Robotics perception

Language-controlled robots at the edge

Running large language models on-device so people can command mobile robots and robotic arms in plain language.

Cloud-hosted language models add latency and connectivity requirements that robots in the field cannot always meet. This work evaluates natural-language and large-language-model techniques for controlling mobile robots and robotic arms directly on edge hardware.

Publication

P. Sikorski, L. Schrader, K. Yu, L. Billadeau, J. Meenakshi, N. Mutharasan, F. Esposito, H. Ali Akbarpour, and M. Babaiasl. Deployment of Large Language Models to Control Mobile Robots at the Edge. International Conference on Mechatronics, Control and Robotics (ICMCR), 2025. Paper

Collaborators

  • Dr. Flavio Esposito (Computer Science
  • SLU)
  • Dr. Madi Babaiasl (Aerospace and Mechanical Engineering
  • SLU)