Integrating Symmetry into Differentiable Planning

Linfeng Zhao, Xupeng Zhu, Lingzhi Kong, Robin Walters, Lawson L.S. Wong

Keywords: planning, equivariance, symmetry, reinforcement learning, model-based reinforcement learning

Abstract: We study how group symmetry helps improve data efficiency and generalization for end-to-end differentiable planning algorithms, specifically on 2D robotic path planning problems: navigation and manipulation. We first formalize the idea from Value Iteration Networks (VINs) on using convolutional networks for path planning, because it avoids explicitly constructing equivalence classes and enables end-to-end planning. We then show that value iteration can always be represented as some convolutional form for (2D) path planning, and name the resulting paradigm Symmetric Planner (SymPlan). In implementation, we use steerable convolution networks to incorporate symmetry. Our algorithms on navigation and manipulation, with given or learned maps, improve training efficiency and generalization performance by large margins over non-equivariant counterparts, VIN and GPPN.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2206.03674/code)