Learning Equality Constraints for Motion Planning on Manifolds
This addresses constrained motion planning for robots, but it appears incremental as it builds on existing methods for learning constraints.
The paper tackles the problem of learning equality constraints for robot motion planning from demonstrations using a deep neural network called ECoMaNN, which learns a level-set function for integration into a constrained sampling-based planner, and evaluates it on representation capabilities and motion production.
Constrained robot motion planning is a widely used technique to solve complex robot tasks. We consider the problem of learning representations of constraints from demonstrations with a deep neural network, which we call Equality Constraint Manifold Neural Network (ECoMaNN). The key idea is to learn a level-set function of the constraint suitable for integration into a constrained sampling-based motion planner. Learning proceeds by aligning subspaces in the network with subspaces of the data. We combine both learned constraints and analytically described constraints into the planner and use a projection-based strategy to find valid points. We evaluate ECoMaNN on its representation capabilities of constraint manifolds, the impact of its individual loss terms, and the motions produced when incorporated into a planner.