arXiv Open Access 2024

Are Transformers Truly Foundational for Robotics?

James A. R. Marshall Andrew B. Barron

Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

cs.RO cs.AI

Penulis (2)

James A. R. Marshall

Andrew B. Barron

Format Sitasi

APA MLA BibTeX

Marshall, J.A.R., Barron, A.B. (2024). Are Transformers Truly Foundational for Robotics?. https://arxiv.org/abs/2411.16917

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2024
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓