Abstract
This paper considers an autonomous cloud-based multi-robot system designed to execute highly repetitive tasksin a dynamic environment such as a modern megastore. Cloud level is intended for performing the most demandingoperations in order to unload the robots that are users of cloud services in this architecture. For path planningon global level D* Lite algorithm is applied, bearing in mind its high efficiency in dynamic environments. In orderto introduce smart cost map for further improvement of path planning in complex and crowded environment, implementationof fuzzy inference system and learning algorithm is proposed. The results indicate the possibility ofapplying a similar concept in different real-world robotics applications, in order to reduce the total paths length,as well as to minimize the risk in path planning related to the human-robot interactions.
Highlights
The basic purpose of an algorithm used in the robot path planning process is to determine a valid path from the start to the goal position of the robot in its configuration space
The application of Multi-criteria decision making (MCDM) using Full consistency method (FUCOM) provides an adaptive approach to path planning, in terms of optimizing the global cost map taking into account all factors affecting the robots motion in the environment and having in mind a mission specificity that requires the management of risks arising from different sources
But some processes can be underlined as specific from the aspect of the topic of this paper, as follows: _ checking the shelves and determining the percentage of their fullness with goods after the specified intervals, _ generating a notification if the shelf fullness is lower than the preset level, _ planning of engagement the available robots for goods transport from the warehouse to the store with the specification of the start and the goal positions of each robot, _ planning/replanning of robots paths, _ implementation of fuzzy inference system and learning algorithm with a purpose of improvement the path planning efficiency, _ motion coordination, _ solving a conflict situations and updating of environment map based on information collected with robots sensors
Summary
The basic purpose of an algorithm used in the robot path planning process is to determine a valid path from the start to the goal position of the robot in its configuration space. The contribution of this paper is reflected in the original application of FIS to exploit predictable changes in crowd density (in spatio-temporal domain), in order to generate smart cost map to improve autonomous robot path planning in crowded environment It is proposed a learning algorithm that has the same purpose as the FIS, but exploits data of other characteristics. The common goal of applying fuzzy logic and online learning is to generate a smart cost map that is used for defining path in the initial planning phase so that they are similar to the real ones to a feasible extent This will be an attempt to reduce the number of paths corrections during robots motion and to improve system efficiency. The same idea can be implemented in industrial and other similar environments
Sign-in/Register to view highlights & summary 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.
