Local Path Optimization in The Latent Space Using Learned Distance Gradient

TL;DR

This paper introduces a neural network-based local path optimization method in the latent space for robotic motion planning, significantly reducing replanning time by predicting obstacle distances and guiding movement away from collisions.

Contribution

It presents a novel approach that trains a neural network to predict obstacle distances in latent space, enabling efficient local path optimization and faster planning in constrained robotic manipulation.

Findings

Achieves faster planning speed compared to state-of-the-art algorithms.

Reduces the need for extensive path validity checks and replanning.

Effectively guides robot away from obstacles using learned distance gradients.

Abstract

Constrained motion planning is a common but challenging problem in robotic manipulation. In recent years, data-driven constrained motion planning algorithms have shown impressive planning speed and success rate. Among them, the latent motion method based on manifold approximation is the most efficient planning algorithm. Due to errors in manifold approximation and the difficulty in accurately identifying collision conflicts within the latent space, time-consuming path validity checks and path replanning are required. In this paper, we propose a method that trains a neural network to predict the minimum distance between the robot and obstacles using latent vectors as inputs. The learned distance gradient is then used to calculate the direction of movement in the latent space to move the robot away from obstacles. Based on this, a local path optimization algorithm in the latent space is proposed, and it is integrated with the path validity checking process to reduce the time of replanning. The proposed method is compared with state-of-the-art algorithms in multiple planning scenarios, demonstrating the fastest planning speed