AI & ML interests

Embodied AI, synthetic data, AI vision

Recent Activity

duality-robotics's activity

DualityAI-RebekahBogdanoff 
posted an update 7 days ago
view post
Post
2699
🤩 Ready to start creating synthetic data that bridges the Sim2Real gap and trains robust AI models?

🌟 Join Duality AI's free “Intro to Falcon” class this Thursday, March 20th.

Dive into the Digital Twin Simulation workflows—from setting up the simulation software, FalconEditor, to generating custom data. Get hands-on guidance, ask questions, and receive direct support to build a solid foundation for your simulations!

Sign up here:
https://forms.gle/xViMMSMsA5GP468J6

In the class, you will:

✔️Explore FalconCloud features like the digital twin library and cloud simulations
✔️Set up and navigate FalconEditor as a first-time user
✔️Configure FalconEditor for scenario and data creation
✔️Assemble a sim-ready scenario using Falcon library twins
✔️Generate multiple data types with Falcon’s virtual sensors

New: This class also covers the latest Falcon 5.1 features!

Interested in checking out FalconEditor? Start your FREE EDU tier account to access online resources and lessons designed to teach you FalconEditor:
https://falcon.duality.ai/auth/sign-up?utm_source=huggingface&utm_medium=social&utm_campaign=031825intro

Get access to comprehensive resources for digital twin simulation and synthetic data, access full-featured FalconEditor, and stay up-to-date on future webinars and training courses.
DualityAI-RebekahBogdanoff 
posted an update 10 days ago
view post
Post
2137
Think building custom digital twins for AI training is hard? Let us show you how to make it easy!

Next week, Duality AI is offering a free "Creating Your Own 4-Wheeled Vehicle Digital Twins for AI Training with Falcon Editor" live class.
Sign up here: https://forms.gle/2U5xugMjvSkZdeaR8

What we'll cover:
🚗 Import & Configure a rigged 4-wheeled vehicle and transform it into a controllable system twin using Blueprints.
🚗 Enable Dynamic Control by exposing Python variables for real-time adjustments.
🚗 Attach Sensors to capture valuable simulation data.
🚗 Assemble & Run a Simulation Scenario to generate training data for AI & robotics applications.

See how Falcon creates synthetic data for faster, easier, and more targeted AI training by creating a FREE account here: https://www.duality.ai/edu
  • 1 reply
·
DualityAI-RebekahBogdanoff 
posted an update 14 days ago
view post
Post
1514
🙋‍♀️ Happy Monday! Duality AI has released another dataset for pose estimation

duality-robotics/pose_estimation5.1

It's once again 100% ✨FREE✨
Access the full-size dataset by creating an EDU account here- https://falcon.duality.ai/secure/documentation/pose-colab?sidebarMode=learn
Or check it out in the linked HuggingFace dataset

Why train a model in pose estimation?
Many functions require pose estimation, such as...
🤖Defining the orientation of an object on a conveyer belt for pick and place operations with a robotic arm,
🤖 Replicating an object's pose for AR and VR application overlays,
🤖 Localizing and mapping an environment for path navigation,
🤖 ...and more!

What makes this dataset useful for training a model?

💠Duality AI's digital twins are not generated by AI, but are instead crafted by 3D artists. This allows the training from this data to transfer into real-world applicability. Read more about our techniques for bridging the Sim2Real gap here: https://www.duality.ai/blog/ml-synthetic-data-model
💠The simulation software, called FalconEditor, can easily create thousands of images with varying lighting, posing, occlusions, backgrounds, camera positions, and more using a versatile python API
💠FalconEditor is able to create 100% accurate labels at the SAME TIME as it creates the images. This makes collecting data for tasks such pose-estimation easier, faster, and more reliable.

Interested in a specific dataset? Let us know!
We're always looking for new ideas on what datasets to create next 👀
DualityAI-RebekahBogdanoff 
posted an update 17 days ago
view post
Post
2822
🚀 Duality is super excited to announce that our Kaggle competition is LIVE! Synthetic-to-Real Object Detection Challenge is LIVE! 🚦
Want to master AI training, learn industry-proven synthetic data workflows, and compete for public recognition and cash prizes?

👉 Join our Synthetic-to-Real Object Detection Challenge on Kaggle! https://www.kaggle.com/competitions/synthetic-2-real-object-detection-challenge/overview

Compete to build the top-performing model capable of detecting real-world objects—trained entirely on synthetic data. Master these industry-proven methods for faster, more targeted, and diverse dataset creation, and set yourself apart, unlocking today's most exciting AI opportunities.

Ready to test your skills?

🏆 The Challenge

Train an object detection model using synthetic images created with Falcon—Duality AI's cutting-edge digital twin simulation software—then evaluate your model on real-world imagery.

The Twist?
📈 Boost your model’s accuracy by creating and refining your own custom synthetic datasets using Falcon! Get access to the tools and double the data by following this link and creating a free account-
https://falcon.duality.ai/secure/documentation/ex-1-objdetection?sidebarMode=learn

Win Cash Prizes & Recognition
🔹 Earn cash and public shout-outs from the Duality AI accounts
Enhance Your Portfolio
🔹 Demonstrate your real-world AI and ML expertise in object detection to prospective employers and collaborators.
Expand Your Network
🔹 Engage, compete, and collaborate with fellow ML engineers, researchers, and students.

🚀 Put your skills to the test and join our Kaggle competition today: https://www.kaggle.com/competitions/synthetic-2-real-object-detection-challenge/overview
DualityAI-RebekahBogdanoff 
posted an update 20 days ago
view post
Post
3199
Duality.ai just released a 1000 image dataset used to train a YOLOv8 model in multiclass object detection -- and it's 100% free!
duality-robotics/YOLOv8-Multiclass-Object-Detection-Dataset

Access the full size dataset by creating an EDU account here- https://falcon.duality.ai/secure/documentation/ex3-dataset?sidebarMode=learn

Or check it out in the linked HuggingFace dataset!

What makes this dataset unique, useful, and capable of bridging the Sim2Real gap?

💠 The digital twins are not generated by AI, but instead crafted by 3D artists to be INDISTINGUISHABLE from the physical-world objects. This allows the training from this data to transfer into real-world applicability

💠 The simulation software, called FalconEditor, can easily create thousands of images with varying lighting, posing, occlusions, backgrounds, camera positions, and more. This enables robust model training.

💠 The labels are created along with the data. This not only saves large amounts of time, but also ensures the labels are incredibly accurate and reliable.

This HuggingFace dataset is a 20 image and label sample, but you can get the rest at no cost by creating a FalconCloud account here: https://falcon.duality.ai/secure/documentation/ex3-dataset?sidebarMode=learn.

Once you verify your email, the link will redirect you to the dataset page.
DualityAI-RebekahBogdanoff 
posted an update 25 days ago
view post
Post
3111
✨🎉Duality.ai just released a multiclass object detection dataset for YOLOv8, as well as a tutorial on how to create your own multiclass dataset!

Carefully crafted (not GenAI created) synthetic data that ACTUALLY trains a model that works in the physical world.

Create a free FalconEDU account, and download the 1000 image and annotation dataset - https://falcon.duality.ai/secure/documentation/ex3-dataset?sidebarMode=learn
-or-
Follow along with Exercise 3: Multiclass Object Detection to start creating - https://falcon.duality.ai/secure/documentation/ex3-objdetection-multiclass
-or-
Download this Colab notebook to see the data work, no hardware required - https://falcon.duality.ai/secure/documentation/ex3-dataset?sidebarMode=learn

MMSDuality 
updated a Space about 1 month ago
DualityAI-RebekahBogdanoff 
posted an update about 1 month ago
view post
Post
3099
This Friday at 11 pm ET, Duality.ai is offering a free course on creating realistic materials in simulation. https://forms.gle/iHjqojKUEJZ3EU7w6

Crafting data in simulation that is indistinguishable from the physical world is essential for bridging the sim2real gap. Physically Based Rendering, or PBR, materials play a huge role in realism. Join us the Friday to learn more.

Duality.ai has been successful in using game engine simulation to create synthetic data that jumps the sim2 real gap for many commercial clients including JPL-NASA, AWS, P&G, and more. Check out our educational content to access the software and the work flow that makes this possible https://www.duality.ai/edu
DualityAI-RebekahBogdanoff 
posted an update about 2 months ago
view post
Post
2437
🗣️💬We at Duality.ai want to hear about your specific dataset needs!!

We created a pose estimation dataset and an explanatory colab here:
➡️Dataset: duality-robotics/pose_estimation
➡️Colab: https://falcon.duality.ai/secure/documentation/pose-colab (you will have to create a free account to access)

😎We want to continue supporting the computer vision community, but we need to hear from you-
❓What computer vision tasks you are working on that could benefit from intentionally crafted data produced by our simulation software, FalconEditor?

Share your ideas in the comment section below, and we'll create annotated and labeled datasets to address the most pressing community needs.

Some areas to consider:

- Object detection in challenging environments
- Semantic segmentation for diverse scenes
- Pose Estimation data set with variance (IDK)
- Multi-object tracking
- Anomaly detection
- Domain-specific tasks (e.g., medical imaging, autonomous driving)

Let us know your dataset needs, and we'll work on generating synthetic data to address them!

As always, create a free EDU account to start using FalconEditor to create synthetic data on your own! Sign up here: https://falcon.duality.ai/auth/sign-up
Mishsim 
updated a Space about 2 months ago
Mishsim 
in duality-robotics/README about 2 months ago
DualityAI-RebekahBogdanoff 
posted an update 2 months ago
view post
Post
1845
🗣️📢This Friday January 24th at 11 ET, Duality.ai is hosting a free class demonstrating how to craft synthetic data using game engines and digital twin simulation workflows (not GenAI) in our FalconEditor simulation software. https://forms.gle/89Y7QrkrYJV6JrFk7

🤔Curious to delve into digital twin simulation for AI training, but don't know where to start?
Get hands-on experience with FalconEditor and learn how to assemble digital twins into simulation scenarios that produce high-quality synthetic data.

👉 Note: You don't have to wait for Friday to experiment with Falcon. Create a free account here and start learning to create synthetic data and train AI models: https://falcon.duality.ai/secure/documentation?learnWelcome=true&sidebarMode=learn
  • 2 replies
·
DualityAI-RebekahBogdanoff 
posted an update 2 months ago
view post
Post
1953
Learn about using (crafted, not GenAI) synthetic data from simulation to train and AI vision model by watching the replay of Duality's webinar from Friday-
https://www.youtube.com/watch?v=BmpH3xtoS38

You can also see the replay for the free Photogrammetry course-
https://www.youtube.com/watch?v=52gCkc9Hijg
We take you through a free workflow for creating digital twins that can then be used in simulation to create synthetic data.

Finally, hear from our Senior Technical Artist here at Duality.ai. His work with Unreal Engine, building digital twins that we use to generate accurate synthetic data, is indispensable to our success with training AI vision models-
https://www.youtube.com/watch?v=tIwz_i5RU7E
DualityAI-RebekahBogdanoff 
posted an update 2 months ago
view post
Post
537
Duality.ai is offering a one-hour webinar and Q&A with Duality's Felipe Mejia (AI Vision Engineer) and Gandharv Mahajan (Solutions Architect) next Friday. https://forms.gle/JznzvKasYVYGfXda6

During the session, Felipe and Gandharv will walk through vital techniques for ensuring success when using digital twins in game engines to create synthetic data for training AI vision models. Leveraging examples from Duality's diverse work, the team will illustrate what they have learned about effective AI training, and answer questions about specific approaches, current challenges, and best practices grounded in real-world experience.