A semantically-informed multirobot system for exploration of relevant areas in search and rescue settings

Abstract

Coordinated multirobot exploration involves autonomous discovering and mapping of the features of initially unknown environments by using multiple robots. Autonomously exploring mobile robots are usually driven, both in selecting locations to visit and in assigning them to robots, by knowledge of the already explored portions of the environment, often represented in a metric map. In the literature, some works addressed the use of semantic knowledge in exploration, which, embedded in a semantic map, associates spatial concepts (like 'rooms' and 'corridors') with metric entities, showing its effectiveness in improving the total area explored by robots. In this paper, we build on these results and propose a system that exploits semantic information to push robots to explore relevant areas of initially unknown environments, according to a priori information provided by human users. Discovery of relevant areas is significant in some search and rescue settings, in which human rescuers can instruct robots to search for victims in specific areas, for example in cubicles if a disaster happened in an office building during working hours. We propose to speed up the exploration of specific areas by using semantic information both to select locations to visit and to determine the number of robots to allocate to those locations. In this way, for exam-B Alberto Quattrini Li ple, more robots could be assigned to a candidate location in a corridor, so the attached rooms can be explored faster. We tested our semantic-based multirobot exploration system within a reliable robot simulator and we evaluated its performance in realistic search and rescue indoor settings with respect to state-of-the-art approaches.

[Retracted] Control System of Fire Rescue Robot for High‐Rise Building Design

“…By adjusting the position, the robot approaches the attic, locates the exact location of the trapped person, and rescues them through the emergency shelter. In the whole process, it is necessary to keep the balance of the main body of the robot in the air [16,17].…”

Decision-making of Emergent Incident based on P-MADDPG

“…When there is an emergency, in order to maximize the completion of the original task, the optimal decisions have to be compromised. In recent years, unmanned system can complete difficult tasks such as search and rescue [1], [2], [3], space underwater detection [4], surveillance and target tracking [5], [6], transmission and communication in complex environment, and has the characteristics of autonomy, flexibility, low operation cost, good availability, more safety and efficiency, while systems modeled in multi-agents have become a research hotspot in various fields. By the recent reports and surveys, the unmanned system such as robots or UAVs have shown significant potential of reducing the cost and time needed for dynamic scheduling [7].…”

Predicting the global structure of indoor environments: A constructive machine learning approach

“…The use of semantic knowledge has been shown to improve the performance of autonomous robots executing Matteo Luperto and Francesco Amigoni are with the Artificial Intelligence and Robotics Laboratory, Politecnico di Milano, Piazza Leonardo da Vinci 32, 20133 Milano, Italy {matteo.luperto,francesco.amigoni}@polimi.it tasks such as exploration and search (Quattrini Li et al, 2016;Stachniss et al, 2006). The semantic knowledge regarding indoor environments takes usually the form of a semantic map that associates semantic labels to spatial portions of environments (Hemachandra et al, 2014;Mozos et al, 2005;Pronobis et al, 2010).…”

“…Oßwald et al (2016) show how knowing a rough topo-metric graph of the environment improves the exploration performance in an otherwise unknown environment. In (Quattrini Li et al, 2016) a correct prediction of the labeling of the unexplored parts of an environment is shown to improve the exploration performance of a team of robots.…”