Towards Generalizable Robotic Manipulation in Dynamic Environments
Vision-Language-Action (VLA) models excel in static manipulation but struggle in dynamic environments with moving targets. This performance gap primarily stems from a scarcity of dynamic manipulation datasets and the reliance of mainstream VLAs on single-frame observations, restricting their spatiotemporal reasoning capabilities. To address this, we introduce DOMINO, a large-scale dataset and benchmark for generalizable dynamic manipulation, featuring 35 tasks with hierarchical complexities, over 110K expert trajectories, and a multi-dimensional evaluation suite. Through comprehensive experiments, we systematically evaluate existing VLAs on dynamic tasks, explore effective training strate...
| Authors | Heng Fang, Shangru Li, Shuhan Wang et al. |
|---|---|
| Primary category | cs.CV |
| Published | 16 March 2026 |
| Last updated at source | 30 June 2026 |
Popularity, last 2 days
0 now. Counts as reported by the source, snapshotted daily by Silytics.
Connected in the knowledge graph
- H-EmbodVis/DOMINODataset · cited by
Models and datasets referencing this paper
- H-EmbodVis/DOMINODataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 19 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.