4.7 Article

An imitation from observation approach for dozing distance learning in autonomous bulldozer operation

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Computer Science, Artificial Intelligence

Recovery planning of industrial robots based on semantic information of failures and time-dependent utility

Satoru Matsuoka et al.

Summary: This paper proposes a recovery planning system for industrial robots that considers the semantic information behind errors during robotic actions. It establishes general repair strategies for feasible recovery plans under uncertainties using a conceptual graph and a Bayesian network. The system controls the decision model effectively and demonstrates its effectiveness through simulations of assembly tasks by multiple robots.

ADVANCED ENGINEERING INFORMATICS (2022)

Article Computer Science, Artificial Intelligence

Evolution pathways of robotic technologies and applications in construction

Siwei Chang et al.

Summary: This study traces the evolution pathways of construction robotics technologies using critical juncture timings, identifying four development stages since 1983 and revealing three critical junctures. It finds that the demand for construction robots emerged after 2015 and the robot configuration evolved from large-scale machinery to smaller and movable vehicles. Image-related sensor systems and processing algorithms have become popular after 2009, enabling more accurate operation in unknown and complex environments.

ADVANCED ENGINEERING INFORMATICS (2022)

Article Construction & Building Technology

Robotic architectural assembly with tactile skills: Simulation and optimization

Boris Belousov et al.

Summary: Research shows that a combination of reinforcement learning and planning can be used to autonomously assemble structures with a robotic arm, and trial-and-error algorithms have proven effective in this field. Although the achieved results are imperfect, they serve as a proof of concept and indicate directions for further research.

AUTOMATION IN CONSTRUCTION (2022)

Article Computer Science, Artificial Intelligence

Fine-grained semantic ethnic costume high-resolution image colorization with conditional GAN

Di Wu et al.

Summary: This study introduces a high-resolution image colorization model for ethnic costumes targeting enhancement, inspired by semantic-level colorization, which utilizes fine-grained semantic information to maintain color distribution correspondence and spatial consistency of costume images. Extensive experiments demonstrate its superior performance compared to other state-of-the-art automatic colorization methods.

INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS (2022)

Article Computer Science, Artificial Intelligence

Intelligent trademark recognition and similarity analysis using a two-stage transfer learning approach

Amy J. C. Trappey et al.

Summary: This research develops an intelligent system that can detect, locate, and crop logos posted online and check their similarity to registered trademarks. It integrates two deep learning models for logo detection and localization, as well as trademark similarity analysis. The system achieves high precision in trademark class matching.

ADVANCED ENGINEERING INFORMATICS (2022)

Article Computer Science, Artificial Intelligence

Mixed reality environment for learning sensing technology applications in Construction: A usability study

Omobolanle R. Ogunseiju et al.

Summary: Mixed reality is becoming increasingly important in education, especially in construction engineering education where it can provide students with practical skills and overcome resource constraints. This study explores the design features of a mixed reality learning environment and reveals the importance of accuracy, animation quality, and easy access to information and resources. The use of knowledge scaffolding improves task performance in mixed reality learning environments.

ADVANCED ENGINEERING INFORMATICS (2022)

Article Computer Science, Artificial Intelligence

End-to-end deep learning for reverse driving trajectory of autonomous bulldozer

Ke You et al.

Summary: This study proposes a decision planning method based on deep learning for the intelligent construction of autonomous bulldozers. The method can obtain relevant image features in both spatial attention and channel attention based on modified coordinate attention, showing advantages compared to traditional convolutional methods. By fusing multimodal data, including images and construction trajectories, the method can obtain the output of turning angle and turning point and calculate the reverse driving trajectory. Visualization analysis shows the interpretability of the network, and the method is proven to have anthropomorphic intelligence and is effective in practical construction.

KNOWLEDGE-BASED SYSTEMS (2022)

Article Computer Science, Artificial Intelligence

Fine-tuning deep learning model parameters for improved super-resolution of dynamic MRI with prior-knowledge

Chompunuch Sarasaen et al.

Summary: The study introduces a super-resolution MRI reconstruction method that utilizes prior knowledge and fine-tuning to enhance spatial resolution of dynamic MRI images and reduce scanning time. Experimental results demonstrate that the method can significantly improve image quality while maintaining high similarity with ground-truth images.

ARTIFICIAL INTELLIGENCE IN MEDICINE (2021)

Article Construction & Building Technology

5G-based earthwork monitoring system for an unmanned bulldozer

Ke You et al.

Summary: This paper introduces an unmanned bulldozer for automatic construction with an earthwork monitoring system based on 5G, which improves construction efficiency through unmanned design and automatic operation, and verifies its high reliability and ultra-low latency.

AUTOMATION IN CONSTRUCTION (2021)

Article Computer Science, Interdisciplinary Applications

Combined Transfer Learning and Test-Time Augmentation Improves Convolutional Neural Network-Based Semantic Segmentation of Prostate Cancer from Multi-Parametric MR Images

David Hoar et al.

Summary: In this study, the impact of transfer learning, unsupervised pre-training, and test time augmentation on CNN performance for pixel-by-pixel prediction of cancer vs. non-cancer using mp-MRI datasets was evaluated. The results showed that test time augmentation significantly improved CNN performance, while transfer learning and unsupervised pre-training did not have a significant impact on CNN performance.

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE (2021)

Review Computer Science, Information Systems

A comprehensive review on soil classification using deep learning and computer vision techniques

Pallavi Srivastava et al.

Summary: This paper discusses the importance of soil classification and related technological methods. It covers traditional and modern soil classification techniques, as well as different research databases and evaluation metrics.

MULTIMEDIA TOOLS AND APPLICATIONS (2021)

Article Computer Science, Artificial Intelligence

An intelligent content-based image retrieval methodology using transfer learning for digital IP protection

Amy J. C. Trappey et al.

Summary: Trademarks are used by companies to help customers identify products or services, and the intellectual property rights of trademark owners have strong legal protection when registered with international intellectual property platforms. Unauthorized use of a registered trademark may result in intellectual property infringement.

ADVANCED ENGINEERING INFORMATICS (2021)

Review Computer Science, Artificial Intelligence

A review on image-based approaches for breast cancer detection, segmentation, and classification

Zahra Rezaei

Summary: Breast cancer is one of the most life-threatening diseases among women globally. Early testing and treatment are crucial for improving survival rates. Research focuses on enhancing diagnostic methods, outlining principles, risk factors, and imaging techniques for breast cancer diagnosis.

EXPERT SYSTEMS WITH APPLICATIONS (2021)

Article Computer Science, Artificial Intelligence

Tracking-by-Counting: Using Network Flows on Crowd Density Maps for Tracking Multiple Targets

Weihong Ren et al.

Summary: The paper proposes a new MOT paradigm tailored for crowded scenes, simultaneously finding global optimal detections and trajectories of multiple targets over the whole video, yielding promising results on public benchmarks in various domains.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2021)

Article Engineering, Industrial

Data-driven safety enhancing strategies for risk networks in construction engineering

Fangyu Chen et al.

RELIABILITY ENGINEERING & SYSTEM SAFETY (2020)

Article Construction & Building Technology

Detecting semantic regions of construction site images by transfer learning and saliency computation

Ling Chen et al.

AUTOMATION IN CONSTRUCTION (2020)

Article Computer Science, Artificial Intelligence

Inter-subject transfer learning for EEG-based mental fatigue recognition

Yisi Liu et al.

ADVANCED ENGINEERING INFORMATICS (2020)

Article Construction & Building Technology

Teaching robots to perform quasi-repetitive construction tasks through human demonstration

Ci-Jyun Liang et al.

AUTOMATION IN CONSTRUCTION (2020)

Article Construction & Building Technology

Sensor-based straight-line control of the end-point of a typical retrofitted hydraulic excavator

Dongik Sun et al.

AUTOMATION IN CONSTRUCTION (2020)

Proceedings Paper Computer Science, Artificial Intelligence

Multi-Scale Boosted Dehazing Network with Dense Feature Fusion

Hang Dong et al.

2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2020)

Review Construction & Building Technology

On-site autonomous construction robots: Towards unsupervised building

Nathan Melenbrink et al.

AUTOMATION IN CONSTRUCTION (2020)

Article Construction & Building Technology

Prediction of brake pedal aperture for automatic wheel loader based on deep learning

Junren Shi et al.

AUTOMATION IN CONSTRUCTION (2020)

Article Computer Science, Interdisciplinary Applications

Estimating Worker-Centric 3D Spatial Crowdedness for Construction Safety Management Using a Single 2D Camera

Xuzhong Yan et al.

JOURNAL OF COMPUTING IN CIVIL ENGINEERING (2019)

Article Computer Science, Artificial Intelligence

Times-series data augmentation and deep learning for construction equipment activity recognition

Khandakar M. Rashid et al.

ADVANCED ENGINEERING INFORMATICS (2019)

Article Construction & Building Technology

Application and outlook of information and intelligence technology for safe and efficient TBM construction

Jianbin Li et al.

TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY (2019)

Article Computer Science, Interdisciplinary Applications

Detecting Construction Equipment Using a Region-Based Fully Convolutional Network and Transfer Learning

Hongjo Kim et al.

JOURNAL OF COMPUTING IN CIVIL ENGINEERING (2018)

Review Engineering, Industrial

Engineering management for high-end equipment intelligent manufacturing

Shanlin Yang et al.

FRONTIERS OF ENGINEERING MANAGEMENT (2018)

Article Psychology, Multidisciplinary

Learning from others' experiences: How patterns foster interpersonal transfer of knowledge-in-use

Johannes Moskaliuk et al.

COMPUTERS IN HUMAN BEHAVIOR (2016)

Review Multidisciplinary Sciences

Deep learning

Yann LeCun et al.

NATURE (2015)

Article Construction & Building Technology

Investigating antecedents and drivers affecting the adoption of collaboration technologies in the construction industry

Athanasios Nikas et al.

AUTOMATION IN CONSTRUCTION (2007)

Article Geochemistry & Geophysics

Automatic construction of building footprint's from airborne LIDAR data

Keqi Zhang et al.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2006)

Article Construction & Building Technology

A concept proving prototype of automated earthmoving control

R Navon et al.

AUTOMATION IN CONSTRUCTION (2004)

Article Construction & Building Technology

Framework for an intelligent earthwork system - Part I. System architecture

SK Kim et al.

AUTOMATION IN CONSTRUCTION (2003)

Article Multidisciplinary Sciences

Caterpillar-induced nocturnal plant volatiles repel conspecific females

CM De Moraes et al.

NATURE (2001)

Article Construction & Building Technology

The Computer Integrated Road Construction project

F Peyret et al.

AUTOMATION IN CONSTRUCTION (2000)