Imperative learning: A self-supervised neuro-symbolic learning framework for robot autonomy
The International Journal of Robotics Research · 05.08.2025
DOI: 10.1177/02783649251353181 ↗Kurz gefasst
Fachartikel in der Zeitschrift The International Journal of Robotics Research, online erschienen am 05.08.2025. Verfasst von Chen Wang und 18 weiteren Autor:innen. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 300 Literaturangaben.
Abstract (Originalsprache)
Data-driven methods such as reinforcement and imitation learning have achieved remarkable success in robot autonomy. However, their data-centric nature still hinders them from generalizing well to ever-changing environments. Moreover, labeling data for robotic tasks is often impractical and expensive. To overcome these challenges, we introduce a new self-supervised neuro-symbolic (NeSy) computational framework, imperative learning (IL), for robot autonomy, leveraging the generalization abilities of symbolic reasoning. The framework of IL consists of three primary components: a neural module, a reasoning engine, and a memory system. We formulate IL as a special bilevel optimization (BLO), which enables reciprocal learning over the three modules. This overcomes the label-intensive obstacles associated with data-driven approaches and takes advantage of symbolic reasoning concerning logical reasoning, physical principles, geometric analysis, etc. We discuss several optimization techniques for IL and verify their effectiveness in five distinct robot autonomy tasks including path planning, rule induction, optimal control, visual odometry, and multi-robot routing. Through various experiments, we show that IL can significantly enhance robot autonomy capabilities and we anticipate that it will catalyze further research across diverse domains.
Zitieren
APA
Wang, C., Ji, K., Geng, J., Ren, Z., Fu, T., Yang, F., Guo, Y., He, H., Chen, X., Zhan, Z., Du, Q., Su, S., Li, B., Qiu, Y., Du, Y., Li, Q., Yang, Y., Lin, X., & Zhao, Z. (2025). Imperative learning: A self-supervised neuro-symbolic learning framework for robot autonomy. The International Journal of Robotics Research. https://doi.org/10.1177/02783649251353181
Vancouver
Wang C, Ji K, Geng J, Ren Z, Fu T, Yang F, et al. Imperative learning: A self-supervised neuro-symbolic learning framework for robot autonomy. The International Journal of Robotics Research. 2025. doi:10.1177/02783649251353181
BibTeX
@article{Wang2025,
author = {Wang, Chen and Ji, Kaiyi and Geng, Junyi and Ren, Zhongqiang and Fu, Taimeng and Yang, Fan and Guo, Yifan and He, Haonan and Chen, Xiangyu and Zhan, Zitong and Du, Qiwei and Su, Shaoshu and Li, Bowen and Qiu, Yuheng and Du, Yi and Li, Qihang and Yang, Yifan and Lin, Xiao and Zhao, Zhipeng},
title = {Imperative learning: A self-supervised neuro-symbolic learning framework for robot autonomy},
journal = {The International Journal of Robotics Research},
year = {2025},
doi = {10.1177/02783649251353181}
}
EUVIMED