NTU & Daxiao Robot Open Source ACE-Data-0: Multimodal Embodied Interaction Dataset
青稞AI · wechat · 2026-08-05
Nanyang Technological University's S-Lab and Daxiao Robot have jointly open-sourced ACE-Data-0, a dataset for embodied intelligence and robot learning. Based on the environmental capture system ACE, it transforms real home environments into data collection platforms.
ACE-Data-0 synchronously records egocentric and multi-view video, whole-body and hand movements, object geometry, 6-DoF actions, trajectories, multi-channel audio, and tactile signals. The data covers fine human-object manipulation and continuous household task chains, preserving natural behavioral differences during real task execution. It aims to provide a unified foundation for understanding long-horizon behavior and physical interaction, with applications in imitation learning, world models, and Vision-Language-Action (VLA) models.
More from Embodied
- Tesla's Planned 'Terafab' to Span 10x Giga Texas, Target 1TW AI Compute — XFreeze · 2026-08-05
- NeurIPS 2026 Calls for Papers on Embodied Spatial Reasoning and World Models — du_yilun · 2026-08-05
- Embodied AI in Action: Agent Autonomously Plans 3D Printer Transport — neurosp1ke · 2026-08-05
- Robotics Needs Custom Small VLMs: Fine-tuned Qwen Beats APIs in Cost and Accuracy — ChongZzZhang · 2026-08-05
- Silico makes robotics model 40% more efficient by removing attention layers — mathildepapillo · 2026-08-05
- Pruning Attention Layers Slashes Action Expert FLOPs by 94% in Robotics — mathildepapillo · 2026-08-05