In the post-pandemic era, organizations grapple with a dynamic workforce, making knowledge transfer a significant challenge. This fluidity necessitates that knowledge is not only stored effectively but also promptly retrievable when required, given the constant influx and outflow of personnel. Autodesk Forma, with its unlimited storage capability, is aptly serving as a robust knowledge vault for Sunway, enabling the firm to overcome this hurdle. The Autodesk Forma Files feature allows us to search keywords within contents, a strength we've capitalized on to maximize its utility. Today, we're pushing boundaries further by integrating Autodesk Forma with ChatGPT via OpenAI API. This integration embeds our files into vectors, forming the foundation for a Q&A system. This groundbreaking approach signifies a knowledge revolution, ensuring seamless knowledge transfer and accessibility, regardless of workforce dynamics.

Integrating building performance analysis results in the early stage of conceptual design supports effective design exploration and decision making. Such integration requires domain expertise and can be technically challenging, time consuming, and computationally expensive. Machine learning demonstrates great potential for building seamless workflows that provide faster analysis feedback. However, one of the challenges in the architecture domain is the lack of diverse data sets to train effective prediction models. This talk will provide a brief overview of the potential of machine learning in building analysis-prediction models and demonstrate how we can capitalize on generative design to compensate for the lack of data. We will present a workflow where generative design features for Revit software, Dynamo software, and Insight software are used to generate a synthetic data set for training a machine-learning model for energy-analysis prediction.

Sewer pipelines are buried and out of sight. They are underinvested in and rapidly deteriorating. There are millions of miles of sewer pipelines that require monitoring to determine the condition and performance of this critical infrastructure. The principal method that utilities use involves closed-circuit television (CCTV) mounted video cameras on crawler units. Video and photographs of the insides of pipes are interpreted by engineers trained in the art of sewer pipeline defect recognition. This time-consuming and expensive process usually carried out in the field is increasingly being challenged by the use of AI and machine learning (ML) image detection and recognition techniques. See how the integration of Autodesk's Info360 Asset SaaS asset management product and VAPAR AI/ML tools will transform the assessment of sewer pipeline conditions, leading to huge cost and efficiency savings and productivity gains. Learn how these inspections are used to identify failure modes and determine the likelihood of failure and remaining life of assets.

In today's rapidly evolving technological landscape, digital twins are revolutionizing traditional business models in the architecture, engineering, construction, and operations (AECO) industry. The technology is not only transforming the way businesses operate, but it's also paving the way for innovative business models, enabling organizations to gain a competitive edge in the global market. A digital twin is a physical object's virtual replica that connects static, spatial, and real-time data from the real-world counterpart to provide valuable insights for the user. It integrates with additional tools that may use machine learning and AI to provide additional value in asset operations and management. This panel will explore how companies are using digital twins to build innovative business models. The panelists will discuss how they are augmenting existing deliverables, creating business opportunities, and diversifying short- and long-term revenue streams while building whole-lifecycle relationships with their clients.

Curious about the road ahead for AutoCAD software? Join Autodesk product managers and leaders for AutoCAD to learn about new features and functionality supporting the capabilities and workflows you need to drive more-efficient and more-collaborative projects. Discover how Autodesk is incorporating Autodesk AI into AutoCAD to elevate your design and drafting capabilities. Learn about the strategic insights and decisions driving development directions. Peer into the future of the product you use every day, and engage with Autodesk to help shape that product to better meet your needs and the needs of your company, project teams, and clients.

In partnership with Esri and Nearmap, Kimley-Horn is using high-resolution aerial imagery and deep-learning tools to transform workflows, gain unprecedented location insights, and make project delivery easier, faster, and more efficient. Attendees will learn how to address common firm challenges, improve design accuracy, and reduce rework using pretrained machine-learning models and up-to-date site intelligence. We'll discuss a wide variety of workflows and use cases, including how to automate image feature identification and extraction and seamlessly integrate those features into project drawings using the Autodesk Connector/ArcGIS for AutoCAD plug-ins.

The water industry is undergoing a state of rapid change as it faces a $1 trillion global risk of damaging flooding and water shortages that could impact 5 billion people by 2050. It's estimated that 60% of global water utilities will be forced to undergo digital transformation of their infrastructure to adapt to growing risks and meet sustainability demands. Join the Autodesk water team as we explore how digital transformation is reshaping the way the world manages water and water infrastructure. Through the lens of Autodesk's desktop hydraulic modeling products—InfoWorks ICM, InfoDrainage, InfoWater Pro, and InfoWorks WS Pro—we'll explore practical examples of how rapidly advancing digital technology is helping transform the workflows of industry stakeholders, including utilities, consultants, engineers, water modelers, and others.

This session will delve deep into BIG's workflow with D5 Render, discovering how BIG harnesses this AI-powered tool to enhance architectural design processes. You will also gain exclusive insights into AI integration and visualization trends from Jens Majdal Kaarsholm, director of design technology at BIG. Come to learn firsthand how these advancements drive design progress, streamline workflows, and ignite fresh creative possibilities. Whether you're an experienced industry professional or an enthusiastic newcomer, this session promises to deliver invaluable insights into powerful architectural methodologies at the forefront of innovation.

In this session, we'll explore the intricacies of drainage design workflows for transportation projects, including rail, roads, and highways. Using Autodesk's InfoDrainage and Civil 3D software, we'll present a streamlined workflow that facilitates the interaction and data exchange between both software solutions, with a special emphasis on drainage for transportation-related projects. One of the key learnings will be spotlighting the data exchange and results migration capabilities between civil design software (Civil 3D) and drainage design software (InfoDrainage), without the interjection of spreadsheets. Additionally, we'll highlight InfoDrainage software's machine learning (ML) deluge feature, with emphasis on its potential to expedite the concept and early planning process by rapidly identifying ponding locations on a site. Testing data showed the ML deluge outperforming traditional deluge by identifying ponding on a site in four seconds compared to more than nine minutes.

Storytelling has been present within architecture as long as the domain itself has existed. Initially, it was done with hand representations of volumes and narratives told over the sheets of paper. As the technology progresses, new ways of telling stories emerge: Renderings became easier and cheaper, causing their function to evolve. Industry saw a shift from only using them for end results (artifacts) to real-time renderings focused on driving communication and decision making. Now, with the democratization of AI, we are facing new possibilities: Visualization for ideation, but also for even faster creation of realistic outputs. This opens the doors for more-effective, data-driven storytelling throughout the design stages. In this live demonstration of the Veras extension within Autodesk Forma and Revit software, we'll show you how to easily create stunning visualizations and convert them to create compelling, data-driven storyboards throughout design stages using Autodesk Forma.

Join this session to learn how a web-based configurator built with Autodesk Platform Services can help to improve sales. With an easy-to-use web tool, we'll see how nontechnical users can design interior floor plans and produce high-quality rendering. From enhancing traditional path-tracer renderings to offering new WebGL optioneering workflows, let's explore what new AI rendering techniques can do in a fraction of the required traditional time and cost.

This session will explore how you can integrate D5's AI-powered tools as a core component of your design workflow, essentially becoming the go-to companion alongside your modeling software. Through the introduction of D5 Lightmode (a DCC add-on that seamlessly takes your designs into AI for an effortless generation of refined architect-friendly reference images) alongside D5 Livesync (the live link plug-ins that synchronize changes with D5 in real time from modeling software like Revit and 3ds Max) and finally D5 Render (a real-time renderer with the best balance between efficiency and quality), you can take advantage of this AI-powered workflow to slash the grind in design, collaboration, and learning. We'll cover nifty tips and tricks to supercharge your workflow, helping you crank up the speed of delivery while focusing on what matters the most: innovating and refining your designs.

Discover the power of AI in design optimization with this innovative AU class. Learn how to use large language models (LLMs) and Autodesk Forma software, a custom extension, to efficiently compare and evaluate multiple design options for a specific site. Gain insights into how AI can analyze various design aspects—such as functionality, aesthetics, and environmental factors—to determine the most suitable option. Throughout the class, you'll explore real-world case studies demonstrating the effectiveness of using LLMs and Forma in design decision making. Acquire practical skills in using the Forma extension to streamline your design workflow and make data-driven decisions. By the end of this class, you'll have the knowledge and tools to harness the potential of AI in design comparison and optimization. Elevate your design process, save time, and create outstanding results that meet and exceed client expectations.

This case study will showcase Autodesk Forma software's new AI-based embodied carbon analysis, built in collaboration with EHDD, examining real-life use cases by Stantec practitioners to evaluate embodied carbon at the earliest stages of design. First, we'll expand on our AU 2023 product demo, exploring Stantec's partnership with Forma, and establishing the user needs and guiding principles that led us to the in-market embodied carbon analysis. Then, Jack Rusk, who leads the EHDD team behind the C.Scale engine that powers the analysis in Forma, will explain how these same user needs manifested in the computational back end, giving a look behind the curtain at the AI model. Finally, and most importantly, Stantec practitioners will show real projects where they've used the analysis to inform effective early-stage decisions. Specifically, these Forma users will demonstrate that democratized carbon solutions empower any designer to champion sustainable, outcome-based design from step one.

This session is a continuation of 2022's "Hard Questions Only" and 2023's "Harder Questions." With this expert panel representing technology leaders from across architecture, engineering, construction, and operations (AECO), once again we dive into the hard questions of digital transformation. It's easy to assume that everyone is "doing building information modeling (BIM)," but this panel wants to dig deeper and talk about the challenges that remain as our industry goes through a digital transformation. We'll go beyond the easy wins and discuss what BIM adoption really looks like and how hard it is to drive change. How is the escalation in tools changing our production process, and what does it mean for how we manage our projects and firms? What does the shift to data-driven work mean for an industry based around design studios and professionally licensed staff? Importantly, this panel will represent diverse views to understand how the responses and need for change vary across disciplines.

Artificial intelligence (AI) has the potential to significantly affect our industry. How can we use AI to improve our programming skills and make us more efficient? In this session, we'll go over the creation of a program using LISP to copy files from one location to another. Once created, we will use AI to convert a portion of that code into a visual basic script (VBS) so that the user can continue to work while files copy in the background.

For several years, KLH Engineers has led efforts to bridge the gap between AutoCAD and Revit software through machine learning, enhancing our deliverable by building intelligent models from CAD plans. Expanding on our foundational work from 2019, our tool now automatically generates Revit wall elements with precise thickness from AutoCAD drawings, eliminating the problem of thin wall creation and significantly saving time. In this session, we'll demonstrate how machine learning is integral to our process. We have incorporated advanced algorithms that accurately place door and window families within Revit models, using AutoCAD data to inform our workflow and put the "I" back in building information modeling (BIM). Join us to see these advancements in action and learn how they can enhance your design process, making it faster, smarter, and more precise.

Although the character-animation process has been largely digitized, the fundamental approach has remained relatively unchanged for more than a century. Animators create performances by creating key poses, which they then string together in a sequence to create motion. They continue to add and finesse these keyframes until they get a believable performance. In this presentation, we will demonstrate a new approach to character animation that uses AI to transform the way animators work. With neural motion controllers, we use machine learning to model how characters move and behave. An animator then only needs to specify high-level intent, like when and where they want the character to move, and the neural motion controller does the tedious work of producing natural, believable motion. We will also demonstrate that by connecting this new technique with core Autodesk capabilities, we can create a production-ready workflow where animators retain full artistic control over the final animation.

Teaching Tectonism to AI"" is an exploration that focusses on the convergence of AI and tectonism. Tectonism, as a leading subsidiary style of parametricism, poses a unique challenge for current text-to-image AI tools due to their limited comprehension of structural dependencies in architectural representations. The presentation will showcase the potential of merging structural topology generation tools with Generative Artificial Intelligence across various architectural typologies and how this is integrated into early stage ideations at Zaha Hadid Architects.

Bifrost is a powerful graphical programming environment for creating procedural visual effects simulations, geometry, rigging, and animation. In this session, we'll showcase new, modular, deep-learning workflows in Maya software using Bifrost. We will demonstrate how to use Bifrost for procedurally generating training data for AI systems, as well as how to deploy trained AI models in Bifrost using new Bifrost nodes designed for deep learning. The session will include practical examples of industry problems that are suited to a media and entertainment audience, such as using AI for complex rigging kinematic solvers.