Aerial Informatics and Robotics Group
Nouvelles et reportages
Dans l’actualité | sees.ai
sees.ai joins Microsoft’s Project AirSim early access program
From the beginning, our simulation software of choice has been Microsoft’s AirSim – an experimental open source code base that has provided a common way for unmanned aerial vehicle developers to share research code and test new ideas around aerial…
Dans l’actualité | Microsoft Project AirSim accelerates autonomous flight with Unreal Engine
Microsoft Project AirSim accelerates autonomous flight with Unreal Engine
The safety and effectiveness of autonomous vehicles relies on rigorous training through simulation. To ensure such training reflects realistic terrain, weather conditions, and scenarios, many companies turn to real-time technology like Unreal Engine. Case in point: Microsoft Project AirSim uses…
Dans l’actualité | FINN
Microsoft’s AirSim uses virtual world to prepare aircraft for real life challenges
Microsoft’s Project AirSim, a new platform to safely build, train and test autonomous aircraft through high-fidelity simulation, offers developers a “unique” opportunity to use a scalable system that ensures their models can meet real-world challenges, Ganesh Rao, general manager at…
CausalCity: Introducing a high-fidelity simulation with agency for advancing causal reasoning in machine learning
| Daniel McDuff, Yale Song, Sai Vemprala, Vibhav Vineet, Shuang Ma, et Ashish Kapoor
The ability to reason about causality, and ask «what would happen if…?’’ is one property that sets human intelligence apart from artificial intelligence. Modern AI algorithms perform well on clearly defined pattern recognition tasks but fall short generalizing in the…
Research Collection – Shall we play a game?
From a research point of view, games offer an amazing environment in which to develop new machine learning algorithms and techniques. And we hope, in due course, that those new algorithms will feed back not just into gaming, but into…
Unadversarial examples: Designing objects for robust vision
| Hadi Salman
Many of the items and objects we use in our daily lives were designed with people in mind. In October, the Reserve Bank of Australia put out into the world its redesigned $100 banknote. Some design elements remained the same—such…
Adversarial robustness as a prior for better transfer learning
| Hadi Salman
Editor’s note: This post and its research are the collaborative efforts of our team, which includes Andrew Ilyas (PhD Student, MIT), Logan Engstrom (PhD Student, MIT), Aleksander Mądry (Professor at MIT), Ashish Kapoor (Partner Research Manager). In practical machine learning,…
Teaching a robot to see and navigate with simulation
| Sebastian Scherer et Ashish Kapoor
The ability to see and navigate is a critical operational requirement for robots and autonomous systems. For example, consider autonomous rescue robots that are required to maneuver and navigate in challenging physical environments that humans cannot safely access. Similarly, building AI…
Game of Drones at NeurIPS 2019: Simulation-based drone-racing competition built on AirSim
| Ratnesh Madaan et Ashish Kapoor
Drone racing has transformed from a niche activity sparked by enthusiastic hobbyists to an internationally televised sport. In parallel, computer vision and machine learning are making rapid progress, along with advances in agile trajectory planning, control, and state estimation for…