Research

Making robots intelligent, safe and accessible at scale

AirGen : The evolution of AirSim

MatMamba: An Elastic and Efficient Neural Network Architecture

7 Lessons from AirSim

Introducing GRID Enterprise

Announcing GRID Beta - An Open and Free Platform for Robot Intelligence

Enhancing Robotic Planning with Logically Constrained Transformers

GRID: A Platform For General Robot Intelligence Development

Hello World: Launch of Scaled Foundations' Robotics AI Development Platform

SMART – A Generalized Pretraining Framework For Control Tasks

ChatGPT For Robotics: Design Principles And Model Abilities

PACT: Perception-Action Causal Transformer For Autoregressive Robotics Pretraining

Data-driven Sensor Simulation for Realistic LiDARs

AirGen : The evolution of AirSim

MatMamba: An Elastic and Efficient Neural Network Architecture

7 Lessons from AirSim

Introducing GRID Enterprise

Announcing GRID Beta - An Open and Free Platform for Robot Intelligence

Enhancing Robotic Planning with Logically Constrained Transformers

GRID: A Platform For General Robot Intelligence Development

Hello World: Launch of Scaled Foundations' Robotics AI Development Platform

SMART – A Generalized Pretraining Framework For Control Tasks

ChatGPT For Robotics: Design Principles And Model Abilities

PACT: Perception-Action Causal Transformer For Autoregressive Robotics Pretraining

Data-driven Sensor Simulation for Realistic LiDARs

Just say the magic word: using language to program robots

AirGen : The evolution of AirSim

A pivotal step forward in the evolution of simulation technology, expanding the possibilities for AI and robotics development.

MatMamba: An Elastic and Efficient Neural Network Architecture

Combining the speed of State Space Models (SSMs) like Mamba2 with the adaptability of Matryoshka-style learning.

7 Lessons from AirSim

I ran the autonomous systems and robotics research effort at Microsoft for nearly a decade and here are our biggest learnings.

Introducing GRID Enterprise

A private GRID experience that is scalable, customizable, and deeply integrated into your development pipeline.

Announcing GRID Beta - An Open and Free Platform for Robot Intelligence

We’re opening the waitlist for our General Robot Intelligence Development (GRID) platform. GRID is an open and free cloud-based IDE for robotics, requiring zero setup. GRID accelerates robot AI development with seamless access to foundation models, simulation and AI infrastructure.

Enhancing Robotic Planning with Logically Constrained Transformers

We introduce Perception Action Signal Temporal Logic Transformer (PASTEL), a deep machine learning architecture to control robots safely.

GRID: A Platform For General Robot Intelligence Development

We released a platform for creating intelligent and safe robots using foundation models, large language models, and simulation.

Hello World: Launch of Scaled Foundations' Robotics AI Development Platform

The General Robot Intelligence Development (GRID) platform combines foundation models, simulation, and large language models for rapid prototyping

SMART – A Generalized Pretraining Framework For Control Tasks

We are announcing SMART, a generalized pretraining framework for a wide variety of control tasks.

ChatGPT For Robotics: Design Principles And Model Abilities

We extended the capabilities of ChatGPT to robotics, and controlled multiple platforms such as robot arms, drones, and home assistant robots intuitively with language.

PACT: Perception-Action Causal Transformer For Autoregressive Robotics Pretraining

Recent advances in machine learning architectures have induced a paradigm shift from task-specific models towards large general-purpose networks.

Data-driven Sensor Simulation for Realistic LiDARs

Simulation is playing an increasingly major role in the development of safe and robust autonomous systems, especially given the advent of deep learning techniques.

Just say the magic word: using language to program robots

Language is the most intuitive way for us to express how we feel and what we want.