Abstract
In this paper, we present a navigation strategy exclusively designed for social robots with limited sensors for applications in homes. The overall system integrates a reactive design based on subsumption architecture and a knowledge system with learning capabilities. The component of the system includes several modules, such as doorway detection and room localization via convolutional neural network (CNN), avoiding obstacles via reinforcement learning, passing the doorway via Canny edge’s detection, building an abstract map called a Directional Semantic Topological Map (DST-Map) within the knowledge system, and other predefined layers within the subsumption architecture. The individual modules and the overall system are evaluated in a virtual environment using Webots simulator.
Highlights
Social robots are referred to as a special family of autonomous and intelligent robots that are predominantly designed to interact and communicate with humans or other robots within a collaborative environment
The rest of the paper is organized as follows: in Section 2, we present related studies of performing exploration and Sequential Localization and Mapping (SeqLAM) with a focus on reactive systems integrated with knowledge systems
In contrast to the aforementioned studies, we focus on designing a robotic exploration system that integrates learning and knowledge capability to a reactive system for social robots with limited sensors
Summary
Social robots are referred to as a special family of autonomous and intelligent robots that are predominantly designed to interact and communicate with humans or other robots (agents) within a collaborative environment. Consider a scenario whereby a social robot is required to safely explore and learn in a new environment; in the context of this study, a new apartment. In robotics literature, this task is broadly referred to as robotics exploration, which includes wandering in an unknown environment with the purpose of gaining information of that environment (building a map) using mainly exteroceptive sensors. Several probabilistic techniques have been employed in a SLAM algorithm, including but not limited to, Kalman Filter (KF), Particle Filter (PF), or Expectation-Maximization (EM) [14,15]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
