Dynamic heterogeneous team formation for robotic urban search and rescue

Abstract

Using teams of robots to complete a task provides a number of advantages over the use of a single robot. Multiple robots are able to complete tasks faster, and provide redundancy in case of equipment failure or loss. Teams of robots with different capabilities and physiologies are beneficial because they allow a team to provide a high level of overall functionality while striking a balance between the cost and complexity of the robots. Previous work tends to focus on the use of pre-formed teams of robots, with little attention to the formation and maintenance of the team itself. An environment such as a disaster zone presents numerous challenges to robotic operation, and it can be expected that the nature of a team will change due to, for example, malfunctions and the introduction of replacement equipment. I developed a framework to support the maintenance of teams of heterogeneous robots operating in complex and dynamic environments such as disaster zones. Given an established team, my work also facilitates the discovery of work to be done during the team's mission and its subsequent assignment to members of the team in a distributed fashion. I evaluated my framework through the development of an example implementation where robots perform exploration in order to locate victims in a simulated disaster environment.ii

Allocating structured tasks in heterogeneous agent teams

“…28 Finally, we compare our mechanism with two other task allocation approaches that handle only one of the types of tasks in our approach, more specifically atomic tasks, ie, a task allocation algorithm (we call it TAA) used in the work of Ghamry et al 29 and a role-based task allocation (we call it RBTA) available in the work of Gunn and Anderson. 30 By performance, we mean the overall utility obtained by all the agents to take on all the subtasks that they can. The coefficient of variation (standard deviation divided by the mean) was used as a measure of dispersion (ie, the amount of variability relative to the mean).…”

“…The article focuses on disaster scenarios and proposes the use of heterogeneous robots, in which the robot with the best computational resources plays the role of the coordinator, and consequently, becomes responsible for the coordination of the task allocation process. 30 Thus, it could be said of that approach that there is still a single point of failure within each team, so it is not exactly a decentralized solution like ours.…”

“…In this section, we compare the performance of our mechanism with the task assignment approaches used in two frameworks, ie, a task allocation algorithm (we call it TAA) used in the work of Gharmy et al 29 and a role-based task allocation (we call it RBTA) introduced in the work of Gunn and Anderson. 30 Both approaches deal only with part of the task structures we deal with, more specifically, atomic tasks. Our idea is to compare the performance of approaches developed for specific types of tasks with the performance of our mechanism, which is broader, given that we are not aware of other algorithms that deal with the same types of tasks as in our approach.…”

An Advice Mechanism for Heterogeneous Robot Teams

“…Team formation refers to how the roles within the team are created and organized, while team capabilities refers to the algorithms defining robot behaviour. Some approaches to robot team formation have utilized predefined roles to dynamically form teams and manage the members [7,9], enabling new members to be added and removed. A role can entail a responsibility for a task, or a governing process, such as the processes for environmental mapping or computational resource allocation.…”

Distributed autonomous GIS to form teams for public safety

“…The problem has been allotted to teams of robots, as for example [Gunn et al, 2013]. Robots can be scheduled to do tasks in a particular sequence [Coltin et al, 2011].…”