Next Generation of Engineering Design Tools: Generative, User-friendly, and AI-powered

  • Funded by Swiss National Science Foundation (SNSF)
  • Total publications:5 publications

Grant number: 233062

Grant search

Key facts

  • Disease

    N/A

  • Start & end year

    2025
    2026
  • Known Financial Commitments (USD)

    $147,212.26
  • Funder

    Swiss National Science Foundation (SNSF)
  • Principal Investigator

    Biedermann Manuel
  • Research Location

    Switzerland
  • Lead Research Institution

    Companies/ Private Industry - FP
  • Research Priority Alignment

    N/A
  • Research Category

    N/A

  • Research Subcategory

    N/A

  • Special Interest Tags

    N/A

  • Study Type

    N/A

  • Clinical Trial Details

    N/A

  • Broad Policy Alignment

    Pending

  • Age Group

    N/A

  • Vulnerable Population

    N/A

  • Occupations of Interest

    N/A

Abstract

This project aims to develop the next generation of computer-aided design (CAD) tools that are user-friendly, generative, and powered by artificial intelligence (AI). Despite decades of technological progress, CAD tools have remained largely unchanged: designing 3D geometries still requires users to manually create hundreds of design features, often leading to a time-consuming process that often takes several days to weeks. Such a manual design process demands highly skilled personnel, limits rapid product iterations, and slows time-to-market.The goal of this project is to develop the next generation of design tools for engineering. Just as chatGPT has transformed how people write text, the goal of these new design tools is to enable users to automatically generate the 3D design of physical products. The market potential is significant, with the CAD software market valued at USD 12 billion. The plan is to offer the generative design tools through a Software-as-a-Service model. The project aims to build a minimal viable product (MPV) by Q2/2026 and address first target markets such as fluid parts, tooling, connectors, and inductors.The project is led by Dr. Manuel Biedermann, who conducted extensive research at ETH Zurich in computational design and digital production. His research addressed the limitations of CAD tools and implemented novel generative design tools for a variety of engineering applications. He used a software-driven approach for CAD that offers significant advantages over state-of-the-art methods such as parametric modeling, topology optimization, and 3D deep learning. The resulting generative design workflows create optimized parts (>50% better performance), reduce manual design time by 90%, are applicable to a wide variety of products, create ready-to-produce 3D designs, and are accessible for non-expert designers using high-level inputs.The BRIDGE funding will allow to transform the research into a beta product of these generative design tools with a user-friendly interface and integrations for selected CAD systems. These design tools will integrate AI-powered functionalities to simplify and accelerate the creation of 3D geometries. The plan is to conduct 3-4 pilot projects with customers that have validated their interest with letters of intent. These pilot projects aim to build generative design workflows tailored for the specific applications of customers, implement and test the design tools, and build plugin integrations for CAD systems.The BRIDGE funding allows to bring these generative design tools to the market, drive innovation in engineering, foster the competitiveness of Swiss companies, and lay the foundation for an new and innovative deep-tech startup.

Publicationslinked via Europe PMC

Similar antigen cross-presentation capacity and phagocytic functions in all freshly isolated human lymphoid organ-resident dendritic cells.

Autonomous phagosomal degradation and antigen presentation in dendritic cells.

Presentation of phagocytosed antigens by MHC class I and II.

Cross-presentation by dendritic cells.

Sec22b regulates phagosomal maturation and antigen crosspresentation by dendritic cells.