People can learn continuously a wide range of tasks without catastrophic forgetting. To mimic this functioning of continual learning, current methods mainly focus on studying a one-step supervised learning problem, e.g., image classification. They aim to retain the performance of previous image classification results when neural networks are sequentially trained on new images. In this paper, we concentrate on solving multi-step robotic tasks sequentially with the proposed architecture called state primitive learning. By projecting the original state space into a low-dimensional representation, meaningful state primitives can be generated to describe tasks. Under two kinds of different constraints on the generation of state primitives, control signals corresponding to different robotic tasks can be separately addressed only with an efficient linear regression. Experiments on several robotic manipulation tasks demonstrate the new method efficacy to learn control signals under the scenario of continual learning, delivering substantially improved performance over the other comparison methods.

人们可以连续学习各种各样的任务，而不会造成灾难性的遗忘。为了模仿这种持续学习的功能，当前的方法主要集中在研究一步监督学习问题，例如图像分类。他们的目的是在对新图像进行神经网络顺序训练时，保留先前图像分类结果的性能。在本文中，我们集中于通过提出的称为状态原始学习的体系结构依次解决多步机器人任务。通过将原始状态空间投影到低维表示中，可以生成有意义的状态基元来描述任务。在状态基元生成的两种不同约束下，只能通过有效的线性回归分别处理与不同机器人任务相对应的控制信号。在几个机器人操纵任务上进行的实验证明了该新方法在持续学习的情况下学习控制信号的功效，与其他比较方法相比，性能得到了显着改善。