Towards a Data Flywheel for Embodied Intelligence in Logistics
For logistics companies seeking to deploy embodied AI, this work provides a framework to leverage operational data for policy improvement, though results are preliminary.
The paper proposes a data-centric framework for embodied intelligence in logistics, introducing WM-DAgger which uses World Models to generate out-of-distribution recovery data for robust imitation learning, achieving improved policy robustness.
Embodied intelligence is moving from laboratory demonstrations toward industrial deployment, with the logistics industry serving as a key application scenario. Learning-based policies offer a promising path beyond traditional perception-planning-control pipelines, but their scalability depends on how embodied data can be collected, organized, and reused. This research studies a data-centric framework for industrial embodied intelligence by constructing a logistics data flywheel. Our framework converts daily operations into reusable data assets, uses World Models to generate reliable supervision for long-tail parcel manipulation, and feeds deployment feedback back into policy improvement. As an initial result, \textit{WM-DAgger} introduces a World-Model-based data aggregation framework that synthesizes out-of-distribution recovery data for robust imitation learning. Building on this result, ongoing work explores how large-scale in-the-wild multimodal data, including labeled human demonstrations, unlabeled operational videos, and system-level robot logs, can be aligned for policy learning and transformed into feedback for continual system improvement.