EUVIMEDEUVIMED entdecken
Crossref

Cross-robot behavior adaptation through intention alignment

Xi Chen iD, Yuan Gao iD, Hangxin Liu iD, Fangkai Yang iD, Ali Ghadirzadeh iD, Jun Yang iD, Bin Liang, Chongjie Zhang iD, Tin Lun Lam iD, Song-Chun Zhu

Science Robotics · 18.03.2026 · 11 (112)

DOI: 10.1126/scirobotics.adv2250 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Science Robotics, erschienen am 18.03.2026. Verfasst von Xi Chen und 9 weiteren Autor:innen. Beteiligte Einrichtung: State Key Laboratory of General Artificial Intelligence, Beijing Institute for General Artificial Intelligence (BIGAI), Beijing, China. Hauptthemen laut MEDLINE: Robotics, Intention. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 73 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Shenzhen Science and Technology Innovation Program, Basic and Applied Basic Research Foundation of Guangdong Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Imitation learning (IL) has succeeded in enabling robots to perform new tasks by learning from demonstrations. However, its success is often constrained by the need for direct skill mappings between a learner and a demonstrator under identical conditions, limiting its adaptability to diverse environments and generalization across robots with different physical embodiments. To address these challenges, we introduce the Intention-Aligned Imitation Learning (IAIL) framework, a behavior adaptation approach that extends the conventional scope of IL by enabling robots to reproduce motions demonstrated by heterogeneous peers, even in previously unseen situations. Inspired by human cultural learning, IAIL aligns and adapts robot motions on the basis of high-level intentions annotated in natural language rather than by directly copying motor movements. This alignment is achieved by constructing a shared intention space that connects robot-generated motions with linguistic annotations, enabling inference-time behavior adaptation across diverse embodiments and environmental contexts. The framework further supports scalable task allocation in heterogeneous robot teams by leveraging differences in capabilities and constraints. We validated IAIL through real-world experiments involving seven distinct robots performing multistep collaboration tasks across 30 scenarios. Our results demonstrate that IAIL enables robust intention-aligned behavior adaptation across variations in embodiment, motion modality, and task configuration. These capabilities enable flexible behavior transfer across heterogeneous robots and support resilient, autonomous multirobot systems for reliable real-world collaboration.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

RoboticsIntentionHumansAlgorithmsLearningIntelligent SystemsMotionArtificial IntelligenceAdaptive AlgorithmsAutonomous RobotsImitative Behavior

Autor:innen und Institutionen

  • State Key Laboratory of General Artificial Intelligence, Beijing Institute for General Artificial Intelligence (BIGAI), Beijing, China.
  • School of Science and Engineering, Chinese University of Hong Kong, Shenzhen, China.
  • Shenzhen Institute of Artificial Intelligence and Robotics for Society, Shenzhen, China.
  • School of Intelligence Science and Technology, Peking University, Beijing, China.
  • Microsoft, Beijing, China.
  • Embark Studios, Stockholm, Sweden.

ORCID-Profile: Xi Chen, Yuan Gao, Hangxin Liu, Fangkai Yang, Ali Ghadirzadeh, Jun Yang, Chongjie Zhang, Tin Lun Lam

Förderung

  • National Natural Science Foundation of China
  • Shenzhen Science and Technology Innovation Program
  • Basic and Applied Basic Research Foundation of Guangdong Province
  • National Key Research and Development Program of China

Zitieren

APA

Chen, X., Gao, Y., Liu, H., Yang, F., Ghadirzadeh, A., Yang, J., Liang, B., Zhang, C., Lam, T. L., & Zhu, S. C. (2026). Cross-robot behavior adaptation through intention alignment. Science Robotics, 11(112). https://doi.org/10.1126/scirobotics.adv2250

Vancouver

Chen X, Gao Y, Liu H, Yang F, Ghadirzadeh A, Yang J, et al. Cross-robot behavior adaptation through intention alignment. Science Robotics. 2026;11(112). doi:10.1126/scirobotics.adv2250

BibTeX
@article{Chen2026,
  author = {Chen, Xi and Gao, Yuan and Liu, Hangxin and Yang, Fangkai and Ghadirzadeh, Ali and Yang, Jun and Liang, Bin and Zhang, Chongjie and Lam, Tin Lun and Zhu, Song-Chun},
  title = {Cross-robot behavior adaptation through intention alignment},
  journal = {Science Robotics},
  year = {2026},
  volume = {11},
  number = {112},
  doi = {10.1126/scirobotics.adv2250}
}
Kostenlos starten →