Resource Library

Whitepapers —

The Task Coding Framework for Leveraging Large Language Models in Robotics

The Task Coding Framework takes advantage of the generative capabilities of LLMs to perform general reasoning to take high level policy goals, framed as prompts, and turn them into well defined coded tasks capable of being directly run on a robotic system. This presents an effective approach to make robotic systems less brittle, with more generalized domains of operations, while keeping their behavior predictable.

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

Creating Simulation-Ready Digital Twins

Modularity and reusability are key features driving digital twin simulation — so how do we create real interoperability that ensures a meaningful and long lasting digital twin infrastructure? Presented at I/ITSEC 2023, this paper, titled The Digital Twin Encapsulation Standard: An Open Standard Proposal for Simulation-Ready Digital Twins, presents a path forward that ensures full reusability of digital twins in any operational context, while avoiding the possibility of vendor lock-in.

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

Is Your Machine Learning Model Bingeing on Junk Data?

Training a model on poor quality data can cause it to pick up “bad habits” that don’t transfer well to real-world scenarios. So how do we quantify if our synthetic data is relevant and valuable?

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

Whitepapers —

Is Your Machine Learning Model Bingeing on Junk Data?:The Three I’s Framework for Realistic and Relevant Synthetic Data

The Task Coding Framework takes advantage of the generative capabilities of LLMs to perform general reasoning to take high level policy goals, framed as prompts, and turn them into well defined coded tasks capable of being directly run on a robotic system. This presents an effective approach to make robotic systems less brittle, with more generalized domains of operations, while keeping their behavior predictable.

Download PDF

Modularity and reusability are key features driving digital twin simulation — so how do we create real interoperability that ensures a meaningful and long lasting digital twin infrastructure? Presented at I/ITSEC 2023, this paper, titled The Digital Twin Encapsulation Standard: An Open Standard Proposal for Simulation-Ready Digital Twins, presents a path forward that ensures full reusability of digital twins in any operational context, while avoiding the possibility of vendor lock-in.

Download PDF

Training a model on poor quality data can cause it to pick up “bad habits” that don’t transfer well to real-world scenarios. So how do we quantify if our synthetic data is relevant and valuable?

Download PDF

Slides & Presentations —

Proposal for a Metaverse-friendly Digital Twin Encapsulation Standard (DTES)

As the possibility of broad Digital Twin adoption moves towards reality, the need for ensuring interoperability becomes increasingly evident. Presented at the 125th Member Meeting of the Open Geospatial Consortium, the Digital Twin Encapsulation Standard (DTES) emphasizes simplicity, flexibility, extensibility, and reusability.

Building City-Scale Simulation with Falcon and AWS SimSpace Weaver

At AWS re:Invent 2022, Duality Co-Founder and CPO, Mike Taylor demoed “Rush Hour Emergency and Response Simulation in Smart Cities”. This talk illustrates the scale and fidelity of simulation accomplished with the integration of Falcon, Duality’s Digital Twin simulator, and AWS’s fully managed compute service for large-scale spatial simulations, AWS SimSpace Weaver.

Immersive Visualization of Wildfire Indicators (Open Geospatial Consortium, Disaster Pilot 2023)

Providing the right people in the right place at the right time with the clues they need to take the right action: this is the only way to limit the impact of disasters. To help make this possible, DP23 focused on out-of-the-box indicator workflows that can be adapted to the situation at hand. Duality's team showscased Falcon's ability to accomplish a key goal of DP23: leverage visualization to promote a broader understanding of the wide range of geographic and temporal scales at which coordinated disaster resilience actions are required.

Explore the possibilities:

Whitepapers —

The Task Coding Framework for Leveraging Large Language Models in Robotics

Creating Simulation-Ready Digital Twins

Is Your Machine Learning Model Bingeing on Junk Data?

Whitepapers —

Is Your Machine Learning Model Bingeing on Junk Data?:The Three I’s Framework for Realistic and Relevant Synthetic Data

Slides & Presentations —

Proposal for a Metaverse-friendly Digital Twin Encapsulation Standard (DTES)

Building City-Scale Simulation with Falcon and AWS SimSpace Weaver

Immersive Visualization of Wildfire Indicators (Open Geospatial Consortium, Disaster Pilot 2023)

Industry Insights —

What is digital-twin technology?

Digital Twins: From One Twin To The Enterprise Metaverse

The Emergent Industrial Metaverse