论文标题
将对称性集成到可区分的计划中
Integrating Symmetry into Differentiable Planning with Steerable Convolutions
论文作者
论文摘要
我们研究了在决策任务中出现对称性时，群体对称如何有助于提高端到端可区分计划算法的数据效率和概括。由均值卷积网络激励，我们将路径计划问题视为\ textit {信号}。我们表明，在这种情况下，价值迭代是线性模棱两可的运算符，这是（可检修的）卷积。这扩展了使用卷积网络进行路径计划的价值迭代网络（VIN），并具有额外的旋转和反射对称性。我们的实现基于VIN，并使用可进入的卷积网络来合并对称性。实验是在四个任务上进行的：2D导航，视觉导航和2度的自由度（2DOF）配置空间和工作空间操作。与非等价式的VIN和GPPN相比，我们的对称计划算法提高了较大边缘的训练效率和概括。
We study how group symmetry helps improve data efficiency and generalization for end-to-end differentiable planning algorithms when symmetry appears in decision-making tasks. Motivated by equivariant convolution networks, we treat the path planning problem as \textit{signals} over grids. We show that value iteration in this case is a linear equivariant operator, which is a (steerable) convolution. This extends Value Iteration Networks (VINs) on using convolutional networks for path planning with additional rotation and reflection symmetry. Our implementation is based on VINs and uses steerable convolution networks to incorporate symmetry. The experiments are performed on four tasks: 2D navigation, visual navigation, and 2 degrees of freedom (2DOFs) configuration space and workspace manipulation. Our symmetric planning algorithms improve training efficiency and generalization by large margins compared to non-equivariant counterparts, VIN and GPPN.
