PFI-TT: Autonomous Robotic Systems for Bridge Inspection and Evaluation

PFI-TT：用于桥梁检查和评估的自主机器人系统

• 批准号: 1919127
• 负责人: Hung La
• 金额: $ 25万
• 依托单位: Board of Regents, NSHE, obo University of Nevada, Reno
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-08-01 至 2024-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1919127&HistoricalAwards=false
• 关键词: PFI; TT; Autonomous; Robotic; Systems

The broader impact/commercial potential of this Partnerships for Innovation - Technology Translation (PFI-TT) project is to significantly improve the structural health inspection and monitoring of civil infrastructures (bridges, tunnels, dams, etc.) by using automated and non-destructive inspection robots. More than 35% of the 600,000 bridges in the U.S. have been subject to extreme deterioration due to aging, various mechanical and weather conditions, inadequate maintenance, and deficiencies in inspection and evaluation. The cost of inspecting and repairing deteriorating highway bridges in the U.S. alone is estimated at more than $140 billion. Currently, bridges are inspected manually by using visual inspection, chain drag, and non-destructive evaluation (NDE) techniques. However, manual inspection techniques are too slow, labor intensive, and create traffic congestion, leading to demand for efficient, cost-effective, and safe inspection and evaluation. The proposed innovation through new NDE robotic development will bridge the gap between these approaches, allowing inspectors to assess bridge conditions in a timely manner. The project is expected to, for the first time, enable widespread use of advanced robotic technologies across more than 600,000 bridges in the U.S. and will also expand to the international civil infrastructure inspection market. The proposed project will advance the development of bridge inspection robots to automate the NDE data collection process and filter NDE data to enable accurate and reliable assessment of a bridge's condition. Research objectives include: development of hardware and software for NDE sensor-robot integration, non-contact acoustic array for fast inspections, NDE data processing algorithms for automated inspection and evaluation, and three-dimensional data visualization for seamless assessment of a bridge deck's condition. Extensive tests and deployment of the robotic platforms on bridges and other civil infrastructures will be conducted. If successful, the resulting integrated prototype will allow fast, accurate detection and evaluation of bridge conditions and will create a standard tool to enable wide and efficient use of NDE technologies to inspect other infrastructure. The project is expected to represent a major advancement within civil engineering and infrastructure maintenance.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

这一创新-技术转化伙伴关系(PFI-TT)项目的更广泛影响/商业潜力是显著改善对民用基础设施(桥梁、隧道、大坝等)的结构健康检查和监测。通过使用自动化和无损检测机器人。在美国60万座桥梁中，超过35%的桥梁由于老化、各种机械和天气条件、维护不足以及检查和评估方面的缺陷而极度恶化。仅在美国，检查和修复日益恶化的公路桥的成本估计就超过1400亿美元。目前，桥梁检测主要采用目视检测、链条拖曳和无损检测等方法。然而，人工检测技术速度太慢、劳动强度大、造成交通拥堵，导致对高效、经济、安全的检测和评估的需求。通过开发新的无损检测机器人进行的拟议创新将弥合这些方法之间的差距，使检查人员能够及时评估桥梁状况。该项目预计将首次在美国60多万座桥梁上广泛使用先进的机器人技术，并将扩展到国际民用基础设施检测市场。拟议的项目将推动桥梁检测机器人的发展，使无损检测数据收集过程自动化，并对无损检测数据进行过滤，从而能够准确可靠地评估桥梁状况。研究目标包括：开发无损检测传感器-机器人集成的硬件和软件，用于快速检测的非接触式声阵，用于自动检测和评估的无损检测数据处理算法，以及用于无缝评估桥梁桥面状况的三维数据可视化。将在桥梁和其他民用基础设施上进行广泛的测试和机器人平台的部署。如果成功，所产生的集成原型将允许快速、准确地检测和评估桥梁状况，并将创建一个标准工具，使无损检测技术能够广泛和有效地用于检查其他基础设施。该项目预计将代表土木工程和基础设施维护方面的重大进步。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

STEEL DEFECT DETECTION IN BRIDGES USING DEEP ENCODER-DECODER NETWORKS

• DOI: 10.12783/shm2021/36335
• 发表时间: 2022-03
• 期刊: Proceedings of the 13th International Workshop on Structural Health Monitoring
• 作者: Habib Ahmed;H. La

Deep Reinforcement Learning for Robotic Manipulation Tasks using a Genetic Algorithm-based Function Optimizer

使用基于遗传算法的函数优化器进行机器人操作任务的深度强化学习

• 发表时间: 2023
• 期刊: Encyclopedia with semantic computing and robotic intelligence
• 作者: Sehgal, Adarsh;Ward, Nicholas;La, Hung Manh;Louis, Sushil
• 通讯作者: Louis, Sushil

Multi-directional Bicycle Robot for Bridge Inspection with Steel Defect Detection System

• DOI: 10.1109/iros47612.2022.9981325
• 发表时间: 2022-10
• 期刊: 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
• 作者: Habib Ahmed;S. Nguyen;D. La;C. Le;Hung M. La

Flying-Climbing Mobile Robot for Steel Bridge Inspection

钢桥检测飞爬式移动机器人

• DOI: 10.1109/ssrr53300.2021.9597676
• 发表时间: 2021
• 期刊: and Rescue Robotics (SSRR
• 作者: Pham, Anh Q.;La, Anh T.;Chang, Ethan;La, Hung M.
• 通讯作者: La, Hung M.

Deep Architecture Based Spalling Severity Detection System Using Encoder-Decoder Networks

• DOI: 10.1007/978-3-031-20716-7_26
• 发表时间: 2022
• 作者: Tamanna Yasmin;C. Le;Hung M. La