Optimizing the Sensory Apparatus of Voxel-based Soft Robots through Evolution and Babbling

Abstract # ↰

The behavior of biological and artificial agents strongly depends, in general, on the data acquired through sensors while interacting with the environment. The sensory apparatus, namely the location and kind of sensors, has therefore a great impact on an agent’s ability of exhibiting complex behaviors. Considering the case of robots, sensors are usually a design choice that is hard to take, due to the complexity of the robotic structure and a potentially large number of possible combinations. Here, we explore the possibility of using evolutionary algorithms to automatically design (and optimizing their use) the sensors of voxel-based soft robots (VSRs), a kind of robots composed of multiple deformable components. We chose these robots due to their intrinsic modularity, which allows to freely shape the robot body, brain, and sensory apparatus. We consider a set of sensors that allow agents to sense themselves and their environment and we show, experimentally, that the effectiveness of the sensory apparatus depends on the body shape and the actuation capability. Then we show that evolutionary optimization is able to evolve effective sensory apparatuses, even with constraints on the availability of sensors. We also consider how information from sensors can be exploited more efficiently by introducing the concept of “sensor babbling”, which aims to enhance the robots' perception and, hence, their performances.