Design and Evaluation of an Assisted Programming Interface for Behavior Trees in Robotics

2026-02-10

AI Summary

This work proposes BETR-GUI, a novel graphical drag-and-drop behavior tree editor that integrates multiple AI-assisted techniques—including large language models, automated planning, genetic programming, and Bayesian optimization—to lower the barrier for non-expert users developing reactive robotic programs. The system enables users to validate, modify, and optimize automatically generated behavior trees within an intuitive interface. In a user study involving 60 participants, those using the full BETR-GUI system demonstrated significantly higher task completion rates and programming efficiency compared to a control group relying solely on an AI assistant, thereby demonstrating the system’s effectiveness and practical utility in real-world programming scenarios.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Intelligent Robots: Behavior Learning & Control
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

The possibility to create reactive robot programs faster without the need for extensively trained programmers is becoming increasingly important. So far, it has not been explored how various techniques for creating Behavior Tree (BT) program representations could be combined with complete graphical user interfaces (GUIs) to allow a human user to validate and edit trees suggested by automated methods. In this paper, we introduce BEhavior TRee GUI (BETR-GUI) for creating BTs with the help of an AI assistant that combines methods using large language models, planning, genetic programming, and Bayesian optimization with a drag-and-drop editor. A user study with 60 participants shows that by combining different assistive methods, BETR-GUI enables users to perform better at solving the robot programming tasks. The results also show that humans using the full variant of BETR-GUI perform better than the AI assistant running on its own.

Problem

• Behavior Trees
• Robot Programming
• Graphical User Interface
• AI-assisted Programming
• Human-AI Collaboration

Innovation

• Behavior Trees
• AI-assisted programming
• Graphical User Interface
• Large Language Models
• Human-AI collaboration