الملخص
World Action Models (WAMs) acquire behavioral priors by modeling future scene evolution, but predicting detailed futures in pixel or latent space incurs substantial cost. Recent evidence that co-training gains persist without test-time generation raises a question: what must a WAM learn to improve control? We introduce Copper-Policy, which learns a compact World representation with the policy rather than relying on a predefined target space. Through temporal joint-embedding prediction, it predicts future observation embeddings conditioned on task intention without reconstructing pixels. This prediction and action decoding shape the representation jointly, while the policy retains access to current-frame spatial detail for execution. Representation analyses show that the learned features better separate task-driven change from perturbations and provide complementary information for control. Compact prediction targets reduce training tokens per sample, enabling a 2B-parameter model trained in 9.67 hours on 8$\times$ RTX 5090 GPUs and 6$\times$ faster than Fast-WAM on matched A100 GPUs. Copper-Policy outperforms every compared method without embodied pretraining on RoboTwin and several embodied-pretrained VLAs on LIBERO-Plus (80.85%). On three challenging real-robot tasks, it performs comparably to $π_{0.5}$ and attains a higher average score. Together, these results show that Copper-Policy combines strong control performance with efficient training.
الكلمات المفتاحية
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Feng, Z., Feng, Y., Xiao, L., Su, S., Zheng, K., Xu, C., Shi, M., Feng, S., & Yan, X. (2026). Copper-Policy: Focus on the Representation for Robust Robot Manipulation. https://omanscience.com/ar/articles/copper-policy-focus-on-the-representation-for-robust-robot-manipulation
MLA 9
Feng, Zexin, et al. "Copper-Policy: Focus on the Representation for Robust Robot Manipulation." https://omanscience.com/ar/articles/copper-policy-focus-on-the-representation-for-robust-robot-manipulation.
شيكاغو (المؤلف–التاريخ)
Feng, Zexin, Yixu Feng, Lingyu Xiao, Shang Su, Kexin Zheng, Chang Xu, Mengkai Shi, Shuo Feng, and Xintao Yan. 2026. "Copper-Policy: Focus on the Representation for Robust Robot Manipulation." https://omanscience.com/ar/articles/copper-policy-focus-on-the-representation-for-robust-robot-manipulation.
هارفارد
Feng, Z., Feng, Y., Xiao, L., Su, S., Zheng, K., Xu, C., Shi, M., Feng, S. and Yan, X. (2026) 'Copper-Policy: Focus on the Representation for Robust Robot Manipulation', Available at: https://omanscience.com/ar/articles/copper-policy-focus-on-the-representation-for-robust-robot-manipulation.
فانكوفر
Feng Z, Feng Y, Xiao L, Su S, Zheng K, Xu C, et al. Copper-Policy: Focus on the Representation for Robust Robot Manipulation. https://omanscience.com/ar/articles/copper-policy-focus-on-the-representation-for-robust-robot-manipulation
IEEE
Z. Feng, Y. Feng, L. Xiao, S. Su, K. Zheng, C. Xu, M. Shi, S. Feng, and X. Yan, "Copper-Policy: Focus on the Representation for Robust Robot Manipulation," https://omanscience.com/ar/articles/copper-policy-focus-on-the-representation-for-robust-robot-manipulation.