TR2026-048

Embedding Morphology into Transformers for Cross-Robot Policy Learning

    •  Suzuki, K., Liu, J., Wang, Y., Hori, C., Brand, M., Romeres, D., Koike-Akino, T., "Embedding Morphology into Transformers for Cross-Robot Policy Learning", International Conference on Learning Representations (ICLR) Workshop, April 2026.
      BibTeX TR2026-048 PDF
      • @inproceedings{Suzuki2026apr,
      • author = {Suzuki, Kei and Liu, Jing and Wang, Ye and Hori, Chiori and Brand, Matthew and Romeres, Diego and Koike-Akino, Toshiaki},
      • title = {{Embedding Morphology into Transformers for Cross-Robot Policy Learning}},
      • booktitle = {International Conference on Learning Representations (ICLR) Workshop},
      • year = 2026,
      • month = apr,
      • url = {https://www.merl.com/publications/TR2026-048}
      • }
  • MERL Contacts:
  • Research Areas:

    Artificial Intelligence, Machine Learning

Abstract:

Transformer-based VLA policies have advanced rapidly as training data scales, yet cross-robot policy learning—training a single policy across multiple embodiments—remains challenging. Such policies are often embodimentagnostic and must infer kinematics from observations, which can hurt robustness. We propose an embodiment-aware transformer that injects morphology via: (1) kinematic tokens with per-joint temporal chunking; (2) topology-aware attention bias to encourage message passing along kinematic edges; and (3) joint-attribute conditioning using per-joint descriptors.
Across multiple embodiments, our method consistently outperforms the vanilla (pi)0.5 baseline.

 

  • Related Publication

  •  Suzuki, K., Liu, J., Wang, Y., Hori, C., Brand, M., Romeres, D., Koike-Akino, T., "Embedding Morphology into Transformers for Cross-Robot Policy Learning", arXiv, February 2026.
    BibTeX arXiv
    • @article{Suzuki2026feb,
    • author = {{Suzuki, Kei and Liu, Jing and Wang, Ye and Hori, Chiori and Brand, Matthew and Romeres, Diego and Koike-Akino, Toshiaki}},
    • title = {{Embedding Morphology into Transformers for Cross-Robot Policy Learning}},
    • journal = {arXiv},
    • year = 2026,
    • month = feb,
    • url = {https://arxiv.org/abs/2603.00182}
    • }