Autonomous robotic nanofabrication with reinforcement learning
Autonomous robotic nanofabrication with reinforcement learning
复制标题
DOI：
10.1126/sciadv.abb6987
复制
发表时间：
2020-09-01
期刊：
影响因子：
13.6
通讯作者：
Tautz, F. Stefan
中科院分区：
文献类型：
--
作者：
Leinen, Philipp;Esders, Malte;Tautz, F. Stefan
能够像处理宏观积木一样有效地处理单个分子的能力，将使复杂的超分子结构的构建成为可能，而这种结构是自组装所无法达到的。阻碍这一目标的根本挑战是原子尺度构象的不受控制的可变性和差的可观测性。在这里，我们提出了一种策略，以解决这两个障碍，并通过操纵单分子展示自主机器人纳米纤维。我们的方法使用强化学习（RL），即使面对大的不确定性和稀疏的反馈，也能找到解决方案。我们展示了我们的RL方法的潜力，通过从超分子结构中自动去除分子与扫描探针显微镜。我们的RL代理达到了出色的性能，使我们能够自动执行以前必须由人类执行的任务。我们预计，我们的工作开辟了自主代理的机器人构建功能超分子结构的速度，精度和毅力超出了我们目前的能力。
The ability to handle single molecules as effectively as macroscopic building blocks would enable the construction of complex supramolecular structures inaccessible to self-assembly. The fundamental challenges obstructing this goal are the uncontrolled variability and poor observability of atomic-scale conformations. Here, we present a strategy to work around both obstacles and demonstrate autonomous robotic nanofabrication by manipulating single molecules. Our approach uses reinforcement learning (RL), which finds solution strategies even in the face of large uncertainty and sparse feedback. We demonstrate the potential of our RL approach by removing molecules autonomously with a scanning probe microscope from a supramolecular structure. Our RL agent reaches an excellent performance, enabling us to automate a task that previously had to be performed by a human. We anticipate that our work opens the way toward autonomous agents for the robotic construction of functional supramolecular structures with speed, precision, and perseverance beyond our current capabilities.