Amortized Synthesis of Constrained Configurations Using a Differentiable Surrogate
Amortized Synthesis of Constrained Configurations Using a Differentiable Surrogate
复制标题
DOI：
--
复制
发表时间：
2021-06
期刊：
影响因子：
--
通讯作者：
Xingyuan Sun;Tianju Xue;S. Rusinkiewicz;Ryan P. Adams
中科院分区：
文献类型：
--
作者：
Xingyuan Sun;Tianju Xue;S. Rusinkiewicz;Ryan P. Adams
在设计、制造和控制问题中，我们经常面临综合的任务，在这个任务中，我们必须生成一个满足一组约束的对象或构形，同时最大化一个或多个目标函数。综合问题的典型特征是一个物理过程，在这个过程中，许多不同的实现可以实现目标。这种多对一映射对前馈综合的监督学习提出了挑战，因为可行的设计集可能具有复杂的结构。此外，许多物理模拟的不可微性阻碍了有效的直接优化。我们用两级神经网络体系结构来解决这两个问题，我们可以认为它是一个自动编码器。我们首先学习解码器：一个近似多对一物理实现过程的可微代理。然后我们学习编码器，它从目标映射到设计，同时使用固定的解码器来评估实现的质量。我们通过两个实例对该方法进行了评估：加法制造中的挤出机路径规划和受限软机器人逆运动学。我们比较了我们的方法，使用学习的代理直接优化设计，并监督学习的综合问题。我们发现，我们的方法产生了比监督学习更高质量的解，同时在质量上与直接优化相比具有竞争力，并且大大减少了计算成本。
In design, fabrication, and control problems, we are often faced with the task of synthesis, in which we must generate an object or configuration that satisfies a set of constraints while maximizing one or more objective functions. The synthesis problem is typically characterized by a physical process in which many different realizations may achieve the goal. This many-to-one map presents challenges to the supervised learning of feed-forward synthesis, as the set of viable designs may have a complex structure. In addition, the non-differentiable nature of many physical simulations prevents efficient direct optimization. We address both of these problems with a two-stage neural network architecture that we may consider to be an autoencoder. We first learn the decoder: a differentiable surrogate that approximates the many-to-one physical realization process. We then learn the encoder, which maps from goal to design, while using the fixed decoder to evaluate the quality of the realization. We evaluate the approach on two case studies: extruder path planning in additive manufacturing and constrained soft robot inverse kinematics. We compare our approach to direct optimization of the design using the learned surrogate, and to supervised learning of the synthesis problem. We find that our approach produces higher quality solutions than supervised learning, while being competitive in quality with direct optimization, at a greatly reduced computational cost.