Learning Manifolds for Sequential Motion Planning

2020/06/13 by Isabel M. Rayas Fernández, Fernández, Isabel M. Rayas, Giovanni Sutanto +7
Computer Science · Engineering · #AI-based Problem Solving and Planning #Computational Geometry (cs.CG) #FOS: Computer and information sciences #Robot Manipulation and Learning #Robotic Path Planning Algorithms #Robotics (cs.RO)

paper · pdf · doi:10.48550/arxiv.2006.07746

openalex publication_date 2020/06/13 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Motion planning with constraints is an important part of many real-world robotic systems. In this work, we study manifold learning methods to learn such constraints from data. We explore two methods for learning implicit constraint manifolds from data: Variational Autoencoders (VAE), and a new method, Equality Constraint Manifold Neural Network (ECoMaNN). With the aim of incorporating learned constraints into a sampling-based motion planning framework, we evaluate the approaches on their ability to learn representations of constraints from various datasets and on the quality of paths produced during planning.

Related

• Learning Equality Constraints for Motion Planning on Manifolds
• Physics-informed Neural Motion Planning on Constraint Manifolds
• Constrained Motion Planning Networks X
• Fast Kinodynamic Planning on the Constraint Manifold with Deep Neural Networks
• Differentiable Motion Manifold Primitives for Reactive Motion Generation under Kinodynamic Constraints