Research2 @ A2I
Research @ A2I
The research we do at A2I spans a diverse range of application areas, from robot perception to reinforcement learning and learning from demonstration. Our focus lies on exploring fundamental challenges at the intersection of machine learning, AI, and robotics.
Here’s a closer look at some of the exciting work going on in the group.
Perception
Perception
We develop methods for weak and unsupervised learning at scale and across multiple modalities such as vision, 3D, and radar. Sub-themes include:
- Unsupervised Scene Understanding
- Affordance Learning and Intuitive Physics
- Dynamics Learning
Action
Action:
In order to perform complex, real-world tasks robots need to plan and act reactively for a number of concurrent objectives. Our research focuses on achieving intelligent robot action via the following sub-themes:
- Versatile Motor Reflexes
- Latent-Space Control
- Metacognition