91����

ORNL researchers have developed a deep learning-based approach to rapidly perform high-quality reconstructions from sparse X-ray computed tomography measurements. 

In additive manufacturing, choice of process parameters for a given material and geometry can result in porosities in the build volume, which can result in scrap.

We have been working to adapt background oriented schlieren (BOS) imaging to directly visualize building leakage, which is fast and easy.

The lack of real-time insights into how materials evolve during laser powder bed fusion has limited the adoption by inhibiting part qualification.  The developed approach provides key data needed to fabricate born qualified parts.

We present the design, assembly and demonstration of functionality for a new custom integrated robotics-based automated soil sampling technology as part of a larger vision for future edge computing- and AI- enabled bioenergy field monitoring and management technologies called

Creating a framework (method) for bots (agents) to autonomously, in real time, dynamically divide and execute a complex manufacturing (or any suitable) task in a collaborative, parallel-sequential way without required human interaction.

Materials produced via additive manufacturing, or 3D printing, can experience significant residual stress, distortion and cracking, negatively impacting the manufacturing process.

In additive printing that utilizes multiple robotic agents to build, each agent, or “arm”, is currently limited to a prescribed path determined by the user.

This invention discusses the methodology to calibrating a multi-robot system with an arbitrary number of agents to obtain single coordinate frame with high accuracy.