テスト駆動型エージェントフレームワークによる信頼性の高いロボットコントローラの合成
Test-Driven Agentic Framework for Reliable Robot Controller
2Dマップや3Dシミュレーション環境で、テスト駆動のエージェントフレームワークを用いて低レベルナビゲーションコントローラのコードを反復的に改良し、信頼性と堅牢性を向上させる手法を提案した。
著者: Shivanshu Tripathi, Reza Akbarian Bafghi, Maziar Raissi
分類: cs.RO, cs.SY, eess.SY
原文アブストラクト
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.