基于视觉语言模型（VLM）主观评估的动物机器人进化模型
An evolutionary model of animats with VLM-based subjective evaluation
浏览论文内容
中文总结 AI 辅助
本研究提出将VLM主观评估融入遗传算法的框架，使虚拟软体机器人同步进化形态与运动，实验显示该方法可加快种群收敛，且VLM主观选择的结果与人类评估倾向相似。
中文摘要 AI 辅助
本研究提出了一个将视觉语言模型（Vision-Language Model，VLM）提供的主观评估融入遗传算法的适应度评估与选择过程的框架。作为进化目标，我们采用具有柔性形态与运动能力的虚拟软体机器人，并向VLM呈现代表两个个体运动状态的序列图像。选择过程基于“可爱地”“怪异地”等主观评估术语进行成对比较，这些比较结果被用作遗传算法内的选择压力，从而实现形态与运动的同步进化。实验结果表明，与随机选择相比，VLM的主观选择可加快种群收敛速度，同时产生与各评估术语对应的独特形态与运动。针对人类参与者的辅助实验进一步显示，尽管个体成对选择仅与VLM的选择部分一致，但产生的形态与运动倾向在性质上相似，且重复的人类评估会造成明显疲劳。此外，不同评估术语下出现相似进化结果的观察表明，VLM并非以纯粹字面方式应用这些术语，而是在判断时将其分解为多个内部评估标准。本研究可视化了主观语言表达映射到具身表型的进化过程，并为分析VLM主观判断的结构提供了基础框架，预期将推动基于主观评估的进化计算与人工生命研究的新发展。
英文摘要
In this study, we propose a framework that incorporates subjective evaluations provided by a Vision-Language Model (VLM) into the fitness evaluation and selection processes of a genetic algorithm. As the target of evolution, we employ virtual soft robots with flexible morphologies and locomotion and present the VLM with sequence images representing the locomotion of two individuals. Selection is performed via pairwise comparisons based on subjective evaluation terms such as adorably and weirdly. The outcomes of these comparisons are used as selection pressure within the genetic algorithm, enabling the simultaneous evolution of morphology and locomotion. Experimental results demonstrate that subjective selection by the VLM accelerates population convergence compared to random selection, while also giving rise to distinctive morphologies and motions corresponding to each evaluation term. An auxiliary experiment with human participants further showed that, although individual pairwise choices only partly agreed with the VLM selections, the resulting morphological and locomotion tendencies were qualitatively similar and repeated human evaluations imposed noticeable fatigue. Moreover, the observation that similar evolutionary outcomes emerged across different evaluation terms suggests that the VLM does not apply these terms in a purely literal manner but instead decomposes them into multiple internal evaluation criteria when making judgments. This work visualizes the evolutionary process through which subjective linguistic expressions are mapped onto embodied phenotypes and provides a foundational framework for analyzing the structure of subjective judgment in VLMs. The proposed approach is expected to contribute to new developments in evolutionary computation and artificial life research based on subjective evaluation.
发表机构
- Graduate School of Informatics, Nagoya University（名古屋大学信息学研究生院）
机构由 AI 辅助整理，请以论文原文为准。
