Collaborative Control of Multiple Robots Using Genetic Fuzzy Systems

Abstract

SummaryThis paper introduces an approach of collaborative control for individual robots to collaboratively perform a common task, without the need for a centralized controller to coordinate the group. The approach is illustrated by an application example involving multiple robots performing a collaborative task to achieve a common goal. The objective of this example problem is to control multiple robots that are connected to an object through elastic cables in order to bring the object to a target position. There is no communication between the robots, and hence each robot is unaware of how the other robots are going to react at any instant. Only the information pertaining to the object and the target is available to all the robots at any instant. Genetic fuzzy system (GFS) is used to develop controller for each of the robots. The nonlinearity of fuzzy logic systems coupled with the search capability of genetic algorithms provides a tool to design controllers for such collaborative tasks. A set of training scenarios are developed to train the individual robot controllers for this task. The trained controllers are then tested on an extensive set of scenarios. This paper describes the development process of GFS controllers for dynamic case involving systems consisting of three robots. It is also shown that the GFS controllers are scalable for the more complex systems involving more than three robots.

Genetic Fuzzy Based Scalable System of Distributed Robots for a Collaborative Task

“…This section extends the dynamics analysis from our previous work (Sathyan and Ma, 2019) to asymmetric multi-robot topologies. For the sake of uniformity, we will follow the same notation system as in Sathyan and Ma (2019).…”

“…In our previous work (Sathyan and Ma, 2019 ), we had described some limitations, such as increased complexity of training as the number of robots are increased. Moreover, in the previous work, the GFSs had to be trained again when adding more robots.…”

“…This is extremely important in fault scenarios where a robot can breakdown and become inactive in the system, as well as in scenarios where more robots are added to provide more strength and efficiency. This work builds on our previous research (Sathyan and Ma, 2019 ) that was limited to teams consisting only upto 5 robots that were located only in a symmetric topology.…”

“…Such GFSs have proven to be extremely successful in various applications including task assignment and planning (Sathyan et al, 2016 ), simulated air-to-air combat (Ernest et al, 2016 ), athlete movement prediction (Sathyan et al, 2019b ), etc. GFS framework was also used for our previous work on a problem where the robots were placed along a regular polygon with the same objective of bringing the common effector to any arbitrarily defined position within the polygon (Sathyan and Ma, 2018 , 2019 ; Sathyan et al, 2018 , 2019a ).…”

“…In this paper, we extend on our previous work (Sathyan and Ma, 2019 ) to design a scalable GFS framework for a reinforcement learning problem involving a team of stationary, homogenous robots. Mamdani FLS is considered in this work.…”