Are transformers truly foundational for robotics?
Abstract Generative Pre-Trained Transformers (GPTs) are hyped to revolutionize robotics. Here we question their utility. GPTs for autonomous robotics demand enormous and costly compute, excessive training times and (often) offboard wireless control. We contrast GPT state of the art with how tiny insect brains have achieved robust autonomy with none of these constraints. We highlight lessons that can be learned from biology to enhance the utility of GPTs in robotics.
Authors
- James A. R. Marshall (ORCID: https://orcid.org/0000-0002-1506-167X)
- Andrew B. Barron (ORCID: https://orcid.org/0000-0002-8135-6628)
Institutions
- Materials Technologies (United States) (US)
- Sheffield Hallam University (GB)
- University of Sheffield (GB)
- Macquarie University (AU)
Publication Details
- Journal
- npj Robotics
- Published
- 2025-05-06
- DOI
- https://doi.org/10.1038/s44182-025-00025-4
- Citations
- 3
- Primary Topic
- Advanced Memory and Neural Computing
- Type
- article
- Field-Weighted Citation Impact
- 2.19
Funders
- National Science Foundation
- University of Sheffield
- Australian Research Council