Learning-Based Motion Planning with Mixture Density Networks

TL;DR

This paper introduces a multimodal motion planning approach using mixture density networks that efficiently predicts multiple optimal paths, improving both speed and path quality over existing methods.

Contribution

The paper presents a novel multimodal neural network architecture for motion planning that explicitly models multiple optimal solutions, enhancing efficiency and path quality.

Findings

Outperforms state-of-the-art learning-based method MPNet

Achieves better path optimality and efficiency than IRRT* and BIT*

Effectively handles environments represented by point clouds

Abstract

The trade-off between computation time and path optimality is a key consideration in motion planning algorithms. While classical sampling based algorithms fall short of computational efficiency in high dimensional planning, learning based methods have shown great potential in achieving time efficient and optimal motion planning. The SOTA learning based motion planning algorithms utilize paths generated by sampling based methods as expert supervision data and train networks via regression techniques. However, these methods often overlook the important multimodal property of the optimal paths in the training set, making them incapable of finding good paths in some scenarios. In this paper, we propose a Multimodal Neuron Planner (MNP) based on the mixture density networks that explicitly takes into account the multimodality of the training data and simultaneously achieves time efficiency and path optimality. For environments represented by a point cloud, MNP first efficiently compresses the point cloud into a latent vector by encoding networks that are suitable for processing point clouds. We then design multimodal planning networks which enables MNP to learn and predict multiple optimal solutions. Simulation results show that our method outperforms SOTA learning based method MPNet and advanced sampling based methods IRRT* and BIT*.