Multi-Modal Motion Planning Using Composite Pose Graph Optimization

TL;DR

This paper introduces a novel multi-modal motion planning framework using composite pose graph optimization, enabling efficient trajectory and mode transition optimization for vehicles with diverse dynamics.

Contribution

It formulates multi-modal motion planning as a composite pose graph problem, leveraging sparse graph optimization techniques for efficient trajectory and mode transition planning.

Findings

Effective multi-modal trajectory optimization demonstrated in simulation.

Real-world experiments validate the approach for different vehicle dynamics.

The method reduces unnecessary mode transitions and improves planning efficiency.

Abstract

In this paper, we present a motion planning framework for multi-modal vehicle dynamics. Our proposed algorithm employs transcription of the optimization objective function, vehicle dynamics, and state and control constraints into sparse factor graphs, which -- combined with mode transition constraints -- constitute a composite pose graph. By formulating the multi-modal motion planning problem in composite pose graph form, we enable utilization of efficient techniques for optimization on sparse graphs, such as those widely applied in dual estimation problems, e.g., simultaneous localization and mapping (SLAM). The resulting motion planning algorithm optimizes the multi-modal trajectory, including the location of mode transitions, and is guided by the pose graph optimization process to eliminate unnecessary transitions, enabling efficient discovery of optimized mode sequences from rough initial guesses. We demonstrate multi-modal trajectory optimization in both simulation and real-world experiments for vehicles with various dynamics models, such as an airplane with taxi and flight modes, and a vertical take-off and landing (VTOL) fixed-wing aircraft that transitions between hover and horizontal flight modes.