从视觉搜索到运动控制：人工代理的优先级场
From Visual Search to Movement Control: A Priority Field for Artificial Agents
- University of Michigan Transportation Research Institute（密歇根大学交通研究所）
- University of Michigan（密歇根大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出将优先级场扩展到人工代理的运动控制，通过视觉搜索模型和到达-回避任务验证，优先级场代理训练更高效、在复杂场景中表现更优，并产生类似人类的历史驱动效应。
AI中文摘要：
人类空间注意力被广泛概念化为由优先级图引导，该图整合了感知显著性、当前目标和过往经验。在此，我们将基于优先级的计算扩展到人工代理的运动控制中。我们首先引入了一个基于集成优先级图的轻量级视觉搜索模型。该模型在人类眼动数据上训练，重现了关键行为模式，包括眼动抑制和历史驱动的选择。扩展搜索模型后，我们为人工代理配备了优先级场，并在一个需要到达目标目的地同时避开移动障碍物的到达-回避任务中评估其性能。与替代架构相比，优先级场代理训练效率更高，并且在未见过的复杂场景中表现更好，即使仅从简单演示中学习也是如此。添加一个简单的记忆机制还产生了类似人类的、历史驱动的效果，用于预测即将到来的目标的可能位置。这些发现表明，基于优先级的计算可能为人工代理的运动控制提供有前景的基础。
英文摘要：
Human spatial attention is widely conceptualized as being guided by a priority map that integrates perceptual salience, current goals, and past experiences. Here, we extend priority-based computation to movement control in artificial agents. We first introduce a lightweight model of visual search based on an integrated priority map. Trained on human saccades, it reproduced key behavioral patterns, including oculomotor suppression and history-driven selection. Extending the search model, we equipped an artificial agent with a priority field and evaluated its performance in a reach-avoid task that required reaching a goal destination while avoiding moving obstacles. Compared with alternative architectures, priority-field agents trained more efficiently and performed better in unseen, complex scenarios, even from simple demonstrations. Adding a simple memory mechanism also produced human-like, history-driven effects in anticipating the likely location of the upcoming goal. These findings suggest that priority-based computation may provide a promising foundation for movement control in artificial agents.
