Reaching Through Latent Space: From Joint Statistics to Path Planning in Manipulation

Abstract

We present a novel approach to path planning for robotic manipulators, in which paths are produced via iterative optimisation in the latent space of a generative model of robot poses. Constraints are incorporated through the use of constraint satisfaction classifiers operating on the same space. Optimisation leverages gradients through our learned models that provide a simple way to combine goal reaching objectives with constraint satisfaction, even in the presence of otherwise non-differentiable constraints. Our models are trained in a task-agnostic manner on randomly sampled robot poses. In baseline comparisons against a number of widely used planners, we achieve commensurate performance in terms of task success, planning time and path length, performing successful path planning with obstacle avoidance on a real 7-DoF robot arm.

arXiv comment10 pages, 6 figures, 4 tables

References in corpus (11)

• Adam: A Method for Stochastic Optimization
• Auto-Encoding Variational Bayes
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• InfoVAE: Information Maximizing Variational Autoencoders
• Continuous-Time Gaussian Process Motion Planning via Probabilistic Inference
• Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images
• Batch Informed Trees (BIT*): Informed Asymptotically Optimal Anytime Search
• Neural Manipulation Planning on Constraint Manifolds
• Taming VAEs
• Robot Motion Planning in Learned Latent Spaces
• Imagine That! Leveraging Emergent Affordances for 3D Tool Synthesis

Cited by in corpus (2)

• Neural Contractive Dynamical Systems
• Toward Generalist Neural Motion Planners for Robotic Manipulators: Challenges and Opportunities