Research Analyzer
← Back ICRA 2026

An Entropy-Based Hybrid Local-Global Algorithm to Navigate Information-Sparse Environments

Bennett Carley, Jason O'Kane

PDF

AI summary

Key figure (auto-extracted from paper)
An entropy-guided hybrid planner enables robust robot navigation through environments with extremely sparse and noisy sensor data.
Entropy-based planning Navigation under uncertainty Autonomous underwater vehicles Hybrid local-global planning Information gathering Particle filter localization

Problem

Robots operating in GPS-denied or feature-poor environments struggle to localize and navigate due to severe sensing noise and motion uncertainty. This paper addresses how to reliably guide a robot to a goal when distinguishing sensor information is scarce.

Approach

The method uses a particle filter to track state uncertainty and estimates sensor entropy to identify informative regions. It combines a global planner that maximizes entropy per distance with a dynamic local planner that adaptively balances information gain and goal progress.

Key results

  • A computationally efficient method for approximating Gaussian mixture entropy
  • A global path planner that maximizes expected local entropy per unit distance
  • A dynamic local planner that adaptively balances information gain and goal progress
  • Simulation results demonstrating successful navigation despite severe sensing and actuation noise

Why it matters

Enables reliable autonomous navigation for underwater vehicles and other GPS-denied platforms operating in feature-poor environments.

Abstract

We explore a navigation problem for a simple robot with extremely noisy sensing and significant movement uncertainty. We are particularly interested in environments containing large regions in which relatively little distinguishing sensor information is available to assist with localization. This paper proposes a navigation algorithm for this setting that strategically directs the robot through such regions when possible, but with a careful view of the need to regain rela- tively accurate localization at certain points in the execution. Reasoning directly about the robot’s uncertainty, the approach utilizes a local entropy metric to identify regions where sensors have strong informative value. This metric informs the selection of coarse global paths that guide a more precise local planner. We discuss an implementation of this algorithm, and provide simulation results demonstrating its effectiveness in spite of large errors in both sensing and actuation.

Index terms

Reactive and Sensor-Based Planning Planning under Uncertainty

Related papers