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

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

Visual based Tomato Size Measurement System for an Indoor Farming Environment

Visual based Tomato Size Measurement System for an Indoor Fa...

引用

2022 Australasian Conference on robotics and automation, ACRA 2022

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 University of Auckland New Zealand

ISBN: (纸本)9781713866480

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. © 2022 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

Improving Pallet Detection Using Synthetic Data

Improving Pallet Detection Using Synthetic Data

引用

2023 Australasian Conference on robotics and automation, ACRA 2023

作者： Gann, Henry Bull, Josiah Gee, Trevor Nejati, Mahla Centre for Automation and Robotic Engineering Science The University of Auckland New Zealand

The use of synthetic data in machine learning saves a significant amount of time when implementing an effective object detector. However, there is limited research in this domain. This study aims to improve upon previously applied implementations in the task of instance segmentation of pallets in a warehouse environment. This study proposes using synthetically generated domain-randomised data as well as data generated through Unity to achieve this. This study achieved performance improvements on the stacked and racked pallet categories by 69% and 50% mAP50, respectively when being evaluated on real data. Additionally, it was found that there was a considerable impact on the performance of a model when it was evaluated against images in a darker environment, dropping as low as 3% mAP50 when being evaluated on images with an 80% brightness reduction. This study also created a two-stage detector that used YOLOv8 and SAM, but this proved to have unstable performance. The use of domain-randomised data proved to have negligible performance improvements when compared to the Unity-generated data. © 2023 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

Deep Reinforcement Learning for Local Path Following of an Autonomous Formula SAE Vehicle

Deep Reinforcement Learning for Local Path Following of an A...

引用

2023 Australasian Conference on robotics and automation, ACRA 2023

作者： Merton, Harvey Delamore, Thomas Stol, Karl Williams, Henry Centre for Automation and Robotic Engineering Science The University of Auckland New Zealand

With the continued introduction of driverless events to Formula:Society of Automotive Engineers (F:SAE) competitions around the world, teams are investigating all aspects of the autonomous vehicle stack. This paper presents the use of Deep Reinforcement Learning (DRL) and Inverse Reinforcement Learning (IRL) to map locally-observed cone positions to a desired steering angle for race track following. Two state-of-the-art algorithms not previously tested in this context: soft actor critic (SAC) and adversarial inverse reinforcement learning (AIRL), are used to train models in a representative simulation. Three novel reward functions for use by RL algorithms in an autonomous racing context are also discussed. Tests performed in simulation and the real world suggest that both algorithms can successfully train models for local path following. Suggestions for future work are presented to allow these models to scale to a full F:SAE vehicle. © 2023 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：