ArtsDesignEducation

CDFAM Computational Design Symposium

Duann Scott

Recordings of presentations from the CDFAM Computational Design Symposium held worldwide. Leading experts in computational design, AI and machine learning for industrial design, engineering and architecture from industry, academia and software development.

www.designforam.com

Play

Open in

39 episodes
Avg 20 min
English

Episodes 39

Newest Oldest Longest

All20 Unplayed20 In progress0 Played0

Counted on this page — what you have heard stays on this device, so it is not something the list can be paged by.

S8 · E9
Yesterday · 16 min
Toward Generative Engineering: Case Studies In Computational Creation Of New Design Concepts
CDFAM Computational Design Symposium — Tokyo 2026 Kotaro Tanimichi · Nature Architects Nature Architects Inc. develops a software platform that deeply integrates geometry processing, numerical analysis, and optimization, while also providing design solutions enabled by the platform through its Generative Engineering™ approach. Covering a wide range of manufacturing contexts, from mass production to advanced manufacturing methods, the company dramatically accelerates design exploration and creates new designs beyond existing design paradigms. This presentation will introduce case studies in which design concepts were generated under complex, large-scale physical phenomena and geometric constraints. Examples include the rapid exploration and creation of new design concepts for electric vehicle bodies, innovative garment design using origami-based techniques, and the design of highly efficient heat exchange structures enabled by additive manufacturing. The presentation　will also outline future directions for Generative Engineering™ Links Talk page with full transcript Watch the talk on YouTube Search this talk's transcript Cite this talk This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.designforam.com
- Transcript
S8 · E8
Yesterday · 12 min
Aeroforms: Modeling Olfactory Cartographies Of Japan - Harvard University
CDFAM Computational Design Symposium — Tokyo 2026 Zinab Eisa & Esha Morakhiya · Harvard University Aeroforms emerges from a shared curiosity of how the invisible sensory phenomena of scent can be modelled, mapped and ultimately understood as data, with a unique focus on scentscapes of Japan. Scent is one of the most powerful triggers of memory and belonging, yet it remains largely absent from environmental modeling and urban analytics. In 2001, Japan’s Ministry of Environment created “100 Scents of Japan”, a curated archive of culturally significant smellscapes tied to regional identity. The catalog revealed how smell functions as a vessel of ecological collective memory. Two decades later however, the physical landscapes that produced these scents have changed. Industrialization, land-use transformation, and air pollution have altered Japan’s atmospheric composition, and with it, its olfactory ecology. Aeroforms surfaces at the intersection of environmental science and design engineering to address this gap by asking: how can we computationally model scent at a national scale, and what happens when we compare modeled atmospheric composition to cultural memory? We developed a computational framework for olfactory modeling, a way to approximate the composition of scents across Japan using quantitative environmental data. Through this framework, we constructed a sensory digital twin of Japan’s olfactory environment, integrating agricultural and industrial datasets to estimate the relative presence of ten scent taxonomies across all prefectures. We derived emission factors from literature-based odor threshold values using inverse-potency summation, median log compression, and adaptive normalization. These were then multiplied by prefectural land area to estimate natural emissions, with industrial pollutant emissions incorporated as a parallel weighted contribution layer. The result is a combined, normalized composition vector per prefecture. By comparing these modeled scent compositions with the “100 Scents of Japan” catalog, we measure where cultural memory aligns with — and diverges from — ecological and industrial reality. This research therefore operates at the intersection of environmental data science, cultural geography, and sensory humanities, developing a reproducible model for environmental perception and introducing a methodology for quantifying perceptual-environmental divergence or, the measurable difference between how people remember environments and how those environments now exist materially. Links Talk page with full transcript Watch the talk on YouTube Search this talk's transcript Cite this talk This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.designforam.com
- Transcript
S8 · E7
Yesterday · 24 min
The Next Era Of Interaction Layers For Engineering - Generative Engineering
CDFAM Computational Design Symposium — Tokyo 2026 Laurence Cook + Beatrice Zanardi · Generative Engineering What could the next generation of engineering software feel like, and what becomes possible when the interface is no longer the constraint? The tools we use to create are changing. AI is making it possible to move beyond traditional software interfaces, but the opportunity isn’t simply to add AI to the interfaces we already have. It’s to rethink the interaction layer itself. Explore what happens when the interface becomes more fluid, more exploratory, and more directly connected to the human act of engineering Links Talk page with full transcript Watch the talk on YouTube Search this talk's transcript Cite this talk This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.designforam.com
- Transcript
S8 · E5
Friday · 22 min
Engineering/Manufacturing Processes With Implicit Modeling
CDFAM Computational Design Symposium — Tokyo 2026 George Allen · nTop By now, implicit modeling technology and its benefits are well understood. In situations where a part is highly complex or its design process is highly iterative, implicit modeling using signed distance fields is uniquely able to deliver the reliability, performance, and scalability that are required for success. However, the novelty of implicit modeling is also a source of problems. Current engineering/manufacturing processes are often heavily dependent on legacy software tools that cannot consume implicit models — they require meshes or boundary representations, instead. So how do we address this problem? There are a few options — we can either convert implicit models to the forms needed by legacy tools, replace the legacy tools with new ones that consume implicit models directly, or change the data flow in the overall process. The talk examines these issues, reports progress and the current status, and suggests some ways forward. Links Talk page with full transcript Watch the talk on YouTube Search this talk's transcript Cite this talk This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.designforam.com
- Transcript
S8 · E6
November 4 · 22 min
Teaching AI Engineering not Geometry: Why Text-To-Code-To-CAD, The Next Step In Computational Design
CDFAM Computational Design Symposium — Tokyo 2026 Darren Henry · PTC The race toward AI-generated CAD has largely focused on teaching models to produce geometry directly—from B-reps and meshes to feature histories and sketches. But what if we’re teaching AI the wrong language? This presentation explores an alternative paradigm: Text-to-Code-to-CAD, where large language models generate engineering logic rather than geometry itself. Instead of predicting low-level geometric entities, AI writes executable CAD code that captures design intent, constraints, parameters, and engineering relationships. The result is not merely a finished model, but a native, editable, and reusable engineering feature that integrates naturally into the design workflow. Using real-world examples, including AI-generated CAD features built through FeatureScript, this session demonstrates how modern language models can write, test, debug, and refine engineering code to create complex parametric designs while preserving the transparency and editability required for professional engineering. The discussion contrasts this approach with direct geometry generation and examines why engineering intent—not geometry—may be the more scalable representation for AI-assisted design. Attendees will leave with a new perspective on computational design: the future may not be AI replacing CAD, but AI leveraging programming languages purpose-built for engineering to accelerate design while keeping engineers firmly in control. Links Talk page with full transcript Watch the talk on YouTube Search this talk's transcript Cite this talk This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.designforam.com
- Transcript
S8 · E4
November 4 · 27 min
Mesh-Free Simulation for AI Agents
CDFAM Computational Design Symposium — Tokyo 2026 Matt Sederberg; Dr. Michael Scott · Coreform Matt Sederberg and Dr. Michael Scott of Coreform present isogeometric analysis (IGA) as a route to simulating directly on CAD geometry, and outline a mathematical framework for running multi-agent LLM workflows in high-assurance engineering domains. Sederberg covers the background of IGA, introduced by Tom Hughes and now the subject of more than 7,000 research papers, and its recent integration into Abaqus through a partnership with Dassault Systèmes. In one example, a brake caliper that took 20 hours to defeature and hex mesh, with critical fillets removed, was ready to solve in under a minute with full CAD geometry intact. With no meshing step, an agent can change the design, rerun the analysis and read the results without a human repairing the mesh in between. Scott then previews Coreform AI, built on four concepts: IGA as a robust physics solver for agent-driven workflows A data weave, an algebraic relational representation that lets agents query all simulation pipeline data at roughly constant token cost, regardless of data size Support for smaller, controllable and air-gapped models, demonstrated with Claude Haiku reaching the same result as larger models Agent coordination posed as an energy minimization problem using game theory, with market mechanisms that penalize agents for false completion claims He also describes formally verifying the underlying software in Lean, with more than 6,000 theorems backing returned results. Links Talk page with full transcript Watch the talk on YouTube Search this talk's transcript Cite this talk This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.designforam.com
- Transcript
S8 · E3
October 18 · 18 min
Form Follows Force: Data-Responsive Stochastic Algorithms For Additive Footwear
CDFAM Computational Design Symposium — Tokyo 2026 David Burpee · MorphXgen Many Additive footwear platforms promise a level of customization beyond traditional footwear manufacturing processes, but how custom is it really? This presentation will explore a variety of strategies for the integration of various custom data into bespoke additive-ready algorithms in footwear design. The ability to create force-responsive structures through various types of micro lattice to tune flexibility, gradient behavior, anisotropy all within the confines of additive manufacturability parameters. Approaches include multi-agent algorithms with intelligent emergent behavior, simulation-driven anisotropic stochastic lattice structures, and body-responsive data mapping for truly one-of-one additive footwear creations. Links Talk page with full transcript Watch the talk on YouTube Search this talk's transcript Cite this talk This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.designforam.com
- Transcript
S8 · E2
October 16 · 22 min
Sub-Optimal: Designer-Built Tools for Additive Manufacturing
CDFAM Computational Design Symposium — Tokyo 2026 Sarat Babu · SARAT Computational design approaches to optimization are often constrained by the tools available and the established methods for generating optimal forms. With AI coding tools, the barrier for designers to develop their own software and pipelines has dropped considerably. Sub-Optimal reframes optimization around two priorities: preserving the original designer’s macro intent, and using geometry to address the anisotropic surface roughness of additive manufacturing. The result is neither lattice application nor topology optimization, but a grown internal structure driven by simulation, surface texture and build orientation that remains largely invisible at the macro level. The talk covers the trust gap senior engineers face with optimized DfAM parts, the use of surface texture to mask layering defects and build orientation, and how the pipeline was built in six weeks for about $400 in AI tokens using open-source libraries including geometry3Sharp and OpenVDB, with 3MF as the output format. Links Talk page with full transcript Watch the talk on YouTube Search this talk's transcript Cite this talk This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.designforam.com
- Transcript
S8 · E1
October 15 · 23 min
Introducing AURA, A Reasoning Engine for Design Exploration and Synthesis by Braid
CDFAM Computational Design Symposium — Tokyo 2026 This episode is the opening keynote from CDFAM Tokyo 2026, presented by Guido Cossu and Ivo Timóteo of Braid. Braid was founded in Tokyo in 2020 by a team drawn from physics, applied mathematics, computational geometry, large-scale simulation and machine learning. At the time, the prevailing view in AI held that scaling end-to-end learning on ever-larger datasets would solve most problems. Braid took a different position: engineering design, where physical accuracy, safety and manufacturability are non-negotiable, requires reasoning from the laws of physics and the constraints of manufacturing rather than pattern-matching from prior examples. Their system, AURA, combines learning with formal reasoning to move from engineering intent to manufacturable geometry, replacing the manual draw, simulate, review and redraw loop with structured exploration of alternatives that the engineer evaluates and selects from. In this talk, Cossu and Timóteo explain the semantic architecture behind that approach and show results from deployments in Japanese manufacturing, across several mass-production processes with little in common. The Best Design Is The Design You Can Make Guido Cossu; Ivo Timóteo · Braid Across computational design, the part that performs and the part that can be built are rarely the same part: optimization and generative methods meet the functional targets, and the work of making the result manufacturable happens afterward, by hand, often negating the performance that was gained. Braid closes that gap differently. Rather than optimizing a seed geometry or generating candidates from data, the system designs de novo — geometry reasoned directly from what an engineer specifies: function, physical conditions, the manufacturing process the part must suit, the cost it must meet. The mechanism is semantic reasoning rather than data-driven generation: a semantic architecture encodes physics, geometry, and manufacturing constraints with their relationships, and enforces constraint satisfaction by construction. Because the manufacturing process is reasoned from rather than filtered for, the geometry is manufacturable from the first output, not repaired into manufacturability afterward. Braid demonstrate this on real engineering components across several conventional mass-manufacturing processes, each with its own design constraints. The examples come from deployments in Japanese manufacturing industries where tolerances are tight and errors are costly. One system handling processes with so little in common is the crucial point: each result is reasoned from principle, not retrieved from examples of similar parts — which is, in the end, the difference between a design system you can trust on a novel part and one you can only trust on a familiar one. Links Talk page with full transcript Watch the talk on YouTube Interview with Braid Cite this talk This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.designforam.com
- Transcript
S7 · E24
October 5 · 20 min
The Era of Living Machines: How Biology Will Build the Next Generation of Building Materials
CDFAM Computational Design Symposium — DC 2026 Giorgia Cannici · Virginia Tech What if material fabrication could shift from assembly to growth—and be directed with precision through external fields? This work introduces magnetotropic plants: genetically engineered organisms in which gravity-sensing organelles (statoliths) are rendered magnetically responsive. By replacing gravitational cues with externally applied magnetic fields, plant growth direction can be actively controlled in real time. This enables programmable morphogenesis, where biological growth becomes a steerable process rather than a fixed outcome of genetics and environment. The presentation will outline the biological mechanism, the experimental framework, and the implications of this approach for material production. Magnetic fields act as an invisible, non-contact control layer, allowing spatial and temporal guidance of growth without mechanical intervention. Beyond applications in microgravity environments such as space, this work suggests a broader shift in how we produce materials—moving from extractive, energy-intensive processes toward growth-driven fabrication, where form emerges from the interaction between engineered biology and designed environmental conditions. Links Talk page with full transcript Watch the talk on YouTube Search this talk's transcript Cite this talk This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.designforam.com
- Transcript
S7 · E23
October 3 · 19 min
From Horns to Armor: Biomimicry, Computational Design, and the Future of Impact Protection
CDFAM Computational Design Symposium — DC 2026 Matthew Shomper · Not a Robot Engineering Nature has been solving the problem of impact protection for millennia, in order to arrive at solutions far more elegant than anything on the market today. The microstructure of a bighorn sheep’s horn is one of the most striking examples : a geometry that is brutally efficient at scattering and absorbing energy, such that the animal can sustain repeated high-speed collisions without lasting damage. The challenge has always been translating that geometry into something we can actually manufacture. Additive manufacturing allows us to build internal geometries that were previously impossible to fabricate : graded densities, interlocking fiber patterns, and layered structures that mirror what nature spent millions of years optimizing. By digitally modeling the ram’s horn at the microstructural level and translating those patterns directly into printable designs, we can produce armor components that outperform conventional materials in energy absorption while perfectly conforming to the body. This work represents a broader shift in protective equipment design: away from material selection alone, and toward architecture as the primary engineering tool. Links Talk page with full transcript Watch the talk on YouTube Search this talk's transcript Cite this talk This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.designforam.com
- Transcript
S7 · E22
October 1 · 23 min
Before the Model: Aurora as AI-Grounded Climate Intelligence for Early-Stage Design
CDFAM Computational Design Symposium — DC 2026 Damola Michael; Elliot Glassman · CannonDesign The environmental design conversation typically begins too late, after massing is committed and geometry is locked. Aurora repositions that conversation to day one, giving architects and engineers an immediate, evidence-based picture of any site before a design tool is opened. The platform synthesises EPW weather files, CMIP6 climate projections, ASHRAE design conditions, NOAA historical records for US sites, and seismic hazard data into a unified analysis environment, covering temperature and humidity distributions, wind roses, solar radiation by facade orientation, thermal comfort (UTCI, PET, SET), rainfall, carbon intensity, and future projections to 2050. Every analysis is immediately exportable as a formatted PDF or PowerPoint report, ready to present to a client or design team without additional preparation. Two integrated AI layers surface this data as design insight. A streaming conversational assistant powered by Google Gemini is grounded in the actual EPW and CMIP6 data for the active location. It explains what site climate means for design decisions, renders specific charts inside the conversation, and adjusts application settings through natural language. A second layer generates AI-written summary cards for ASHRAE design conditions and 2050 climate outlooks, automatically scoped to the site. Aurora does not generate or evaluate geometry. This is intentional: it is a pre-design climate intelligence layer, not a replacement for tools like Autodesk Forma. It provides the environmental literacy that should inform every decision made in those tools, a shared language between architect, engineer, and client before a single wall is drawn. Links Talk page with full transcript Watch the talk on YouTube Search this talk's transcript Cite this talk This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.designforam.com
- Transcript
S7 · E21
October 1 · 15 min
Bridging the CAD-to-Simulation Gap: Integrating Meshing-free Isogeometric Analysis into Industrial Workflows
CDFAM Computational Design Symposium — DC 2026 Matthew Sederberg · Coreform The traditional “design-to-analysis” loop is often bottlenecked by the laborious process of mesh generation, which can consume up to 80% of total simulation time. This presentation introduces Coreform IGA for Abaqus, a solution that brings CAD-exact isogeometric analysis (IGA) directly into the Abaqus ecosystem. By utilizing Coreform’s Isogeometric Analysis approach, users can perform high-fidelity simulations directly on CAD geometry, effectively bypassing the need for traditional finite element meshing. Links Talk page with full transcript Watch the talk on YouTube Search this talk's transcript Cite this talk This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.designforam.com
- Transcript
S7 · E20
October 1 · 16 min
AI-Native, Simulation-Driven Insight with End-to-End Traceability
CDFAM Computational Design Symposium — DC 2026 Mike Park · Flexcompute Computational design enables wider configuration exploration and reduces time to market, but turning innovation into validated, manufacturable designs is hampered by human-in-the-loop simulation. Manual geometry cleanup, meshing, and data management pace every workflow, while the feedback loops between simulation and the rest of the design organization stay broken by data silos. This talk presents an end-to-end, AI-native approach to closing those loops. GeometryAI applies a novel, topology-aware geometry representation that takes raw CAD to analysis-ready models automatically with mathematical guarantees that facilitate meshing and analysis. Physics-agnostic output feeds CFD, structural, and thermal tools with direct connections to surrogate training and inference. The GPU-native solver Flow360 delivers high-fidelity physics at speeds that tighten feedback loops. Thread ties it together with automatic data lineage, so every run is reproducible, every result is traceable, and institutional knowledge becomes the starting point rather than the bottleneck. Standard web interfaces and Python APIs enable humans and their agents equally. Real-world results are validated with industry-standard AIAA High-Lift Prediction Workshop submissions. Full-aircraft hover analysis is possible in hours. We show how geometry-aware automation, GPU-native simulation, and complete traceability make simulation-driven design genuinely agent-ready, at the scale and speed modern programs demand. Links Talk page with full transcript Watch the talk on YouTube Search this talk's transcript Cite this talk This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.designforam.com
- Transcript
S7 · E19
September 29 · 20 min
Optimal Lattice Selection for PCM Thermal Management
CDFAM Computational Design Symposium — DC 2026 Andreas Vlahinos · Advanced Engineering Solutions PCMs provide cooling without requiring an extra power source, unlike fans or active liquid cooling systems. They absorb peak energy loads during operation and release that heat when the ambient temperature drops, acting as a buffer against rapid temperature changes. This allows for more compact thermal management systems. Because most PCMs have inherently low thermal conductivity, they often fail to absorb or release heat quickly enough for high-demand applications. Designers can significantly improve the thermal performance of Phase Change Materials (PCM) by embedding lattice structures. Embedding a highly conductive lattice, such as aluminum or copper, forms a “thermal skeleton” that functions as a heat highway, dissipating heat more quickly and evenly through the PCM. Adding a 3D-printed metal lattice can increase the effective thermal conductivity of a PCM system by an order of magnitude compared to pure PCM. The internal structure provides a continuous path for heat conduction, which can double the melting speed. Beyond thermal benefits, the lattice provides mechanical support to the PCM, preventing leakage and helping it maintain its shape during the liquid phase. Simulating PCMs’ thermal behavior is difficult due to the highly nonlinear nature of latent heat release, the shifting phase-change boundaries, and the significant differences in physical properties between the solid and liquid states. This presentation demonstrates simulation techniques and showcases the process of optimal lattice selection. Links Talk page with full transcript Watch the talk on YouTube Search this talk's transcript Cite this talk This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.designforam.com
- Transcript
S7 · E18
September 29 · 15 min
Git for Hardware: Version Control as the Foundation for Agile Systems Engineering
CDFAM Computational Design Symposium — DC 2026 Steve Massey · SysGit Software development was transformed when version control became infrastructure rather than afterthought. Hardware engineering has not had an equivalent transition. Requirements live in documents. System models are stored in vendor-locked platforms. Design reviews happen in meetings rather than pull requests. The result is programs that cannot iterate at the speed the environment demands. SysGit applies the tools and workflows that scaled software development — branching, merging, diffing, CI/CD pipelines — directly to systems engineering artifacts, built on SysMLv2 and backed by existing Git infrastructure. Requirements, system models, and verification activities are captured in a single machine-readable format, traceable across the full program lifecycle and accessible to every stakeholder from specialist engineers to contracting officers. This presentation covers the technical architecture behind that approach, the role of agentic AI in automating requirements generation and model validation, and what continuous acquisition looks like when the digital thread is built on open standards rather than walled gardens. Links Watch the talk on YouTube Search this talk's transcript Cite this talk This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.designforam.com
- Transcript
S7 · E17
September 25 · 21 min
Artificial Intuition: Building an AI Mind for Electromagnetic Design and Engineering
CDFAM Computational Design Symposium — Washington DC 2026 Michael Frei · ARENA Physica Most advances in computational design focus on mechanical structure — domains we can visualize and have evolved an intuition for. But as modern hardware becomes increasingly software defined, the unseen and unintuitive world of electromagnetism is taking center stage. Conventional solvers can simulate fields, yet they cannot imagine new ones. Over the past year, our team has been building toward that capability. At CDFAM NYC and Barcelona, we shared early results from Atlas — an AI that learns electromagnetic behavior inductively from test data rather than deductively from first principles, enabling verification, optimization, and design postulation in domains where classical simulation reaches its limits. This talk shares our vision for the future of AI-driven electromagnetic design. Links Talk page with full transcript Watch the talk on YouTube Cite this talk Search the full text of every recorded CDFAM presentation This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.designforam.com
- Transcript
S7 · E16
September 25 · 20 min
AI-Enabled Assembly Configuration Spaces: Encoding Mechanical Intuition at the Design-Manufacturing Interface
CDFAM Computational Design Symposium — Washington DC 2026 Sai Nelaturi · C-Infinity The gap between digital design and physical assembly is not primarily a geometry problem. It is a reasoning problem. Engineering teams spend thousands of hours communicating assembly intent through manual CAD workflows, managing configuration complexity across product variants, and catching fitment and feasibility issues that could have been identified before any metal was cut. The cost is measured in weeks of engineering time per product release cycle. Links Talk page with full transcript Watch the talk on YouTube Cite this talk Search the full text of every recorded CDFAM presentation This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.designforam.com
- Transcript
S7 · E15
September 24 · 20 min
Physics AI as a Strategic Advantage: How Physics-based AI Models Are Reshaping U.S. Defense Engineering
CDFAM Computational Design Symposium — Washington DC 2026 Juan Alonso · Luminary The next decade of great-power competition will be won or lost in the engineering loop. Adversaries have increased the speed of iteration in hypersonics, undersea platforms, and autonomous aircraft and the U.S. defense industrial base cannot keep up by relying on traditional engineering workflows. Closing that gap requires a step-change in how programs are developed with AI-accelerated engineering. Links Talk page with full transcript Watch the talk on YouTube Cite this talk Search the full text of every recorded CDFAM presentation Join leading experts in computational design at all scales for two days of knowledge sharing and networking at CDFAM in Tokyo, October 8-9, 2026 This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.designforam.com
- Transcript
S7 · E11
September 23 · 11 min
From Text to Robotic Assembly: 3D Generative AI and Discrete Robotic Assembly for Making Physical Objects
CDFAM Computational Design Symposium — Washington DC 2026 Alexander Htet Kyaw · MIT Recent advances in 3D generative AI make it possible to create object geometries directly from natural language, but turning these digital forms into functional physical objects remains a major challenge. Most generated 3D models are meshes that do not contain the component level, structural, material, and assembly information required for robotic fabrication. This presentation introduces a research pipeline that combines 3D generative AI, vision language models, and robotic assembly to transform text prompts into multicomponent physical objects. Rather than only asking what an object should look like, the system reasons about how it should be physically composed, including where stronger, lighter, stiffer, or more flexible components are needed. The work points toward a future in which AI driven design systems can generate not only visual form, but also buildable, reusable, and materially informed assemblies for real world fabrication. Links Talk page with full transcript Watch the talk on YouTube Cite this talk Search this talk's transcript This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.designforam.com
- Transcript

Showing 1–20 of 39 episodes