MPC-MPNet: Model-Predictive Motion Planning Networks for Fast, Near-Optimal Planning under Kinodynamic Constraints

TL;DR

This paper introduces MPC-MPNet, a scalable neural network framework that efficiently produces near-optimal kinodynamic motion plans with theoretical guarantees, outperforming existing methods in speed and quality.

Contribution

It presents a novel imitation learning-based approach combining neural networks and Model Predictive Control for fast, near-optimal kinodynamic motion planning with theoretical guarantees.

Findings

Significant reduction in computation times.

Improved path quality and success rates.

Effective planning in cluttered, underactuated environments.

Abstract

Kinodynamic Motion Planning (KMP) is to find a robot motion subject to concurrent kinematics and dynamics constraints. To date, quite a few methods solve KMP problems and those that exist struggle to find near-optimal solutions and exhibit high computational complexity as the planning space dimensionality increases. To address these challenges, we present a scalable, imitation learning-based, Model-Predictive Motion Planning Networks framework that quickly finds near-optimal path solutions with worst-case theoretical guarantees under kinodynamic constraints for practical underactuated systems. Our framework introduces two algorithms built on a neural generator, discriminator, and a parallelizable Model Predictive Controller (MPC). The generator outputs various informed states towards the given target, and the discriminator selects the best possible subset from them for the extension. The MPC locally connects the selected informed states while satisfying the given constraints leading to feasible, near-optimal solutions. We evaluate our algorithms on a range of cluttered, kinodynamically constrained, and underactuated planning problems with results indicating significant improvements in computation times, path qualities, and success rates over existing methods.