Event
Nexus-VLA proposes a cross-embodiment framework for joint human-robot training
1 reports · 1 sources
Biaoliang Guan and other authors have released a paper proposing the Nexus-VLA hybrid policy learning framework, which achieves cross-embodiment knowledge transfer through end-to-end joint human-robot training, allowing human operation experience to directly participate in robot policy learning. The framework first establishes hierarchical cross-embodiment semantic alignment from task intent to fine-grained interaction, and then encodes multi-level shared knowledge as a shared manipulation latent representation, which is directly used for continuous action generation. The authors state that in RoboCasa-GR1, OOD settings, and real-robot experiments, Nexus-VLA achieved an 80.5% task success rate on RoboCasa-GR1 and demonstrated advantages in human data utilization, learning efficiency, and cross-scenario generalization.
Report timeline
- Nexus-VLA: Connecting Human and Robot Experience with a Shared Hierarchical Semantic Latent Space
The authors propose Nexus-VLA, a hybrid policy learning framework that enables cross-embodiment knowledge transfer through end-to-end human-robot joint training, allowing human manipulation experience to directly contribute to robot policy learning. The framework first establishes hierarchical cross-embodiment semantic alignment from task intent to fine-grained interactions, then encodes multi-level shared knowledge into a shared manipulation latent representation used directly for continuous action generation. In RoboCasa-GR1, OOD settings, and real-robot experiments, Nexus-VLA achieved an 80.5% task success rate on RoboCasa-GR1.
arXiv cs.RO ·
Related topics
Interest trend
- Current
- 3
- Peak
- 4Nov 4 01:00
- Past 24 hours
- –
The trend compares participants observed throughout the same period, so its range may be smaller than the current interest count. Move or tap to inspect each hour; use the arrow keys on a keyboard.