Long-term human-robot interaction requires the continuous acquisition of knowledge. This ability is referred to as lifelong learning (LL). LL is a long-standing challenge in machine learning due to catastrophic forgetting, which states that continuously learning from novel experiences leads to a decrease in the performance of previously acquired knowledge. Two recently published LL approaches are the Growing Dual-Memory (GDM) and the Self-organizing Incremental Neural Network+ (SOINN+). Both are growing neural networks that create new neurons in response to novel sensory experiences. The latter approach shows state-of-the-art clustering performance on sequentially available data with low memory requirements regarding the number of nodes. However, classification capabilities are not investigated. Two novel contributions are made in our research paper: (I) An extended SOINN+ approach, called associative SOINN+ (A-SOINN+), is proposed. It adopts two main properties of the GDM model to facilitate classification. (II) A new LL object recognition dataset (v-NICO-World-LL) is presented. It is recorded in a nearly photorealistic virtual environment, where a virtual humanoid robot manipulates 100 different objects belonging to ten classes. Real-world and artificially created background images, grouped into four different complexity levels, are utilized. The A-SOINN+ reaches similar state-of-the-art classification accuracy results as the best GDM architecture of this work and consists of 30 to 350 times fewer neurons, evaluated on two LL object recognition datasets, the novel v-NICO-World-LL and the well-known CORe50. Furthermore, we observe an approximately 268 times lower training time.} These reduced numbers result in lower memory and computational requirements, indicating higher suitability for autonomous social robots with low computational resources to facilitate a more efficient LL during long-term human-robot interactions.

中文翻译：

---

然后学习，现在开始学习，以及之间的每一秒：使用人形机器人进行终身学习

长期的人机交互需要不断获取知识。此功能称为终身学习（LL）。由于灾难性的遗忘，LL是机器学习中的长期挑战，它指出，不断从新颖的经验中学习会导致以前获得的知识的性能下降。最近发布的两种LL方法是“增长双存储（GDM）”和“自组织增量神经网络+（SOINN +）”。两者都是正在发展的神经网络，它们会根据新的感觉体验创建新的神经元。后一种方法显示了对顺序可用数据的最新群集性能，而有关节点数量的内存需求较低。但是，没有研究分类能力。我们的研究论文有两个新的贡献：（I）提出了一种扩展的SOINN +方法，称为关联SOINN +（A-SOINN +）。它采用GDM模型的两个主要属性来促进分类。（II）提出了一个新的LL对象识别数据集（v-NICO-World-LL）。它被记录在接近真实感的虚拟环境中，其中虚拟的类人动物机器人操纵着属于十个类别的100个不同的对象。利用真实世界和人工创建的背景图像，这些图像分为四个不同的复杂度级别。A-SOINN +具有与这项研究中最好的GDM架构相似的最新分类精度结果，并且由两个LL对象识别数据集（新颖的v-NICO-World- LL和著名的CORe50。此外，