الملخص
World Action Models (WAMs) couple action generation with future visual prediction for robotic manipulation. However, completing the joint video-action denoising process at each replanning cycle incurs substantial latency, delaying action updates and limiting closed-loop responsiveness. We present Rolling-WAM, a formulation that distributes joint denoising across successive replanning cycles. Our method maintains a sliding window of video-action chunks at staggered noise levels. At each step, a rolling noise schedule fully denoises the imminent action chunk for execution, while partially refining farther-future chunks. As the window advances with new camera observations, the retained future chunks continue their denoising process. This distributes the computational cost over time while carrying an evolving visual-action context across chunk boundaries. Evaluations on LIBERO, RoboTwin, and a real-world Unitree G1 humanoid show that Rolling-WAM achieves competitive manipulation performance. By removing the need to denoise the entire prediction horizon from scratch, it delivers a 4.5x steady-state replanning speedup over standard joint WAMs.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Zhou, Y., Ye, J., Zhao, Y., Dong, H., Wang, C. S., Ge, R., Yang, T., Van Hoorick, B., Sukhatme, G., Guizilini, V., & Wang, Y. (2026). Rolling-WAM: World Action Models with Rolling Imagination. https://omanscience.com/ar/articles/rolling-wam-world-action-models-with-rolling-imagination
MLA 9
Zhou, Yinghua, et al. "Rolling-WAM: World Action Models with Rolling Imagination." https://omanscience.com/ar/articles/rolling-wam-world-action-models-with-rolling-imagination.
شيكاغو (المؤلف–التاريخ)
Zhou, Yinghua, Junjie Ye, Yiqi Zhao, Hao Dong, Celina Shiyu Wang, Ruohai Ge, Tingyi Yang, Basile Van Hoorick, Gaurav Sukhatme, Vitor Guizilini, and Yue Wang. 2026. "Rolling-WAM: World Action Models with Rolling Imagination." https://omanscience.com/ar/articles/rolling-wam-world-action-models-with-rolling-imagination.
هارفارد
Zhou, Y., Ye, J., Zhao, Y., Dong, H., Wang, C. S., Ge, R., Yang, T., Van Hoorick, B., Sukhatme, G., Guizilini, V. and Wang, Y. (2026) 'Rolling-WAM: World Action Models with Rolling Imagination', Available at: https://omanscience.com/ar/articles/rolling-wam-world-action-models-with-rolling-imagination.
فانكوفر
Zhou Y, Ye J, Zhao Y, Dong H, Wang CS, Ge R, et al. Rolling-WAM: World Action Models with Rolling Imagination. https://omanscience.com/ar/articles/rolling-wam-world-action-models-with-rolling-imagination
IEEE
Y. Zhou, J. Ye, Y. Zhao, H. Dong, C. S. Wang, R. Ge, T. Yang, B. Van Hoorick, G. Sukhatme, V. Guizilini, and Y. Wang, "Rolling-WAM: World Action Models with Rolling Imagination," https://omanscience.com/ar/articles/rolling-wam-world-action-models-with-rolling-imagination.