الملخص
Recent advances in learning-based robot policies have demonstrated promising progress, yet they are predom- inantly evaluated in static or quasi-static environments. In dynamic manipulation, objects and scenes continuously evolve while the robot perceives, reasons, and acts. However, recent dynamic simulation benchmarks largely focus on short-horizon, reactive interactions with simple motion patterns and offer limited support for both systematic evaluation under domain shifts and model-agnostic real-time execution protocols. To bridge these gaps, we introduce MotionForge, the first large- scale simulation benchmark and data-generation pipeline tailored to jointly evaluate domain shifts and long-horizon interaction in dynamic manipulation. MotionForge comprises 40 dynamic interaction tasks spanning 11 distinct motion patterns, with dedicated support for 17 long-horizon tasks. Our benchmark introduces two key novelties: (1) a systematic evaluation protocol for assessing policy robustness under both single-factor (e.g., only backgrounds shift) and joint domain shifts (e.g., simultaneous shifts of objects, backgrounds, lighting, and speed); and (2) a decoupled, latency-aware execution protocol where the environ- ment continuously evolves independently of policy inference time. Extensive evaluations of representative general-purpose robot policies on our benchmark reveal substantial limitations under joint domain shifts. These findings expose a critical gap between current policy capabilities and the requirements of robust long- horizon manipulation of dynamic objects under domain shifts, establishing MotionForge as a comprehensive testbed for future research in embodied AI.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Liu, M., Mei, D., Xian, H., Han, R., Sun, J., Chen, X., Zhang, H., Li, L., Mao, K., & Wang, L. (2026). MotionForge: A Data Generation Pipeline and Large-Scale Benchmark for Long-Horizon Manipulation of Dynamic Objects with Domain Shifts. https://omanscience.com/ar/articles/motionforge-a-data-generation-pipeline-and-large-scale-benchmark-for-long-horizon-manipulation-of-dynamic-objects-with-domain-shifts
MLA 9
Liu, Mohan, et al. "MotionForge: A Data Generation Pipeline and Large-Scale Benchmark for Long-Horizon Manipulation of Dynamic Objects with Domain Shifts." https://omanscience.com/ar/articles/motionforge-a-data-generation-pipeline-and-large-scale-benchmark-for-long-horizon-manipulation-of-dynamic-objects-with-domain-shifts.
شيكاغو (المؤلف–التاريخ)
Liu, Mohan, Dengchen Mei, Haotian Xian, Ruyang Han, Jiayi Sun, Xuanyu Chen, Haitian Zhang, Luxi Li, Kaimin Mao, and Lin Wang. 2026. "MotionForge: A Data Generation Pipeline and Large-Scale Benchmark for Long-Horizon Manipulation of Dynamic Objects with Domain Shifts." https://omanscience.com/ar/articles/motionforge-a-data-generation-pipeline-and-large-scale-benchmark-for-long-horizon-manipulation-of-dynamic-objects-with-domain-shifts.
هارفارد
Liu, M., Mei, D., Xian, H., Han, R., Sun, J., Chen, X., Zhang, H., Li, L., Mao, K. and Wang, L. (2026) 'MotionForge: A Data Generation Pipeline and Large-Scale Benchmark for Long-Horizon Manipulation of Dynamic Objects with Domain Shifts', Available at: https://omanscience.com/ar/articles/motionforge-a-data-generation-pipeline-and-large-scale-benchmark-for-long-horizon-manipulation-of-dynamic-objects-with-domain-shifts.
فانكوفر
Liu M, Mei D, Xian H, Han R, Sun J, Chen X, et al. MotionForge: A Data Generation Pipeline and Large-Scale Benchmark for Long-Horizon Manipulation of Dynamic Objects with Domain Shifts. https://omanscience.com/ar/articles/motionforge-a-data-generation-pipeline-and-large-scale-benchmark-for-long-horizon-manipulation-of-dynamic-objects-with-domain-shifts
IEEE
M. Liu, D. Mei, H. Xian, R. Han, J. Sun, X. Chen, H. Zhang, L. Li, K. Mao, and L. Wang, "MotionForge: A Data Generation Pipeline and Large-Scale Benchmark for Long-Horizon Manipulation of Dynamic Objects with Domain Shifts," https://omanscience.com/ar/articles/motionforge-a-data-generation-pipeline-and-large-scale-benchmark-for-long-horizon-manipulation-of-dynamic-objects-with-domain-shifts.