Modeling perspective-taking by forecasting 3D biological motion sequences
Modeling perspective-taking by forecasting 3D biological motion sequences
复制标题
通过预测 3D 生物运动序列来建模视角采择
DOI：
--
复制
发表时间：
2014
期刊：
影响因子：
--
通讯作者：
Martin Volker Butz
中科院分区：
文献类型：
--
作者：
Fabian Schrodt;Martin Volker Butz
镜像神经元系统（MNS）被认为与同理心和模仿等社交能力有关。虽然多个大脑区域与 MNS 相关，但镜像神经元特性本身是如何发育的仍不清楚。之前，我们介绍了一种循环神经网络，它通过学习体现的、尺度和平移不变的生物运动（BM）模型来实现镜像神经元功能。该模型允许通过 (i) 在公共位置和角度空间中分割 BM 以及 (ii) 生成后续运动的短期、自上而下的预测来推导观察到的 BM 的方向。虽然我们之前的模型生成了短期运动预测，但在这里我们引入了一种新颖的预测算法，它可以显式地预测 BM 片段的序列。我们展示了模型在人形行走的 3D 模拟上的缩放
The mirror neuron system (MNS) is believed to be involved in social abilities like empathy and imitation. While several brain regions have been linked to the MNS, it remains unclear how the mirror neuron property itself develops. Previously, we have introduced a recurrent neural network, which enables mirror-neuron capabilities by learning an embodied, scale- and translation-invariant model of biological motion (BM). The model allows the derivation of the orientation of observed BM by (i) segmenting BM in a common positional and angular space and (ii) generating short-term, top-down predictions of subsequent motion. While our previous model generated short-term motion predictions, here we introduce a novel forecasting algorithm, which explicitly predicts sequences of BM segments. We show that the model scales on a 3D simulation of a humanoid walking