Abstract
Due to the decentralized, loosely coupled nature of a swarm and to the lack of a general design methodology, the development of control software for robot swarms is typically an iterative process. Control software is generally modified and refined repeatedly, either manually or automatically, until satisfactory results are obtained. In this paper, we propose a technique based on off-policy evaluation to estimate how the performance of an instance of control software—implemented as a probabilistic finite-state machine—would be impacted by modifying the structure and the value of the parameters. The proposed technique is particularly appealing when coupled with automatic design methods belonging to the AutoMoDe family, as it can exploit the data generated during the design process. The technique can be used either to reduce the complexity of the control software generated, improving therefore its readability, or to evaluate perturbations of the parameters, which could help in prioritizing the exploration of the neighborhood of the current solution within an iterative improvement algorithm. To evaluate the technique, we apply it to control software generated with an AutoMoDe method, . In a first experiment, we use the proposed technique to estimate the impact of removing a state from a probabilistic finite-state machine. In a second experiment, we use it to predict the impact of changing the value of the parameters. The results show that the technique is promising and significantly better than a naive estimation. We discuss the limitations of the current implementation of the technique, and we sketch possible improvements, extensions, and generalizations.
Highlights
In this paper, we investigate the use of off-policy evaluation to estimate the performance of a swarm of robots
We focus on control software implemented as a probabilistic finite-state machine (PFSM): a graph where each node represents a low-level behavior of the robot and each edge represents a transition from a low-level behavior to another
In the experiments presented here, the execution traces are collected during the generation of the control software from the executions performed by the optimization algorithm used in Chocolate − 6S, Iterated F-Race implemented in the irace package (Birattari, 2009; López-Ibáez et al, 2016)
Summary
We investigate the use of off-policy evaluation to estimate the performance of a swarm of robots. In swarm robotics (Dorigo et al, 2014), a group of robots act in coordination to perform a given mission. This engineering discipline is inspired by the principles of swarm intelligence (Dorigo and Birattari, 2007). There is no single point of failure and additional robots can be added to the swarm without changing the control software. The design of the control software of the individual robots comprised in a swarm is an iterative improvement process based on trial and error and heavily relies on the experience and intuition of the designer (Francesca et al, 2014). Reviews of the swarm robotics literature can be found in Garattoni and Birattari (2016) and Brambilla et al (2013), while in depth reviews of automatic design in swarm robotics can be found in Francesca and Birattari (2016); Bredeche et al (2018); Birattari et al (2020)
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.
