RoboNet: Large-Scale Multi-Robot Learning
Classification
View four quadrants- Major category
- Datasets
- Quadrant
- Not applicable
- Architecture
- Not applicable
- Prediction paradigm
- Not applicable
- Subcategories
- Cross-robot & multitask dataRobot interaction data
- Source review status
- Not assigned
Category review. The primary contribution is a shared multi-robot interaction dataset; distinct forward-planning and inverse-dynamics baselines evaluate its transfer utility rather than defining one proposed WAM architecture. The cataloged contribution is a dataset/data-generation method or evaluation/simulation resource, not the architecture of an evaluated or external policy. Reading evidence
Contribution
RoboNet pools robot experience to make visual control transferable. Pretraining improves adaptation with a few hundred target-robot trajectories, but relevant subsets can outperform the broader pool. Its central contribution is a shared dataset evaluated through two distinct control algorithms.
Abstract
An abstract has not been added yet.
Affiliations
UC Berkeley; Stanford University; University of Pennsylvania; CMU