CPS: Medium: Accurate and Efficient Collective Additive Manufacturing by Mobile Robots

CPS：中：移动机器人精确高效的集体增材制造

• 批准号: 1932187
• 负责人: Chen Feng
• 金额: $ 120万
• 依托单位: New York University
• 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: 2019-09-01 至 2024-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1932187&HistoricalAwards=false
• 关键词: CPS; Medium; Accurate; Efficient; Collective

Aging civil infrastructure is a critical worldwide problem that affects daily life, making it important to innovate more efficient and economical repair and construction methods for civil structures. Additive manufacturing, or 3D printing, offers a promising way to fulfill this compelling need. However, almost all current additive manufacturing methods rely on gantry-based systems that can only build structures within rigid frames, thereby restricting printing speed and scale, thus hindering their use in maintenance and construction. This award supports fundamental research to establish collective additive manufacturing, a novel robotics-based approach for large-scale 3D printing. Collective additive manufacturing uses a team of autonomous mobile robots to jointly print large-scale 3D structures. The results of the research will have a potentially wide range of applications in civil infrastructure maintenance and construction, to post-disaster response and extraterrestrial construction. The project is based on a convergent research approach involving robotics, artificial intelligence, control theory, and dynamical systems, which culminates in formal and informal learning activities to broaden participation of underrepresented groups in engineering.Collective additive manufacturing envisions the use of teams of mobile robots to overcome key limitations of existing gantry-based additive manufacturing, including its small scale and slow printing speed. To unleash the full potential of collective additive manufacturing, several scientific boundaries must be pushed, ensuring optimal deployment of multiple mobile robots that print large structures according to an engineered, virtual design. This research will fill critical knowledge gaps in robotic localization, control, and coordination, to realize a robotic team that intentionally and actively modifies its surroundings to successfully complete its printing task. This interdisciplinary research program will unfold along three thrusts: artificial intelligence for planning and localization, model predictive control to adapt to printing disturbances and substrate variations, and distributed control to elicit stable collective dynamics. Theoretical advancements will proceed alongside with experimental research toward demonstrating the potential of collective additive manufacturing to accurately and efficiently print large structures in real-world settings.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.

老化的民用基础设施是影响日常生活的一个重要的全球性问题，因此创新更高效、更经济的土木结构修复和施工方法非常重要。增材制造或 3D 打印为满足这一迫切需求提供了一种有前景的方法。然而，目前几乎所有的增材制造方法都依赖于基于龙门的系统，该系统只能在刚性框架内构建结构，从而限制了打印速度和规模，从而阻碍了它们在维护和施工中的使用。该奖项支持建立集体增材制造的基础研究，这是一种基于机器人的新型大规模 3D 打印方法。集体增材制造使用自主移动机器人团队联合打印大型 3D 结构。研究结果将在民用基础设施维护和建设、灾后响应和外星建设方面具有潜在的广泛应用。该项目基于涉及机器人、人工智能、控制理论和动力系统的融合研究方法，最终形成正式和非正式的学习活动，以扩大工程中代表性不足的群体的参与。集体增材制造设想使用移动机器人团队克服现有基于龙门的增材制造的关键局限性，包括规模小和打印速度慢。为了充分发挥集体增材制造的潜力，必须突破几个科学界限，确保根据工程虚拟设计打印大型结构的多个移动机器人的最佳部署。这项研究将填补机器人定位、控制和协调方面的关键知识空白，实现机器人团队有意、主动地改变周围环境以成功完成打印任务。这一跨学科研究计划将沿着三个主旨展开：用于规划和定位的人工智能、适应印刷干扰和基材变化的模型预测控制以及引发稳定的集体动态的分布式控制。理论进步将与实验研究一起进行，以证明集体增材制造在现实环境中准确、高效地打印大型结构的潜力。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技术进行评估，被认为值得支持。更广泛的影响审查标准。

项目成果

Projector-Guided Non-Holonomic Mobile 3D Printing

• DOI: 10.1109/icra48506.2021.9561719
• 发表时间: 2021-05
• 期刊: 2021 IEEE International Conference on Robotics and Automation (ICRA)
• 作者: Xuchu Xu;Ziteng Wang;Chen Feng

Deep Weakly Supervised Positioning for Indoor Mobile Robots

室内移动机器人的深度弱监督定位

• DOI: 10.1109/lra.2021.3138170
• 发表时间: 2022
• 期刊: IEEE Robotics and Automation Letters
• 影响因子: 5.2
• 作者: Wang, Ruoyu;Xu, Xuchu;Ding, Li;Huang, Yang;Feng, Chen
• 通讯作者: Feng, Chen

Towards 3D Perception and Closed-Loop Control for 3D Construction Printing

• DOI: 10.22260/isarc2020/0219
• 发表时间: 2020-10
• 期刊: Proceedings of the 37th International Symposium on Automation and Robotics in Construction (ISARC)
• 作者: Xuchu Xu;Ruoyu Wang;Qiming Cao;Chen Feng

Learning Distilled Collaboration Graph for Multi-Agent Perception

• 发表时间: 2021-11
• 期刊: ArXiv
• 作者: Yiming Li;Shunli Ren;Pengxiang Wu;Siheng Chen;Chen Feng;Wenjun Zhang

Learning Simultaneous Navigation and Construction in Grid Worlds

• 发表时间: 2023
• 期刊: ArXiv
• 作者: Wenyu Han;Haoran Wu;Eisuke Hirota;Alexander Gao;Lerrel Pinto;L. Righetti;Chen Feng