Project
Performance-aided Design
One of the greatest challenges in product design is when products fail to perform in the real world as designed. Autodesk Research is addressing this by pioneering an innovative product design process that integrates sensor-collected product performance data into the design. This approach incorporates performance data into cloud-based digital twin workflows and automates the product design iteration process. It addresses the paradox of designing products for users without integrating users’ operational data. The focus is on incorporating sensor data into product design iterations, setting the stage for a performance-aided design approach.
A performance-aided design solution deeply integrates the lifecycle of design, make, and operate through a digital thread. This connection underlies all feedback and improvements of designs and processes, resulting in increasingly responsive, adaptive living products. The growing duality of digital and physical representations of these living products, powered by computation, sensing, and actuation, will ultimately blur the difference between them.
“No matter how ideally we design and simulate products, they often perform differently in the real world. By integrating sensor-collected performance data into the design process, we can close the gap between prediction and reality, ensuring products perform as expected.”
Ed Tlegenov
Senior Manager, Research Science
Associated Autodesk Researchers
Leonardo Rodriguez
Experience Designer
Michelle Quan
Associate Research & Design Engineer
Related Resources
2024
Kaizen Aerospace Collaboration Yields Modular Testbeds for Performance-Aided DesignLearn how Autodesk Research and Kaizen Aerospace are exploring…
2024
Predicting Assembly’s Structural Performance via System-level Validation TestingRead how Autodesk Research is exploring the relationship between the…
2024
Handcrafting Non-uniform Grid Refinement for Modern GPUsLearn about a new methodology that carefully orchestrates the parallel…
2024
XLB: A Differentiable Massively Parallel Lattice Boltzmann Library in PythonThis research introduces the XLB library, a scalable Python-based…
Get in touch
Something pique your interest? Get in touch if you’d like to learn more about Autodesk Research, our projects, people, and potential collaboration opportunities.
Load projects