Autonomous Exploration of Unknown Indoor Environments for High-Quality Mapping Using Feature-Based RGB-D SLAM

Abstract

Simultaneous localization and mapping (SLAM) system-based indoor mapping using autonomous mobile robots in unknown environments is crucial for many applications, such as rescue scenarios, utility tunnel monitoring, and indoor 3D modeling. Researchers have proposed various strategies to obtain full coverage while minimizing exploration time; however, mapping quality factors have not been considered. In fact, mapping quality plays a pivotal role in 3D modeling, especially when using low-cost sensors in challenging indoor scenarios. This study proposes a novel exploration algorithm to simultaneously optimize exploration time and mapping quality using a low-cost RGB-D camera. Feature-based RGB-D SLAM is utilized due to its various advantages, such as low computational cost and dense real-time reconstruction ability. Subsequently, our novel exploration strategies consider the mapping quality factors of the RGB-D SLAM system. Exploration time optimization factors are also considered to set a new optimum goal. Furthermore, a Voronoi path planner is adopted for reliable, maximal obstacle clearance and fixed paths. According to the texture level, three exploration strategies are evaluated in three real-world environments. We achieve a significant enhancement in mapping quality and exploration time using our proposed exploration strategies compared to the baseline frontier-based exploration, particularly in a low-texture environment.

Multiagent robotic systems and exploration algorithms: Applications for data collection in construction sites

“…For a robot to autonomously navigate an environment, three things are needed (Wooden et al, 2010): (1) a map of the environment, (2) the ability of the robot to be able to localize itself on the map, and (3) the ability to perceive the environment. To achieve that, extensive research has already been done in the field of robotics (Eldemiry et al, 2022; Jafri & Chellali, 2013; Kim et al, 2018; Nüchter et al, 2007). The different ways to solve this issue can be categorized into three main approaches, varying in different degrees of autonomy.…”

“…| 1189 noncluttered environment. On the other hand, there are 3D-based exploration algorithms like the one proposed by Eldemiry et al (2022).…”

“…With the 2D map generated, they compute an optimal path planning for an unmanned ground robot (UGV) to stop in the predefined locations to collect 3D data. Asadi et al (2022). presented a monocular SLAM approach to creating a 2D spatial map of the scene.…”

“…The result of the process is an uncertainty map of the occupied space within the environment, which could be used for navigation purposes in a noncluttered environment. On the other hand, there are 3D‐based exploration algorithms like the one proposed by Eldemiry et al (2022). They developed an autonomous exploration approach for high‐quality mapping using feature‐based RGB‐D SLAM.…”

Search and Rescue in a Maze-like Environment with Ant and Dijkstra Algorithms

“…The use of drones as mobile and airborne sensing platforms in general [9], and with a focus on disaster response and civil defense in specific circumstances [24], has been discussed in the literature [25]. We now provide some background for Search and Rescue (SAR) operations (Section 2.1) and the use of wireless and mobile/ad hoc networks in this context (Section 2.2), and argue that drone-based wireless networks have great potential for this application domain.…”