Dynamically Constrained Motion Planning Networks for Non-Holonomic Robots

TL;DR

This paper introduces Dynamic MPNet, a neural network-based real-time motion planning algorithm tailored for non-holonomic robots, improving efficiency and generalizability over traditional methods.

Contribution

It extends Motion Planning Networks with modifications enabling real-time planning for non-holonomic robots, enhancing data efficiency and model generalization.

Findings

Successful simulation planning for non-holonomic robots.

Real-time indoor navigation with a Dubins car.

Improved training data efficiency and model generalization.

Abstract

Reliable real-time planning for robots is essential in today's rapidly expanding automated ecosystem. In such environments, traditional methods that plan by relaxing constraints become unreliable or slow-down for kinematically constrained robots. This paper describes the algorithm Dynamic Motion Planning Networks (Dynamic MPNet), an extension to Motion Planning Networks, for non-holonomic robots that address the challenge of real-time motion planning using a neural planning approach. We propose modifications to the training and planning networks that make it possible for real-time planning while improving the data efficiency of training and trained models' generalizability. We evaluate our model in simulation for planning tasks for a non-holonomic robot. We also demonstrate experimental results for an indoor navigation task using a Dubins car.