Third-Person Visual Imitation Learning via Decoupled Hierarchical Controller
Pratyusha Sharma, Deepak Pathak, Abhinav Gupta
–Neural Information Processing Systems
We study a generalized setup for learning from demonstration to build an agent that can manipulate novel objects in unseen scenarios by looking at only a single video of human demonstration from a third-person perspective. To accomplish this goal, our agent should not only learn to understand the intent of the demonstrated thirdperson video in its context but also perform the intended task in its environment configuration. Our central insight is to enforce this structure explicitly during learning by decoupling what to achieve (intended task) from how to perform it (controller). We propose a hierarchical setup where a high-level module learns to generate a series of first-person sub-goals conditioned on the third-person video demonstration, and a low-level controller predicts the actions to achieve those sub-goals.
Neural Information Processing Systems
Jan-25-2025, 10:08:04 GMT
- Country:
- North America (0.28)
- Technology:
- Information Technology > Artificial Intelligence
- Machine Learning > Neural Networks
- Deep Learning (0.68)
- Robots (1.00)
- Vision (1.00)
- Machine Learning > Neural Networks
- Information Technology > Artificial Intelligence