Planning under Uncertainty to Goal Distributions

TL;DR

This paper introduces a novel framework for planning under uncertainty by using goal probability distributions, addressing limitations of deterministic goal sets in robotics applications involving noisy sensors and learned models.

Contribution

It formalizes planning to goal distributions as an instance of planning as inference and demonstrates its advantages over traditional methods.

Findings

Flexible goal representation with probability distributions.

Effective in diverse robotics tasks including navigation and manipulation.

Reduces to common planning objectives as special cases.

Abstract

Goals for planning problems are typically conceived of as subsets of the state space. However, for many practical planning problems in robotics, we expect the robot to predict goals, e.g. from noisy sensors or by generalizing learned models to novel contexts. In these cases, sets with uncertainty naturally extend to probability distributions. While a few works have used probability distributions as goals for planning, surprisingly no systematic treatment of planning to goal distributions exists in the literature. This article serves to fill that gap. We argue that goal distributions are a more appropriate goal representation than deterministic sets for many robotics applications. We present a novel approach to planning under uncertainty to goal distributions, which we use to highlight several advantages of the goal distribution formulation. We build on previous results in the literature by formally framing our approach as an instance of planning as inference. We additionally derive reductions of several common planning objectives as special cases of our probabilistic planning framework. Our experiments demonstrate the flexibility of probability distributions as a goal representation on a variety of problems including planar navigation among obstacles, intercepting a moving target, rolling a ball to a target location, and a 7-DOF robot arm reaching to grasp an object.