Object recognition in bin picking

垃圾箱拣选中的物体识别

• 批准号: 532448-2018
• 负责人: Greenspan, Michael
• 金额: $ 8.72万
• 依托单位: Queen's University
• 依托单位国家: 加拿大
• 项目类别: Collaborative Research and Development Grants
• 财政年份: 2019
• 资助国家: 加拿大
• 起止时间: 2019-01-01 至 2020-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=693050
• 关键词: Object; recognition; bin; picking

The goal of this project is to develop a method to identify appropriate Object Recognition solutions to support specific bin picking tasks. At the conclusion of the project, the research team will have explored and developed various methods to Object Recognition for specified bin picking tasks. They will also have developed a methodology, and a suite of software tools, to evaluate these methods for future specified tasks. Upon project completion, the developed system will be the core enabling technology that will lead to a new disruptive functionality that will alter the way that bin picking tasks are automated, both increasing efficiency of the automation process, as well as increasing the range of tasks that can be accomplished.The applicant, Prof. Michael Greenspan, has a recognized research expertise in 3D Computer Vision. The primary beneficiary of this work will be Canadian company Bluewrist Inc., who will benefit directly from ownership and commercialization of the developed technology. This project will increase Bluewrist's profitability and allow them to hire more personnel to deliver, support and further develop the products. Those companies in Canada and elsewhere that make use of the automated bin picking systems that derive from this project will also benefit from the improvement in the efficiencies of their processes. This will help Canada with increased employment in high value technology development. In addition to the direct economic benefits, there will also be a larger reputational benefit to Canada, in both academic and industrial circles, as Canada will be known to be the intellectual genesis of the fundamental enabling techniques that facilitate the revolutionary transformation of this technology.

这个项目的目标是开发一种方法来确定适当的对象识别解决方案，以支持特定的垃圾箱拣选任务。在项目结束时，研究团队将探索和开发各种方法来识别指定的垃圾箱拾取任务。他们还将开发一种方法和一套软件工具，以评估这些方法用于未来的特定任务。项目完成后，开发的系统将成为核心技术，将带来新的颠覆性功能，改变垃圾箱拣选任务的自动化方式，提高自动化过程的效率，并增加可以完成的任务范围。申请人Michael Greenspan教授在3D计算机视觉方面拥有公认的研究专长。这项工作的主要受益者将是加拿大公司蓝腕公司，他们将直接受益于所开发技术的所有权和商业化。该项目将增加Bluewrist的盈利能力，并允许他们雇用更多的人员来交付，支持和进一步开发产品。加拿大和其他地方的公司使用该项目产生的自动分拣系统也将受益于其流程效率的提高。这将有助于加拿大在高价值技术开发方面增加就业。除了直接的经济利益外，加拿大在学术界和工业界也将获得更大的声誉利益，因为加拿大将被称为促进这项技术革命性转变的基本使能技术的智力起源。