الملخص
General-purpose robots must infer what a new task requires and translate that understanding into appropriate physical action. In-context learning (ICL) for robots supports this process by using demonstrations and interaction to direct existing competence with neural parameters held fixed during deployment. We organize this literature review around the interfaces connecting contextual evidence to execution, distinguishing four families: context-conditioned policies, geometric demonstration transfer, world-model-based control, and skill- and agent-based execution. Comparing these interfaces clarifies their transfer assumptions and the roles of training, correspondence, and memory in making context useful. Across manipulation and navigation, we examine how these mechanisms preserve taught requirements as objects, environments, and execution conditions change. This analysis links method design to evaluation practices that distinguish responsiveness to teaching, physical transfer, and benefits from retained experience. The resulting agenda connects compositional task acquisition and faithful transfer with physical recursive self-improvement, in which experience improves the ability to learn subsequent tasks.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Huang, H., Li, Z., Guo, J., Zhang, Y., Peng, W., Zhou, B., Ruan, W., Wu, L., Wang, C., Su, J., Xie, B., Chen, W., Xu, Y., Zhou, T., Chen, S., Zhao, P., He, J., Li, X. Y., Li, R., Dong, P., Dang, S., Huang, J., Chen, Y., Chang, Y., Zhang, T., Deng, S., Wang, H., Wei, Y., Li, W., Yang, H., Zhou, K., Liu, H., Cheng, J., Shao, R., Wang, D., Jin, Y., Hao, J., Chen, Y. C., & Li, Y. (2026). In-Context Learning for Robots: Methods and Applications. https://omanscience.com/ar/articles/in-context-learning-for-robots-methods-and-applications
MLA 9
Huang, Haojian, et al. "In-Context Learning for Robots: Methods and Applications." https://omanscience.com/ar/articles/in-context-learning-for-robots-methods-and-applications.
شيكاغو (المؤلف–التاريخ)
Huang, Haojian, Zexi Li, Junhao Guo, Yehang Zhang, Wenxuan Peng, Bohan Zhou, Weilin Ruan, Leyi Wu, Chenxu Wang, Jianchong Su, Binghui Xie, Wosong Chen, Yingjie Xu, Tianhao Zhou, Suzeyu Chen, Pukun Zhao, Jiaqi He, Xin-Yi Li, Runze Li, Peiran Dong, Shaoxiang Dang, Jing Huang, Yingbing Chen, Yifan Chang, Tianyi Zhang, Shiyuan Deng, Haozhi Wang, Yangkai Wei, Wenqian Li, Han Yang, Kaiwen Zhou, Huaping Liu, James Cheng, Rui Shao, Donglin Wang, Yaochu Jin, Jianye Hao, Ying-Cong Chen, and Yinchuan Li. 2026. "In-Context Learning for Robots: Methods and Applications." https://omanscience.com/ar/articles/in-context-learning-for-robots-methods-and-applications.
هارفارد
Huang, H., Li, Z., Guo, J., Zhang, Y., Peng, W., Zhou, B., Ruan, W., Wu, L., Wang, C., Su, J., Xie, B., Chen, W., Xu, Y., Zhou, T., Chen, S., Zhao, P., He, J., Li, X. Y., Li, R., Dong, P., Dang, S., Huang, J., Chen, Y., Chang, Y., Zhang, T., Deng, S., Wang, H., Wei, Y., Li, W., Yang, H., Zhou, K., Liu, H., Cheng, J., Shao, R., Wang, D., Jin, Y., Hao, J., Chen, Y. C. and Li, Y. (2026) 'In-Context Learning for Robots: Methods and Applications', Available at: https://omanscience.com/ar/articles/in-context-learning-for-robots-methods-and-applications.
فانكوفر
Huang H, Li Z, Guo J, Zhang Y, Peng W, Zhou B, et al. In-Context Learning for Robots: Methods and Applications. https://omanscience.com/ar/articles/in-context-learning-for-robots-methods-and-applications
IEEE
H. Huang, Z. Li, J. Guo, Y. Zhang, W. Peng, B. Zhou, W. Ruan, L. Wu, C. Wang, J. Su, B. Xie, W. Chen, Y. Xu, T. Zhou, S. Chen, P. Zhao, J. He, X. Y. Li, R. Li, P. Dong, S. Dang, J. Huang, Y. Chen, Y. Chang, T. Zhang, S. Deng, H. Wang, Y. Wei, W. Li, H. Yang, K. Zhou, H. Liu, J. Cheng, R. Shao, D. Wang, Y. Jin, J. Hao, Y. C. Chen, and Y. Li, "In-Context Learning for Robots: Methods and Applications," https://omanscience.com/ar/articles/in-context-learning-for-robots-methods-and-applications.