This early-stage research work aims to improve online human-robot imitation
by translating sequences of joint positions from the domain of human motions to
a domain of motions achievable by a given robot, thus constrained by its
embodiment. Leveraging the generalization capabilities of deep learning
methods, we address this problem by proposing an encoder-decoder neural network
model performing domain-to-domain translation. In order to train such a model,
one could use pairs of associated robot and human motions. Though, such paired
data is extremely rare in practice, and tedious to collect. Therefore, we turn
towards deep learning methods for unpaired domain-to-domain translation, that
we adapt in order to perform human-robot imitation.

早期研究旨在通过将人类动作领域中的关节位置序列转化为给定机器人能够实现且受其体现约束的动作领域，从而改进在线人机模仿技术。通过提出一个编码器 - 解码器神经网络模型进行领域转换，利用深度学习方法的泛化能力来解决这个问题。为了训练这样的模型，可以使用与机器人和人类动作相关联的配对数据，然而这样的数据在实践中非常稀少且收集费时。因此，我们转向了无配对领域转换的深度学习方法，并将其改进以实现人机模仿。

无监督动作转换用于人机模仿

Unsupervised Motion Retargeting for Human-Robot Imitation

Previous work on predicting or generating 3D human pose sequences regresses
either joint rotations or joint positions. The former strategy is prone to
error accumulation along the kinematic chain, as well as discontinuities when
using Euler angles or exponential maps as parameterizations. The latter
requires re-projection onto skeleton constraints to avoid bone stretching and
invalid configurations. This work addresses both limitations. QuaterNet
represents rotations with quaternions and our loss function performs forward
kinematics on a skeleton to penalize absolute position errors instead of angle
errors. We investigate both recurrent and convolutional architectures and
evaluate on short-term prediction and long-term generation. For the latter, our
approach is qualitatively judged as realistic as recent neural strategies from
the graphics literature. Our experiments compare quaternions to Euler angles as
well as exponential maps and show that only a very short context is required to
make reliable future predictions. Finally, we show that the standard evaluation
protocol for Human3.6M produces high variance results and we propose a simple
solution.

通过使用 quaternions 表示旋转，使用前向运动学来惩罚绝对位置误差，同时比较 quaternions 和 Euler 角的性能，我们提出了一种新方法 --QuaterNet，用于预测和生成 3D 人体姿势序列。经过实验证明这种方法在短期和长期预测和生成任务中都取得了良好的效果，相比于人体图像学界最新的神经策略，我们的方法被评估为非常逼真。此外，我们还发现，Human3.6M 的标准评估协议产生了高方差结果，提出了简单的解决方案。