论文标题
潜在空间坐标的初始化通过随机线性投影来学习机器人感觉运动序列
Initialization of Latent Space Coordinates via Random Linear Projections for Learning Robotic Sensory-Motor Sequences
论文作者
论文摘要
机器人运动学数据尽管是一个高维过程，但仍高度相关，尤其是在考虑某些原语中分组的动作时。这些基本中的这些几乎线性相关性使我们能够将动作解释为在所有动作空间中靠近低维线性子空间的点。由嵌入理论的结果，尤其是惠特尼嵌入定理的概括的动机，我们表明，将运动序列的随机线性投射到低维空间中，几乎没有关于运动学数据结构的信息。对于机器人感官行为原始人的生成模型中的潜在变量值，投影点是非常好的初始猜测。我们进行了一系列实验，在其中训练了一个复发性神经网络，以生成具有9个自由度的机器人操作器的感觉运动序列。实验结果表明，在潜在变量初始化潜在变量的情况下，具有随机的电动机数据的随机线性投影而不是零或随机值的初始化。此外，潜在空间是结构良好的，其中属于不同原语的样本与训练过程的开始很好地分开。
Robot kinematics data, despite being a high dimensional process, is highly correlated, especially when considering motions grouped in certain primitives. These almost linear correlations within primitives allow us to interpret the motions as points drawn close to a union of low-dimensional linear subspaces in the space of all motions. Motivated by results of embedding theory, in particular, generalizations of Whitney embedding theorem, we show that random linear projection of motor sequences into low dimensional space loses very little information about structure of kinematics data. Projected points are very good initial guess for values of latent variables in generative model for robot sensory-motor behaviour primitives. We conducted series of experiments where we trained a recurrent neural network to generate sensory-motor sequences for robotic manipulator with 9 degrees of freedom. Experimental results demonstrate substantial improvement in generalisation abilities for unobserved samples in the case of initialization of latent variables with random linear projection of motor data over initialization with zero or random values. Moreover, latent space is well-structured wherein samples belonging to different primitives are well separated from the onset of training process.
