论文标题
通过可区分编程不断发展的软机器人的严重损坏恢复
Severe Damage Recovery in Evolving Soft Robots through Differentiable Programming
论文作者
论文摘要
生物系统对形态损害非常健壮，但人工系统（机器人）目前却不是。在本文中，我们提出了一个基于神经细胞自动机的系统，其中运动机器人的发展，然后赋予能够通过基于梯度的训练而从损害中再生其形态的能力。因此，我们的方法结合了进化的好处，可以发现各种不同的机器人形态，并通过可区别的更新规则对鲁棒性的监督培训效率。所得的神经细胞自动机能够生长能够恢复80 \％功能的虚拟机器人，即使经过严重的形态损害。
Biological systems are very robust to morphological damage, but artificial systems (robots) are currently not. In this paper we present a system based on neural cellular automata, in which locomoting robots are evolved and then given the ability to regenerate their morphology from damage through gradient-based training. Our approach thus combines the benefits of evolution to discover a wide range of different robot morphologies, with the efficiency of supervised training for robustness through differentiable update rules. The resulting neural cellular automata are able to grow virtual robots capable of regaining more than 80\% of their functionality, even after severe types of morphological damage.
