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

TL;DR

This paper introduces a novel path planning method for robotic manipulators that uses a generative model's latent space and gradient-based optimization to efficiently generate feasible paths with obstacle avoidance.

Contribution

It presents a new approach combining generative models and constraint satisfaction classifiers for flexible, gradient-based path planning in manipulation tasks.

Findings

Achieves comparable success rates to traditional planners

Demonstrates effective obstacle avoidance on a real robot

Maintains efficient planning times and path lengths

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.