Harnessing the Power of Collective Intelligence: the Case Study of Voxel-based Soft Robots

The field of Evolutionary Robotics (ER) is concerned with the evolution of artificial agents---robots. Albeit groundbreaking, progress in the field has recently stagnated. In the research community, there is a strong feeling that a paradigm change has become necessary to disentangle ER. In particular, a solution has emerged from ideas from Collective Intelligence (CI). In CI---which has many relevant examples in nature---behavior emerges from the interaction between several components. In the absence of central intelligence, collective systems are usually more adaptable. In this thesis, we set out to harness the power of CI, focusing on the case study of simulated Voxel-based Soft Robots (VSRs): they are aggregations of homogeneous and soft cubic blocks that actuate by altering their volume. We investigate two axes. First, the morphologies of VSRs are intrinsically modular and an ideal substrate for CI; nevertheless, controllers employed until now do not take advantage of such modularity. Our results prove that VSRs can truly be controlled by the CI of their modules. Second, we investigate the spatial and time scales of CI. In particular, we evolve a robot to detect its global body properties given only local information processing, and, in a different study, generalize better to unseen environmental conditions through Hebbian learning. We also consider how evolution and learning interact in VSRs. Looking beyond VSRs, we propose a novel soft robot formalism that more closely resembles natural tissues and blends local with global actuation.

The field of Evolutionary Robotics (ER) is concerned with the evolution of artificial agents---robots. Albeit groundbreaking, progress in the field has recently stagnated. In the research community, there is a strong feeling that a paradigm change has become necessary to disentangle ER. In particular, a solution has emerged from ideas from Collective Intelligence (CI). In CI---which has many relevant examples in nature---behavior emerges from the interaction between several components. In the absence of central intelligence, collective systems are usually more adaptable. In this thesis, we set out to harness the power of CI, focusing on the case study of simulated Voxel-based Soft Robots (VSRs): they are aggregations of homogeneous and soft cubic blocks that actuate by altering their volume. We investigate two axes. First, the morphologies of VSRs are intrinsically modular and an ideal substrate for CI; nevertheless, controllers employed until now do not take advantage of such modularity. Our results prove that VSRs can truly be controlled by the CI of their modules. Second, we investigate the spatial and time scales of CI. In particular, we evolve a robot to detect its global body properties given only local information processing, and, in a different study, generalize better to unseen environmental conditions through Hebbian learning. We also consider how evolution and learning interact in VSRs. Looking beyond VSRs, we propose a novel soft robot formalism that more closely resembles natural tissues and blends local with global actuation.