SLAM-based Safe Indoor Exploration Strategy

TL;DR

This paper introduces a safe indoor exploration strategy for differential drive robots using SLAM, prioritizing obstacle avoidance and space coverage with experimental validation.

Contribution

It presents a novel exploration approach that ensures safety and efficient coverage for non-instantaneous pose adjustment robots using SLAM and sensor fusion.

Findings

Effective obstacle avoidance demonstrated in experiments

Successful exploration of unknown indoor environments

Integration of SLAM with safety-oriented path planning

Abstract

This paper suggests a 2D exploration strategy for a planar space cluttered with obstacles. Rather than using point robots capable of adjusting their position and altitude instantly, this research is tailored to classical agents with circular footprints that cannot control instantly their pose. Inhere, a self-balanced dual-wheeled differential drive system is used to explore the place. The system is equipped with linear accelerometers and angular gyroscopes, a 3D-LiDAR, and a forward-facing RGB-D camera. The system performs RTAB-SLAM using the IMU and the LiDAR, while the camera is used for loop closures. The mobile agent explores the planar space using a safe skeleton approach that places the agent as far as possible from the static obstacles. During the exploration strategy, the heading is towards any offered openings of the space. This space exploration strategy has as its highest priority the agent's safety in avoiding the obstacles followed by the exploration of undetected space. Experimental studies with a ROS-enabled mobile agent are presented indicating the path planning strategy while exploring the space.