3D Reactive Control and Frontier-Based Exploration for Unstructured Environments

TL;DR

This paper introduces a two-layer planning system for long-range robotic exploration in cluttered environments, combining map data and depth sensor info to maximize exploration efficiency and obstacle avoidance.

Contribution

It presents a novel integrated planning architecture that uses frontier-based sampling, fast cost-to-go calculations, and depth-based obstacle avoidance for robust exploration.

Findings

Successful deployment in complex warehouse environments

Robust exploration with onboard sensing and computation

Enhanced obstacle avoidance in unstructured scenes

Abstract

The paper proposes a reliable and robust planning solution to the long range robotic navigation problem in extremely cluttered environments. A two-layer planning architecture is proposed that leverages both the environment map and the direct depth sensor information to ensure maximal information gain out of the onboard sensors. A frontier-based pose sampling technique is used with a fast marching cost-to-go calculation to select a goal pose and plan a path to maximize robot exploration rate. An artificial potential function approach, relying on direct depth measurements, enables the robot to follow the path while simultaneously avoiding small scene obstacles that are not captured in the map due to mapping and localization uncertainties. We demonstrate the feasibility and robustness of the proposed approach through field deployments in a structurally complex warehouse using a micro-aerial vehicle (MAV) with all the sensing and computations performed onboard.