用测试驱动迭代优化机器人控制器，提升导航可靠性。
Test-Driven Agentic Framework for Reliable Robot Controller
- 通过测试反馈循环修正代码，分两层修复：提示优化与直接编码修改。
- 在2D和3D环境中测试，初始提示不完整时性能提升显著。
- 适合需要高可靠性的机器人控制开发人员参考。
本文提出一种测试驱动的智能体框架，用于生成可部署的低层机器人导航控制器。给定二维地图或基于超声波传感器的机器人图像，或三维机器人仿真环境（Webots），该框架通过结构化测试套件提供的诊断反馈，迭代优化生成的控制器代码，以实现任务成功。我们设计了双层修复策略，交替进行提示层面的优化与直接代码编辑。在二维导航任务和Webots模拟器中的三维导航任务上进行了评估。实验结果表明，与一次性生成控制器相比，测试驱动合成显著提升了控制器的可靠性和鲁棒性，尤其是在初始提示信息不足的情况下。源代码与演示视频已公开于：https://shivanshutripath.github.io/robotic_controller.github.io。
原文摘要 · Abstract (English)
In this work, we present a test-driven, agentic framework for synthesizing a deployable low-level robot controller for navigation tasks. Given a 2D map with an image of an ultrasonic sensor-based robot, or a 3D robotic simulation environment, our framework iteratively refines the generated controller code using diagnostic feedback from structured test suites to achieve task success. We propose a dual-tier repair strategy to refine the generated code that alternates between prompt-level refinement and direct code editing. We evaluate the approach across 2D navigation tasks and 3D navigation in the Webots simulator. Experimental results show that test-driven synthesis substantially improves controller reliability and robustness over one-shot controller generation, especially when the initial prompt is underspecified. The source code and demonstration videos are available at: https://shivanshutripath.github.io/robotic_controller.github.io.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。