The ARM (Advanced Robotics for Manufacturing) Institute has selected eight new short-cycle technology projects for funding from its 23-01 Technology Project Call released earlier this year. The ARM Institute plans to award nearly $1.56M in project funding from various sources, for a total contribution of approximately $3.26M across these eight projects. To date, the ARM Institute has funded and managed more than 150 robotics and AI technology and workforce development projects.
The ARM Institute is a Department of Defense Manufacturing Innovation Institute and a member of the Manufacturing USA© Network. The ARM Institute leverages its ecosystem of nearly 400 member organizations across industry, government, and academia to catalyze critically needed robotics and workforce innovations in manufacturing.
ARM Institute projects are selected from our Project Calls. These Project Calls are crafted in collaboration with the ARM Institute’s internal team of experts, ARM Members, and our Department of Defense collaborators. Our 23-01 Technology Project Call specifically called for proposals to address the following topic areas:
- Automated Robotic Task Planning
- Multi-Robot, Multi-Human Collaboration, Task Sharing & Task Allocation
- Safe and Scalable Manufacturing of Energetics
- Artificial Intelligence (AI) in Robotics for Manufacturing
- Discovery Workshops and Market Studies
“Our selections in this latest project call address diverse areas of need in manufacturing – from identifying and road-mapping needed robotics developments to directly creating solutions for the problems that manufacturers are facing today,” stated Dr. Chuck Brandt, ARM Institute Chief Technology Officer. “These projects epitomize the strength of ARM Institute members and the impact of collaboration between different stakeholders in manufacturing.”
Each project is briefly described below:
Technology Assessment of Virtual Commissioning for Day One Manufacturing Readiness
Project Team: Wichita State University’s National Institute for Aviation Research (Principal Investigator), Siemens Corporation, Spirit AeroSystems
Topic Areas Addressed: Discovery Workshops and Market Studies
Description: Complex manufacturing systems can have many costs, errors, and hazards that may not be apparent in the design phase alone. Simulating systems by using digital/virtual twins allows for system testing in a digital environment prior to installation, enabling more successful installs and better “day one” experiences. This project will create a report detailing the framework for the creation of a virtual twin for commissioning, and all the steps involved in its development. The framework package will contain the data and considerations needed to develop a full digital twin.
Autonomous Robotic Iterative Forging Phase 2
Project Team: Ohio State University (Principal Investigator), CapSen Robotics, Yaskawa, and Warner Robbins Air Force Base
Topic Areas Addressed: Artificial Intelligence (AI) in Robotics for Manufacturing
Description: This project builds on the outputs from the previously funded ARM Institute Autonomous Robotic Metal Forming project. There is a growing need for small volume, high mix manufacturing, such as in cases of manufacturing replacement components for aging systems or personalized medical implants. However, there is a limited supply chain for one-off components, and complex components require expensive machining and/or tooling and dies. This project seeks to drastically accelerate the productivity of the robotic system created in phase one of this project by:
- reducing the time required to position the component on the lower die
- removing the need for pauses during pressing to relieve forces and torques
- allowing for larger amounts of deformation to be taken on each iteration
- reducing the number of images needed for component geometry reconstruction
- reducing the time to heat material to forging temperatures
- reducing the amount of deformation needed to transform the initial geometry to the final geometry
- reducing the frequency of component imaging.
Robotic Manipulation of Granular and Paste-like Materials
Project Team: Siemens (Principal Investigator), University of Southern California
Topic Areas Addressed: Safe and Scalable Manufacturing of Energetics
Description: This project seeks to automate the manipulation of granular and paste-like materials with robotics to augment human operators for common handling tasks such as scooping and pouring precise amounts without spillage, including those used in the manufacturing of energetic materials. The outputs of this project can also be applied for use in the pharmaceutical and chemical industries. The team will develop a robotic skill based on AI imitation and reinforcement learning to more safely scoop precise amounts of granular and paste-like materials. This will lead to greater versatility by enabling robots to operate in a flexible way in a broad class of manipulation applications, making them easily reconfigurable to adapt to a different process at lab scale and in production. The project will also require little time to deploy and re-purpose by reducing programming, training and calibration efforts through machine learning and AI.
The Path to Adopt Multi-Modal AI and Rapid Re-tasking & Robot Agility Project
Team: Siemens (Principal Investigator), University of Southern California
Topic Areas Addressed: Discovery Workshops and Market Studies
Description: This project will build Market Studies and complete Discovery Workshops to assess the state of the art and propose technology roadmaps for the following topics:
- Multi-Modal Inputs for AI: Recent advancements of foundation model developed at a surprisingly rapid pace (e.g. ChatGPT). These models are designed for multi-modal inputs and will dominate the AI landscape over the next years. This report will analyze their potential in manufacturing.
- Rapid Re-tasking & Robot Agility: The need for lot-size-one production and flexible manufacturing requires rethinking the current deployment approach to robotics, where robots are often deployed for one specific purpose.
Discovery Workshops/Market Analysis for Space and Hypersonics
Project Team: ASTM International (Principal Investigator)
Topic Areas Addressed: Discovery Workshops and Market Studies
Description: This project will complete Discovery Workshops and Market Studies centered on two topics: (1) Terrestrial Manufacturing for Space and (2) Manufacturing of Hypersonic Components & Structures. The ASTM Team will conduct a literature review, followed by an in-person workshop, and then follow up surveys to develop these two reports. The team will also leverage ASTM’s network of nearly 30,000 subject matter experts.
Time-Optimal Motion Planning using Convex Sets
Project Team: Dexai Robotics (Principal Investigator), Massachusetts Institute of Technology (MIT)
Topic Areas Addressed: Automated Robotic Task Planning
Description: Fixed manipulators perform tasks that require speed and correctness. As the restaurant industry struggles to return to pre-pandemic levels and continues to navigate workforce shortages, robotics can help to fill the gap. This project will build upon Dexai Robotics’ existing product by doubling improvement on ingredient pick up robot moving time, improving the planning time for utensil pick up, and improving on meal throughput. While the use case is focused on the food industry, the deliverables from this project will impact the broader robotics community by increasing speed and accuracy for almost any robotic manufacturing application.
Manipulating Fabric with Robots for Pick-and-Place Operations
Project Team: Apparel Robotics Corporation (Principal Investigator), MassRobotics
Topic Areas Addressed: Automated Robotic Task Planning and Artificial Intelligence (AI) in Robotics for Manufacturing
Description: Clothing manufacturing is a very labor-intensive process with 80% of the total labor cost attributed to material handling, and most labor manufacturing is completed offshore. For the garment manufacturing industry to progress meaningfully towards automation, several effective fabric handling technologies must arise. This project will develop new flexible robotic material handling capabilities required to unload a cutting table or a conveyor that has a number of cut nested fabric pieces of varying sizes and geometries on it. The project will: 1) use a vision system to identify the cut fabric piece based on the shape and other features 2) develop an adaptable end-of-arm-tooling (EOAT) to adjust to the geometry of the fabric piece to be picked up, and 3) leverage the fabric gripper technology developed by Apparel Robotics Corp. Beyond garment manufacturing, the proposed system will bolster automation capabilities in aerospace and other industries working with flexible, fabric-like materials.
Collaborative Framework for Robotics Training
Project Team: Aris Technology (Principal Investigator)
Topic Areas Addressed: Multi-Robot, Multi-Human Collaboration, Task Sharing & Task Allocation
Description: Robotic adoption has been limited by a lack of flexible robotic systems and difficulties in upskilling a large industrial workforce. Enabling shop floor operators with the tools to work with human-friendly robots will help to reduce this limitation. The project will develop a collaborative framework to assist various organizations with assigning robotic tasks based on an individual operator’s unique subject matter expertise. This framework will be designed for both human-robot and robot-machine collaboration to increase the adoptability of the robotic system with existing infrastructure.
Help Us Lead the Future of U.S. Manufacturing
ARM Institute funded projects are just one benefit of ARM Institute Membership. The ARM Institute catalyzes collaboration across our nearly 400 member organizations that span industry, government, and academia to lead the way to a future where people and robots work together to respond to our nation’s greatest challenges and to develop and produce the world’s most desired products.
Join soon to attend our members-only National Annual Member Meeting taking place Nov. 13-15 in Pittsburgh, PA! The Annual Member Meeting brings our members together for three days of in-person collaboration, networking, and knowledge-sharing.