Modular automatic design of collective behaviors for robots endowed with local communication capabilities

Abstract

We investigate the automatic design of communication in swarm robotics through two studies. We first introduce Gianduja an automatic design method that generates collective behaviors for robot swarms in which individuals can locally exchange a message whose semantics is not a priori fixed. It is the automatic design process that, on a per-mission basis, defines the conditions under which the message is sent and the effect that it has on the receiving peers. Then, we extend Gianduja to Gianduja2 and Gianduja 3, which target robots that can exchange multiple distinct messages. Also in this case, the semantics of the messages is automatically defined on a per-mission basis by the design process. Gianduja and its variants are based on Chocolate, which does not provide any support for local communication. In the article, we compare Gianduja and its variants with a standard neuro-evolutionary approach. We consider a total of six different swarm robotics missions. We present results based on simulation and tests performed with 20 e-puck robots. Results show that, typically, Gianduja and its variants are able to associate a meaningful semantics to messages.

Peer Review #1 of "Modular automatic design of collective behaviors for robots endowed with local communication capabilities (v0.1)"

“…Numerical results, videos, code, and probabilistic finite-state machines generated by Chocolate and Gianduja{ø,E} are available as supplementary material (Hasselmann and Birattari, 2019). In the following, with the notation Gianduja{ø,E}, we will collectively refer to Gianduja, and GiandujaE.…”

“…The performance of the real robots is automatically computed by a tracking system based on an overhead camera (Stranieri et al, 2013). The simulation model used as a pseudo-reality for the evaluations of the control software produced is available as supplementary material (Hasselmann and Birattari, 2019).…”

“…An example of probabilistic finite-state machine produced by Gianduja is reported as supplementary material (Hasselmann and Birattari, 2019). The robots start in the exploration state.…”

“…Other robots then stop and relay the message. Videos are available in Hasselmann and Birattari (2019).…”

“…As a result, performance is very inconsistent. Videos are available in Hasselmann and Birattari (2019).…”