Robotic Exploration through Semantic Topometric Mapping

TL;DR

A novel strategy for robotic exploration in unknown environments using a semantic topometric map that leads to faster exploration and requires less computation time, and the findings indicate that the proposed approach leads to faster exploration and requires less computation time.

Abstract

In this article, we introduce a novel strategy for robotic exploration in unknown environments using a semantic topometric map. As it will be presented, the semantic topometric map is generated by segmenting the grid map of the currently explored parts of the environment into regions, such as intersections, pathways, dead-ends, and unexplored frontiers, which constitute the structural semantics of an environment. The proposed exploration strategy leverages metric information of the frontier, such as distance and angle to the frontier, similar to existing frameworks, with the key difference being the additional utilization of structural semantic information, such as properties of the intersections leading to frontiers. The algorithm for generating semantic topometric mapping utilized by the proposed method is lightweight, resulting in the method's online execution being both rapid and computationally efficient. Moreover, the proposed framework can be applied to both structured and unstructured indoor and outdoor environments, which enhances the versatility of the proposed exploration algorithm. We validate our exploration strategy and demonstrate the utility of structural semantics in exploration in two complex indoor environments by utilizing a Turtlebot3 as the robotic agent. Compared to traditional frontier-based methods, our findings indicate that the proposed approach leads to faster exploration and requires less computation time.

Figures (12)

• Figure 1: An illustration of the steps taken by the proposed method to explore an unknown environment. The proposed method processes the occupancy map of the currently explored environment (Fig. 1a)), to find the optimal goal location for further exploration (Fig. 1d)), the path to which is smoothly tracked by the robot using modified potential fields (Fig. 1e)).
• Figure 2: An example of a semantic topological map produced by the method in fredriksson2023semantic.
• Figure 3: Illustration of a path leading to a frontier in a semantic topometric map, highlighted in blue, for a specific scenario. The figure also shows the different semantic entities used in the optimal selection process presented in Section \ref{['sec:goalSel']}. The intersection connected to the target frontier has four openings, and only one of its pathways leads directly to a frontier.
• Figure 4: Illustration of the goal selection for point $G$ on the path represented as a blue line. The area detectable by the LiDAR, up to a range of $f_l* L_{\text{min}}$ for different values of $f_l$ ($f_{l1}$, $f_{l2}$ and $f_{l3}$), is marked by dotted lines.
• Figure 5: The two test environments used in the validation and testing.