On Using Simulation to Predict the Performance of Robot Swarms.

The discrepancy between simulation and reality-known as the reality gap-is one of the main challenges associated with using simulations to design control software for robot swarms. Currently, the reality-gap problem necessitates expensive and time consuming tests on physical robots to reliably assess control software. Predicting real-world performance accurately without recurring to physical experiments would be particularly valuable. In this paper, we compare various simulation-based predictors of the performance of robot swarms that have been proposed in the literature but never evaluated empirically. We consider (1) the classical approach adopted to estimate real-world performance, which relies on the evaluation of control software on the simulation model used in the design process, and (2) some so-called pseudo-reality predictors, which rely on simulation models other than the one used in the design process. To evaluate these predictors, we reuse 1021 instances of control software and their real-world performance gathered from seven previous studies. Results show that the pseudo-reality predictors considered yield more accurate estimates of the real-world performance than the classical approach.

Empirical assessment and comparison of neuro-evolutionary methods for the automatic off-line design of robot swarms.

Neuro-evolution is an appealing approach to generating collective behaviors for robot swarms. In its typical application, known as off-line automatic design, the neural networks controlling the robots are optimized in simulation. It is understood that the so-called reality gap, the unavoidable differences between simulation and reality, typically causes neural network to be less effective on real robots than what is predicted by simulation. In this paper, we present an empirical study on the extent to which the reality gap impacts the most popular and advanced neuro-evolutionary methods for the off-line design of robot swarms. The results show that the neural networks produced by the methods under analysis performed well in simulation, but not in real-robot experiments. Further, the ranking that could be observed in simulation between the methods eventually disappeared. We find compelling evidence that real-robot experiments are needed to reliably assess the performance of neuro-evolutionary methods and that the robustness to the reality gap is the main issue to be addressed to advance the application of neuro-evolution to robot swarms.

Automatic modular design of robot swarms using behavior trees as a control architecture.

We investigate the possibilities, challenges, and limitations that arise from the use of behavior trees in the context of the automatic modular design of collective behaviors in swarm robotics. To do so, we introduce Maple, an automatic design method that combines predefined modules-low-level behaviors and conditions-into a behavior tree that encodes the individual behavior of each robot of the swarm. We present three empirical studies based on two missions: aggregation and Foraging. To explore the strengths and weaknesses of adopting behavior trees as a control architecture, we compare Maple with Chocolate, a previously proposed automatic design method that uses probabilistic finite state machines instead. In the first study, we assess Maple's ability to produce control software that crosses the reality gap satisfactorily. In the second study, we investigate Maple's performance as a function of the design budget, that is, the maximum number of simulation runs that the design process is allowed to perform. In the third study, we explore a number of possible variants of Maple that differ in the constraints imposed on the structure of the behavior trees generated. The results of the three studies indicate that, in the context of swarm robotics, behavior trees might be appealing but in many settings do not produce better solutions than finite state machines.

Concurrent design of control software and configuration of hardware for robot swarms under economic constraints.

Designing a robot swarm is challenging due to its self-organized and distributed nature: complex relations exist between the behavior of the individual robots and the collective behavior that results from their interactions. In this paper, we study the concurrent automatic design of control software and the automatic configuration of the hardware of robot swarms. We introduce Waffle, a new instance of the AutoMoDe family of automatic design methods that produces control software in the form of a probabilistic finite state machine, configures the robot hardware, and selects the number of robots in the swarm. We test Waffle under economic constraints on the total monetary budget available and on the battery capacity of each individual robot comprised in the swarm. Experimental results obtained via realistic computer-based simulation on three collective missions indicate that different missions require different hardware and software configuration, and that Waffle is able to produce effective and meaningful solutions under all the experimental conditions considered.

Automatic Off-Line Design of Robot Swarms: A Manifesto.

Designing collective behaviors for robot swarms is a difficult endeavor due to their fully distributed, highly redundant, and ever-changing nature. To overcome the challenge, a few approaches have been proposed, which can be classified as manual, semi-automatic, or automatic design. This paper is intended to be the manifesto of the automatic off-line design for robot swarms. We define the off-line design problem and illustrate it via a possible practical realization, highlight the core research questions, raise a number of issues regarding the existing literature that is relevant to the automatic off-line design, and provide guidelines that we deem necessary for a healthy development of the domain and for ensuring its relevance to potential real-world applications.

Complexity Measures: Open Questions and Novel Opportunities in the Automatic Design and Analysis of Robot Swarms.

Complexity measures and information theory metrics in general have recently been attracting the interest of multi-agent and robotics communities, owing to their capability of capturing relevant features of robot behaviors, while abstracting from implementation details. We believe that theories and tools from complex systems science and information theory may be fruitfully applied in the near future to support the automatic design of robot swarms and the analysis of their dynamics. In this paper we discuss opportunities and open questions in this scenario.