A Unified View of Algorithms for Path Planning Using Probabilistic Inference on Factor Graphs

TL;DR

This paper presents a unified probabilistic inference framework for path planning algorithms, encompassing various classical methods and enabling flexible policy distributions, demonstrated through simulations on synthetic and real-world maps.

Contribution

It introduces a comprehensive factor graph-based approach that unifies multiple path planning algorithms within a single probabilistic inference framework, including novel algorithmic variants.

Findings

Unified framework includes Sum-product, Max-product, and Dynamic programming.

New algorithmic options for smoother or sharper policies.

Validated through simulations on synthetic and real-world maps.

Abstract

Even if path planning can be solved using standard techniques from dynamic programming and control, the problem can also be approached using probabilistic inference. The algorithms that emerge using the latter framework bear some appealing characteristics that qualify the probabilistic approach as a powerful alternative to the more traditional control formulations. The idea of using estimation on stochastic models to solve control problems is not new and the inference approach considered here falls under the rubric of Active Inference (AI) and Control as Inference (CAI). In this work, we look at the specific recursions that arise from various cost functions that, although they may appear similar in scope, bear noticeable differences, at least when applied to typical path planning problems. We start by posing the path planning problem on a probabilistic factor graph, and show how the various algorithms translate into specific message composition rules. We then show how this unified approach, presented both in probability space and in log space, provides a very general framework that includes the Sum-product, the Max-product, Dynamic programming and mixed Reward/Entropy criteria-based algorithms. The framework also expands algorithmic design options for smoother or sharper policy distributions, including generalized Sum/Max-product algorithm, a Smooth Dynamic programming algorithm and modified versions of the Reward/Entropy recursions. We provide a comprehensive table of recursions and a comparison through simulations, first on a synthetic small grid with a single goal with obstacles, and then on a grid extrapolated from a real-world scene with multiple goals and a semantic map.