Research
- Oct 13·Rhoda AI Research
Giving Robots a Sense of Touch
We introduce a new tactile sensor and integrate its measurements into our multimodal Direct Video-Action model, enabling robots to identify and manipulate objects through touch.
Read more →
- Sep 10·Rhoda AI Research
Does Scaling Web-Video Pre-training Help Real Robots Do Real Work?
We investigate scaling model size and pre-training compute for video-based robot policies, and benchmark on a real industrial manipulation task.
Read more →
- Mar 10·Rhoda AI Research
Causal Video Models Are Data-Efficient Robot Policy Learners
At Rhoda AI, we are building towards generalist robotics. Our Direct Video-Action Model (DVA) reformulates robot policies as video generation, unlocking data-efficient task learning, scaling, long-context memory, and one-shot learning.
Read more →