Autonomous Systems and Robotics Group
Developing training and simulation technologies for robotics systems
Articles
We are announcing SMART, a generalized pretraining framework for a wide variety of control tasks. Self-supervised pretraining of large neural networks (BERT (opens in new tab), GPT (opens in new tab), MoCo (opens in new tab), and CLIP (opens in…
We extended the capabilities of ChatGPT to robotics, and controlled multiple platforms such as robot arms, drones, and home assistant robots intuitively with language. Have you ever wanted to tell a robot what to do using your own words, like…
We are announcing ClimaX, a flexible and generalizable deep learning model for weather and climate science. ClimaX is trained using several heterogeneous datasets spanning many weather variables at multiple spatio-temporal resolutions. We show that such a foundational model can be…
Open sourcing PDEArena
We are open sourcing PDEArena, a modern, scalable, and easy to use PDE surrogate benchmarking framework. PDEArena is designed to train and evaluate neural surrogates for partial differential equations (PDE) at scale. As such, PDEArena contains state of the art…
The use of modeling and simulation in engineering is well recognized as a viable method to build surrogates for real-world systems. Simulation allows for testing and evaluation of large and complex systems in a risk-free environment, helping document failures, reduce…
PACT paper (opens in new tab) | Video (opens in new tab)| Github code (opens in new tab) Recent advances in machine learning architectures have induced a paradigm shift from task-specific models towards large general-purpose networks. For instance, in the…
Paper (opens in new tab) / Code (opens in new tab) / Demo (opens in new tab) / Docs (opens in new tab) Modern machine learning models are known to fail in ways that aren’t anticipated during training these models. These…
Simulation is playing an increasingly major role in the development of safe and robust autonomous systems, especially given the advent of deep learning techniques. Given the challenges and effort involved with collecting data in real life, simulation provides an efficient…
LaTTe paper (opens in new tab) and video (opens in new tab) | Trajectory Transformer paper (opens in new tab) and video (opens in new tab) | Github code (opens in new tab) Language is the most intuitive way for…