[论文解读] A Model for Foraging Ants, Controlled by Spiking Neural Networks and Double Pheromones

Cristian Jimenez-Romero, David Sousa-Rodrigues+2 more|arXiv (Cornell University)|Jul 30, 2015

Advanced Memory and Neural Computing参考文献 13被引用 4

一句话总结

本文提出了一种受生物启发的觅食蚂蚁模型，采用脉冲神经网络（SNNs）实现个体决策，通过双信息素系统——正向（食物奖励）和负向（障碍物标记）——实现群体导航。SNN使蚂蚁能够学习规避有害刺激并寻找食物，而双信息素系统则通过痕迹通讯减少搜索空间，显著提升了传统蚁群优化方法的觅食效率。

ABSTRACT

A model of an Ant System where ants are controlled by a spiking neural circuit and a second order pheromone mechanism in a foraging task is presented. A neural circuit is trained for individual ants and subsequently the ants are exposed to a virtual environment where a swarm of ants performed a resource foraging task. The model comprises an associative and unsupervised learning strategy for the neural circuit of the ant. The neural circuit adapts to the environment by means of classical conditioning. The initially unknown environment includes different types of stimuli representing food and obstacles which, when they come in direct contact with the ant, elicit a reflex response in the motor neural system of the ant: moving towards or away from the source of the stimulus. The ants are released on a landscape with multiple food sources where one ant alone would have difficulty harvesting the landscape to maximum efficiency. The introduction of a double pheromone mechanism yields better results than traditional ant colony optimization strategies. Traditional ant systems include mainly a positive reinforcement pheromone. This approach uses a second pheromone that acts as a marker for forbidden paths (negative feedback). This blockade is not permanent and is controlled by the evaporation rate of the pheromones. The combined action of both pheromones acts as a collective stigmergic memory of the swarm, which reduces the search space of the problem. This paper explores how the adaptation and learning abilities observed in biologically inspired cognitive architectures is synergistically enhanced by swarm optimization strategies. The model portraits two forms of artificial intelligent behaviour: at the individual level the spiking neural network is the main controller and at the collective level the pheromone distribution is a map towards the solution emerged by the colony.

研究动机与目标

• 开发一种生物上合理的觅食蚂蚁模型，整合个体神经控制与群体信息素通信机制。
• 展示脉冲神经网络如何使蚂蚁在动态环境中自主适应并响应环境刺激（食物与障碍物）。
• 探究双信息素系统（正向与负向强化）对群体觅食效率的影响。
• 创建一个易于使用、具有教育意义的工具，结合SNN与基于代理的建模，用于复杂系统研究。

提出的方法

• 每只蚂蚁由一个通过经典条件反射训练的脉冲神经网络控制，以将感官刺激（食物 = 奖励，障碍物 = 伤害）与运动反应（靠近或避开）建立关联。
• 神经回路采用两层结构：感觉神经元检测刺激（绿色 = 食物，白色/红色 = 有害），运动神经元根据学习到的关联驱动运动。
• 实施双信息素机制：正向信息素标记通往食物的高效路径，负向信息素标记禁止或危险区域。
• 信息素蒸发速率控制负向痕迹的临时性，防止永久封锁，从而实现动态适应。
• 该模型在NetLogo中实现，使研究人员能够在虚拟2D环境中模拟和可视化蚂蚁行为、神经学习及信息素动态。
• 系统采用痕迹通讯：蚂蚁通过在环境中沉积信息素间接协调，而非直接通信。

实验结果

研究问题

• RQ1 脉冲神经网络是否能够使个体蚂蚁在动态环境中学习并自适应地响应奖励性与有害性刺激？
• RQ2 与仅使用正向信息素的传统系统相比，负向信息素机制在多大程度上提升了觅食效率？
• RQ3 个体神经学习与群体信息素通信之间的协同作用在多大程度上增强了群体在觅食任务中的问题解决能力？
• RQ4 是否可以有效在广泛使用的基于代理的建模平台（如NetLogo）中实现并可视化一个简单、生物启发的蚂蚁行为模型？

主要发现

• 脉冲神经网络成功使蚂蚁学会避开白色和红色斑块（有害刺激）并靠近绿色斑块（食物），训练过程中轨迹逐渐变长且不发生碰撞，证明了学习效果。
• 在双信息素系统激活后，蚂蚁发展出复杂、非单调的轨迹，能够定位并利用食物源，而在无信息素条件下则无法实现。
• 负向信息素通过将先前未占据区域标记为禁区，随时间逐步缩小有效搜索空间，从而提升觅食效率。
• 经过8,000轮迭代后，系统显示食物源已基本耗尽，表明资源得到了有效的集体利用。
• 随时间变化的食物可用量（图9）在信息素激活后迅速下降，证实了觅食性能的提升。
• 该模型通过结合个体学习与双反馈机制，优于传统蚁群优化策略，展现出涌现的群体智能。