Listen to this article

The Advanced Robotics for Manufacturing (ARM) Institute has announced eight new short-cycle technology projects it will be funding. The Institute plans to award nearly $1.56 million in project funding from various sectors, for a total contribution of $3.26 million across these eight projects. 

ARM Institute projects are selected from its Project Calls, which are made in collaboration with the ARM Institute’s internal team of experts, ARM Members, and its Department of Defense collaborators. This most recent project call specifically called for proposals in these areas:

• Automated robotic task planning
• Multi-robot, multi-human collaboration, task sharing & task allocation
• Safe and Scalable manufacturing of energetics
• 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,” Dr. Chuck Brandt, ARM Institute Chief Technology Officer, said. “These projects epitomize the strength of ARM Institute members and the impact of collaboration between different stakeholders in manufacturing.”

The ARM Insitute’s latest projects are detailed below. 

Technology Assessment of Virtual Commissioning for Day One Manufacturing Readiness

This project is a collaboration between Wichita State University’s National Institute for Aviation Research, Siemens Corporation, and Spirit AeroSystems. It will create a report detailing the framework, and all the steps involved in development, for the creation of a virtual twin for commissioning.

The resulting framework package will contain all the data and considerations necessary to develop a full digital twin, which allows users to perform system testing in a digital environment prior to installation. This enables more successful and faster installs. 

Autonomous Robotic Iterative Forging Phase 2

Building on the results of a previous ARM Institute project, this collaboration between Ohio State University, CapSen Robotics, Yaskawa, and Warner Robbins Air Force Base aims to address the growing need for small-volume, high-mix manufacturing. This kind of manufacturing requires one-off components that can be complex and require expensive machining and tooling. 

This project is building on its first phase by seeking to drastically increase the productivity of the robotic system created in the Autonomous Robotic Metal Forming phase.

Robotic Manipulation of Granular and Paste-like Materials

This collaboration between Siemens and the University of Southern California seeks to automate the manipulation of granular and paste-like materials with robotics. These robots would augment human operators in common handling tasks, like safely scooping and pouring precise amounts of materials without spillage, including those used in the manufacturing of energetic materials. 

The team’s plan is to develop a robotic skill based on AI imitation and reinforcement learning to more safely scoop precise amounts of granular and paste-like materials, enabling robots to operate in a flexible way in a broad class of applications. 

The Path to Adopt Multi-Modal AI and Rapid Re-tasking & Robot Agility Project

This project will build Market Studies and complete Discovery Workshops to propose the technology roadmaps for two topics. The first is multi-model inputs for AI, which will look at the potential for large language models, like Chat GPT, in manufacturing. 

The second is rapid re-tasking and robot agility. The project aims to re-think the way we typically deploy robots, which typically can perform one task very well but are inflexible when it comes to other tasks. This project is a collaboration between Siemens and the University of Southern California. 

Discovery Workshops/Market Analysis for Space and Hypersonics

This project, led by ASTM International, will complete Discovery Workshops and Market studies centered on two topics. The first is terrestrial manufacturing for space, and the second is the manufacturing of hypersonic components and structures. 

The ASTM team plans to conduct a literature review followed by an in-person workshop. After the workshop, they will do follow-up surveys to develop these two reports. 

Time-Optimal Motional Planning using Convex Sets

This project is led by Dexai Robotics and the Massachusetts Institute of Technology and will focus on automated robotic task planning. It will build on Dexai Robotics’ existing product by doubling the ingredient pick-up robot moving time, improving the planning time for utensil pickup, and improving on meal throughput. These changes can help alleviate labor struggles in the restaurant industry. 

While this use case is focused on the food industry, its results could make an impact on to broader robotics community by increasing speed and accuracy for a variety of robotic manufacturing applications. 

Manipulating Fabric with Robots for Pick-and-Place Operations

This project is a collaboration between the Apparel Robotics Corporation and MassRobotics and its goal is to boost robotic capabilities when it comes to handling fabric. It seeks to 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. 

Outside of garment manufacturing, this project will bolster automation capabilities in aerospace and other industries working with flexible, fabric-like materials.

Collaborative Framework for Robotics Training

This Aris Technology project aims to address the limits in robotic adoption that come from the lack of flexible robotic systems and difficulty in upskilling a large industrial workforce. 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. The framework will be designed for both human-robot and robot-machine collaboration.