SBIR Phase I: Scalable Computer Clusters Applied to Sensing and Control of Intelligent Manipulators for Agile Manufacturing

这个小企业创新研究（SBIR）第一阶段项目致力于设计和原型一个新的高性能，但低成本的集成机器人机械手，包括机械，电气和计算子系统的紧密集成。这项工作的一个重要部分是解决开发新一代智能机器人操作器所涉及的计算挑战。例如，使用传统的嵌入式处理器进行实时通用视觉处理和灵巧规划是不可行的。其结果是，只有在机器人手臂可以将计算成本高昂的过程外包给更强大的计算机的环境中，先进的机器人应用才是可能的。低功耗、高性能计算（HPC）集群将用于扩展目前自主和半自主机器人操作系统的可能性。因此，一个研究工作是开发一个可扩展的高层次的智能框架应用于机器人操作器，并实现强大的和实时的算法，利用高度并行计算环境。应用计算将在异构机器人和计算机系统的无线和有线网络之间无缝集成。该项目的目标是为研究和轻工业提供一个高性能、计算可扩展、低成本的智能机器人手臂平台，它可以很容易地适应各种复杂的应用。该项目更广泛的影响/商业潜力是填补市场利基之间的低端机器人机械手，几乎没有商业潜力，高端机器人手臂价格昂贵，安装和操作成本高。高性能计算与先进的机器人机械手系统集成适用于敏捷轻工业和非结构化环境中的其他桌面机械手应用。这将对商业机器人的未来产生巨大影响，并使小型制造企业能够负担得起有能力的机器人系统。高度并行的计算能力将大大增加机器人的应用范围和适用范围。例如，智能机器人操纵器可以用于农业应用或在高度非结构化的环境中自主护理植物。同样的机械手可以很容易地适应在课堂环境中使用;通过简单的脚本界面，学生可以实验先进的机器人控制，使他们能够专注于发现令人兴奋的新应用。这在学术和工业环境中创造了广阔的市场，无论是用于敏捷制造的高性能，低成本智能机器人机械手，还是一般应用于传感器网络集成解决方案的低功耗HPC集群。

This Small Business Innovation Research (SBIR) Phase I project addresses the effort to design andprototype a new high-performance but low-cost integrated robotic manipulator comprising of the tightintegration of mechanical, electrical, and computational subsystems. A significant part of the effort is toaddress the computational challenges involved in developing a new generation of intelligent roboticmanipulators. Real-time general vision processing and dexterous planning, for example, are notfeasible using conventional embedded processors. The consequence is that advanced roboticapplications are only possible in environments where the robotic arm can outsource computationallyexpensive processes to more powerful computers. Low-power, High-Performance Computing (HPC)clusters will be used to extend what is currently possible in autonomous and semi-autonomous roboticmanipulator systems. Therefore a research effort is to develop a scalable high-level intelligenceframework applied to robotic manipulators, and to implement robust and real-time algorithms that takeadvantage of highly parallel computing environments. Application computations will integrateseamlessly across wireless and wired networks of heterogeneous robotic and computer systems. Thegoal is a highly capable, computationally scalable, low-cost intelligent robotic arm platform forresearch and light industry, which can easily be adapted to a variety of complex applications.The broader impact/commercial potential of this project is to fill a market niche between the low-endrobotic manipulators that have little commercial potential and the high-end robotic arms that areexpensive and have high operating costs for setup and operation. High-performance computationintegrated with advanced robotic manipulator systems are applicable for agile light industry and otherdesktop manipulator applications in unstructured environments. This will have a tremendous impact onthe future of commercial robotics and make capable robotic systems affordable to small manufacturingbusinesses. Highly parallel computing power will greatly increase the range of applications andenvironments to which robots are suited. For example, an intelligent robotic manipulator can be used inagricultural applications or autonomously caring for plants in highly unstructured environments. Thesame manipulator could easily be adapted for use in a classroom setting; with a simple scriptinginterface students can experiment with advanced robotic control, allowing them to concentrate ondiscovering exciting new applications. This creates a broad market in academic and industrial settings,both for highly-capable, low-cost intelligent robotic manipulators for agile manufacturing and for lowpowerHPC clusters applied to sensor network integration solutions in general.