Collaborative Mobile Robotics for Semantic Mapping: A Survey

Abstract

Ensuring safety in human–robot collaboration is one of the main challenges in mobile robotics today. Semantic maps are a potential solution because they provide semantic knowledge in addition to the geometric representation of the environment. They allow robots to perform their basic tasks using geometric representation, mainly localization, path planning and navigation, and additionally allow them to maintain a cognitive interpretation of the environment in order to reason and make decisions based on the context. The goal of this paper is to briefly review semantic mapping for a single mobile robot in indoor environments, and then focus on collaborative mobile semantic mapping. In both contexts, the semantic mapping process is divided into modules/tasks, and recent solutions for each module are discussed. Possible system architectures are also discussed for collaborative semantic mapping. Finally, future directions are highlighted.

Optimizing an Autonomous Robot’s Path to Increase Movement Speed

“…This is not satisfactory if symbolic and semantic knowledge are acquired incrementally or if this process is an interpretation of a metric map. Neither the occupancy grid nor the topological graph provides a good means of adding semantic knowledge [41]. Since it has a fine discretization, which is good for a rich description of structural details, the occupancy grid is not easily translated into a symbolic representation, as is necessary for a form of high-level spatial reasoning [42].…”

A Survey on Robot Semantic Navigation Systems for Indoor Environments

“…Recently, there have been several survey articles that have focused on various aspects of this field. For example, the work presented in [12] surveyed the use of reinforcement learning for autonomous driving, whereas the work discussed in [13] presented an overview of semantic mapping in mobile robotics, focusing on collaborative scenarios, where authors highlighted the importance of semantic maps in enabling robots to reason and make decisions based on the context of their environment. Additionally, the authors of [14] addressed the challenges involved in robot navigation in crowded public spaces, discussing both engineering and human factors that impede the seamless deployment of autonomous robots in such environments.…”