Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
131 tokens/sec
GPT-4o
10 tokens/sec
Gemini 2.5 Pro Pro
47 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

BTGenBot: Behavior Tree Generation for Robotic Tasks with Lightweight LLMs (2403.12761v2)

Published 19 Mar 2024 in cs.RO

Abstract: This paper presents a novel approach to generating behavior trees for robots using lightweight LLMs with a maximum of 7 billion parameters. The study demonstrates that it is possible to achieve satisfying results with compact LLMs when fine-tuned on a specific dataset. The key contributions of this research include the creation of a fine-tuning dataset based on existing behavior trees using GPT-3.5 and a comprehensive comparison of multiple LLMs (namely llama2, llama-chat, and code-llama) across nine distinct tasks. To be thorough, we evaluated the generated behavior trees using static syntactical analysis, a validation system, a simulated environment, and a real robot. Furthermore, this work opens the possibility of deploying such solutions directly on the robot, enhancing its practical applicability. Findings from this study demonstrate the potential of LLMs with a limited number of parameters in generating effective and efficient robot behaviors.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (22)
  1. Gpt-4 technical report. arXiv preprint arXiv:2303.08774, 2023.
  2. Sparks of artificial general intelligence: Early experiments with gpt-4. arXiv preprint arXiv:2303.12712, 2023.
  3. Languages for specifying missions of robotic applications. Software Engineering for Robotics, pages 377–411, 2021.
  4. Behavior trees and state machines in robotics applications. IEEE Transactions on Software Engineering, 49(9):4243–4267, 2023.
  5. Open-vocabulary object detection via vision and language knowledge distillation. arXiv preprint arXiv:2104.13921, 2021.
  6. Recent trends in task and motion planning for robotics: A survey. ACM Computing Surveys, 2023.
  7. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685, 2021.
  8. A survey of behavior trees in robotics and ai. Robotics and Autonomous Systems, 154:104096, 2022.
  9. Mdetr-modulated detection for end-to-end multi-modal understanding. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 1780–1790, 2021.
  10. Code as policies: Language model programs for embodied control. In 2023 IEEE International Conference on Robotics and Automation (ICRA), pages 9493–9500. IEEE, 2023.
  11. Llm-brain: Ai-driven fast generation of robot behaviour tree based on large language model. arXiv preprint arXiv:2305.19352, 2023.
  12. The marathon 2: A navigation system. In 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 2718–2725. IEEE, 2020.
  13. Behavior trees in robot control systems. Annual Review of Control, Robotics, and Autonomous Systems, 5:81–107, 2022.
  14. Empirical analysis of the strengths and weaknesses of peft techniques for llms. arXiv preprint arXiv:2304.14999, 2023.
  15. Code llama: Open foundation models for code. arXiv preprint arXiv:2308.12950, 2023.
  16. Progprompt: Generating situated robot task plans using large language models. In 2023 IEEE International Conference on Robotics and Automation (ICRA), pages 11523–11530. IEEE, 2023.
  17. Alpaca: A strong, replicable instruction-following model. Stanford Center for Research on Foundation Models. https://crfm. stanford. edu/2023/03/13/alpaca. html, 3(6):7, 2023.
  18. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288, 2023.
  19. Attention is all you need. Advances in neural information processing systems, 30, 2017.
  20. Eric Wang. Alpaca-lora. https://github.com/tloen/alpaca-lora, 2023.
  21. A survey of large language models. arXiv preprint arXiv:2303.18223, 2023.
  22. A comprehensive survey on pretrained foundation models: A history from bert to chatgpt. arXiv preprint arXiv:2302.09419, 2023.
Citations (5)

Summary

We haven't generated a summary for this paper yet.