2000 character limit reached
Interpreting and learning voice commands with a Large Language Model for a robot system (2407.21512v1)
Published 31 Jul 2024 in cs.RO, cs.CL, and cs.NE
Abstract: Robots are increasingly common in industry and daily life, such as in nursing homes where they can assist staff. A key challenge is developing intuitive interfaces for easy communication. The use of LLMs like GPT-4 has enhanced robot capabilities, allowing for real-time interaction and decision-making. This integration improves robots' adaptability and functionality. This project focuses on merging LLMs with databases to improve decision-making and enable knowledge acquisition for request interpretation problems.
- Voice in human–agent interaction: A survey. ACM Comput. Surv., 54(4), 2021. ISSN 0360-0300. 10.1145/3386867. URL https://doi.org/10.1145/3386867.
- Robots that can chat. Boston Dynamics Blog, 2023. URL https://bostondynamics.com/blog/robots-that-can-chat/. Accessed: 2024-02-04.
- Tiago: the modular robot that adapts to different research needs. 2016. URL https://api.semanticscholar.org/CorpusID:218478582.
- An intent-based approach for creating assistive robots’ control systems. CoRR, abs/2005.12106, 2020. URL https://arxiv.org/abs/2005.12106.
- Ros: an open-source robot operating system. In ICRA workshop on open source software, volume 3, page 5. Kobe, Japan, 2009.
- Winiarski, T. Meros: Sysml-based metamodel for ros-based systems. IEEE Access, 11:82802–82815, 2023. 10.1109/ACCESS.2023.3301727.
- Scheduling of a robot’s tasks with the tasker framework. IEEE Access, 8:161449–161471, 2020. 10.1109/ACCESS.2020.3020265.
- Dudek, W. Prudent management of interruptible tasks executed by a service robot. Ph.D. thesis, Warsaw University of Technology, 2021. URL https://robotyka.ia.pw.edu.pl/papers/phd_thesis_wd.pdf.
- The smach high-level executive [ros news]. IEEE Robotics & Automation Magazine, 17(4):18–20, 2010. 10.1109/MRA.2010.938836.