato Hamilton New Zealand School of Engineering University of Waikato Hamilton New Zealand Robotics Plus Ltd Newnham Innovation Park Tauranga New Zealand

The growing popularity of kiwifruit orchards in New Zealand is increasing the already high demand for traditional pollinators (bees), with alternatives currently too costly for most growers due to high labour requirements or inefficient usage of expensive pollen. A novel pollinating robot has been previously described to provide a more efficient, reliable and cost-effective means of addressing this problem. However, the pollinator suffered from a low fruit-set rate of 40% overall, well below commercial requirements of 80% to 90%. This paper presents two new developments for that system: a new, off the shelf spray nozzle (SS1504) to increase the overall pollen delivery and an automated height controller to keep the spray manifolds at a consistent distance below the canopy while avoiding obstacles. Furthermore, we have designed and conducted a more controlled, real-world evaluation of the pollination system to compare both nozzle variants and measure the commercial viability of the pollination platform. Final results show that, operating from a mobile platform at 2.5kmh −1 , the new nozzle could consistently achieve a fruit-set rate only 16 ± 2% below the control samples in each test orchard (82 ± 2% and 72 ± 4% absolute). Pollen consumption remains high, however, with estimates of up to 4.6 kg ha −1 , thus preventing the system from being economically viable. While cost-effectiveness awaits substantial efficiency improvements, our work has demonstrated an automated pollinator that can produce commercial-grade kiwifruit.

关键词： Pollination (plants) Robots Manifolds Reliability Machine vision Spraying Costs Cameras Robot vision systems Insects

来源：评论

学校读者我要写书评

暂无评论

Pallet Detection And Localisation From Synthetic Data

arXiv

引用

arXiv 2025年

作者： Mueller, Henri Kim, Yechan Gee, Trevor Nejati, Mahla Centre for Automation and Robotic Engineering Science The University of Auckland New Zealand

The global warehousing industry is experiencing rapid growth, with the market size projected to grow at an annual rate of 8.1% from 2024 to 2030 [Grand View Research, 2021]. This expansion has led to a surge in demand for efficient pallet detection and localisation systems. While automation can significantly streamline warehouse operations, the development of such systems often requires extensive manual data annotation, with an average of 35 seconds per image, for a typical computer vision project. This paper presents a novel approach to enhance pallet detection and localisation using purely synthetic data and geometric features derived from their side faces. By implementing a domain randomisation engine in Unity, the need for time-consuming manual annotation is eliminated while achieving high-performance results. The proposed method demonstrates a pallet detection performance of 0.995 mAP50 for single pallets on a real-world dataset. Additionally, an average position accuracy of less than 4.2 cm and an average rotation accuracy of 8.2° were achieved for pallets within a 5-meter range, with the pallet positioned head-on. © 2025, CC BY-NC-ND.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Kiwifruit detection in challenging conditions

Kiwifruit detection in challenging conditions

引用

Australasian Conference on robotics and automation 2019, ACRA 2019

作者： Nejati, Mahla Penhall, Nicky Williams, Henry Bell, Jamie Lim, JongYoon Ahn, Ho Seok MacDonald, Bruce Centre for Automation and Robotic Engineering Science University of Auckland Auckland New Zealand

Accurate and reliable kiwifruit detection is one of the biggest challenges in developing a selective fruit harvesting robot. The vision system of an orchard robot faces difficulties such as dynamic lighting conditions and fruit occlusions. This paper presents a semantic segmentation approach with two novel image prepossessing techniques designed to detect kiwifruit under the harsh lighting conditions found in the canopy. The performance of the presented system is evaluated on a 3D real-world image set of kiwifruit under different lighting conditions (typical, glare, and overexposed). Alone the semantic segmentation approach achieves an F1score of 0.82 on the typical lighting image set, but struggles with harsh lighting with an F1score of 0.13. Utilising the prepossessing techniques the vision system under harsh lighting improves to an F1score 0.42. To address the fruit occlusion challenge, the overall approach was found to be capable of detecting 87.0% of non-occluded and 30.0% of occluded kiwifruit across all lighting conditions. © 2019 Australasian robotics and automation Association. All rights reserved.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Design of a sensing module for a kiwifruit flower pollinator robot

Design of a sensing module for a kiwifruit flower pollinator...

引用

Australasian Conference on robotics and automation 2019, ACRA 2019

作者： Nejati, Mahla Ahn, Ho Seok MacDonald, Bruce Centre for Automation and Robotic Engineering Science University of Auckland Auckland New Zealand

This paper describes steps taken to develop a sensing module for a robotic kiwifruit flower pollinator, which could be integrated into an imaging module and a spray module. The paper described different indicators to present the performance of the sensing module that can be used as a benchmark. The sensing module provides data for the imaging module to detect kiwifruit flower reliably and accurately in the canopy. Four major challenges for a sensing module is the speed, accuracy, visibility, and robustness to variable lighting conditions. Regarding these issues, Basler acA1920-40uc camera with an LM6HC lens were selected from a list of fast cameras and lenses based on different parameters. The sensing module was tested in four orchards and captured 9128 images. According to the saturation rate parameter, the captured images were typical in 96% of conditions and the rest were glare due to the sunny weather and early season. The camera speed and field of view guarantee that in the highest speed of the robot a flower can be seen at least in three images in normal conditions. The sensing module was calibrated with less than 3mm error and integrated to the spray module. The pollinator module was mounted on a robot and tested in the real world and achieved 79.5% hit rate at an average velocity of 3.5 km/h. © 2019 Australasian robotics and automation Association. All rights reserved.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Deep reinforcement learning for path planning

Deep reinforcement learning for path planning

引用

Australasian Conference on robotics and automation 2019, ACRA 2019

作者： Bulog, Eugene Frost, Matthew Williams, Henry Centre for Automation and Robotic Engineering Science University of Auckland Auckland New Zealand

Truly autonomous mobile robots are desirable, as they can perform tasks that require robustness to new environments. Reinforcement learning enables a robot to discover optimal policies through trial-and-error by interacting with its environment, but requires diverse training data to effectively generalise between seen and unseen environments. The topic of our research project is a simulated environment for mobile robotics that provides a variety of environments to train navigational models in. This report details the project implementation, the environments used for training and benchmarking, and the results of the research performed. Implementations compared are the DDPG and PPO reinforcement learning approaches, as well as the more traditional approach to path-planning taken by an implementation of the DWA algorithm. The research in this report finds that reinforcement learning agents are able to successfully generalize their navigational policies to unseen environments, and that reinforcement learning agents can outperform selected traditional path-planning techniques in a number of settings. © 2019 Australasian robotics and automation Association. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Reward Prediction Error Prioritisation in Experience Replay: The RPE-PER Method

Reward Prediction Error Prioritisation in Experience Replay:...

引用

2024 Australasian Conference on robotics and automation, ACRA 2024

作者： Yamani, Hoda Xing, Yuning Ong, Lee Violet C. MacDonald, Bruce A. Williams, Henry Centre for Automation and Robotic Engineering Science The University of Auckland New Zealand

Reinforcement Learning algorithms aim to learn optimal control strategies through iterative interactions with an environment. A critical element in this process is the experience replay buffer, which stores past experiences, allowing the algorithm to learn from a diverse range of interactions rather than just the most recent ones. This buffer is especially essential in dynamic environments with limited experiences. However, efficiently selecting high-value experiences to accelerate training remains a challenge. Drawing inspiration from the role of Reward Prediction Error (RPE) in biological systems, we introduce Reward Predictive Error Prioritised Experience Replay (RPE-PER). RPE signals reflect the difference between expected and actual rewards in the brain, driving adaptive behaviour and learning adjustment. Our method employs a critic network, EMCN, that predicts rewards in addition to the Q-values produced by standard critic networks. The discrepancy between these predicted and actual rewards is computed as RPE and utilised as a signal for experience prioritisation. Experimental evaluations across various continuous control tasks demonstrate RPE-PER’s effectiveness in enhancing the learning speed and performance of off-policy actor-critic algorithms compared to baseline approaches. © 2024 Australasian robotics and automation Association. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Pallet Detection from Synthetic Data using Game Engines

Pallet Detection from Synthetic Data using Game Engines

引用

2022 Australasian Conference on robotics and automation, ACRA 2022

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

ISBN: (纸本)9781713866480

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. © 2022 Australasian robotics and automation Association. All rights reserved.

关键词： Pallets

来源：评论

学校读者我要写书评

暂无评论

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

Racing Towards Reinforcement Learning based control of an Au...

引用

2022 Australasian Conference on robotics and automation, ACRA 2022

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

ISBN: (纸本)9781713866480

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. © 2022 Australasian robotics and automation Association. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：