1,720,968 research outputs found
Harnessing the Power of Collective Intelligence: the Case Study of Voxel-based Soft Robots
Full text linkThe 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
Evolving Modularity in Soft Robots Through an Embodied and Self-Organizing Neural Controller
Full text linkModularity is a desirable property for embodied agents, as it could foster their suitability to different domains by disassembling them into transferable modules that can be reassembled differently. We focus on a class of embodied agents known as voxel-based soft robots (VSRs). They are aggregations of elastic blocks of soft material; as such, their morphologies are intrinsically modular. Nevertheless, controllers used until now for VSRs act as abstract, disembodied processing units: Disassembling such controllers for the purpose of module transferability is a challenging problem. Thus, the full potential of modularity for VSRs still remains untapped. In this work, we propose a novel self-organizing, embodied neural controller for VSRs. We optimize it for a given task and morphology by means of evolutionary computation: While evolving, the controller spreads across the VSR morphology in a way that permits emergence of modularity. We experimentally investigate whether such a controller (i) is effective and (ii) allows tuning of its degree of modularity, and with what kind of impact. To this end, we consider the task of locomotion on rugged terrains and evolve controllers for two morphologies. Our experiments confirm that our self-organizing, embodied controller is indeed effective. Moreover, by mimicking the structural modularity observed in biological neural networks, different levels of modularity can be achieved. Our findings suggest that the self-organization of modularity could be the basis for an automatic pipeline for assembling, disassembling, and reassembling embodied agents
BUSTLE: a Versatile Tool for the Evolutionary Learning of STL Specifications from Data
Full text linkDescribing the properties of complex systems that evolve over time is a crucial requirement for monitoring and understanding them. Signal Temporal Logic (STL) is a framework that proved to be effective for this aim because it is expressive and allows state properties as human-readable formulae. Crafting STL formulae that fit a particular system is, however, a difficult task. For this reason, a few approaches have been proposed recently for the automatic learning of STL formulae starting from observations of the system. In this paper, we propose BUSTLE (Bi-level Universal STL Evolver), an approach based on evolutionary computation for learning STL formulae from data. BUSTLE advances the state-of-the-art because it (i) applies to a broader class of problems, in terms of what is known about the state of the system during its observation, and (ii) generates both the structure and the values of the parameters of the formulae employing a bi-level search mechanism (global for the structure, local for the parameters). We consider two cases where (a) observations of the system in both anomalous and regular state are available, or (b) only observations of regular state are available. We experimentally evaluate BUSTLE on problem instances corresponding to the two cases and compare it against previous approaches. We show that the evolved STL formulae are effective and human-readable: the versatility of BUSTLE does not come at the cost of lower effectiveness
How the Morphology Encoding Influences the Learning Ability in Body-Brain Co-Optimization
Full text linkEmbedding the learning of controllers within the evolution of morphologies has emerged as an effective strategy for the co-optimization of agents' bodies and brains. Intuitively, that is how nature shaped animal life on Earth. Still, the design of such co-optimization is a complex endeavor; one issue is the choice of the genetic encoding for the morphology. Such choice can be crucial for the effectiveness of learning, i.e., how fast and to what degree agents adapt, through learning, during their life. Here we evolve the morphologies of voxel-based soft agents with two different encodings, direct and indirect while learning the controllers with reinforcement learning. We experiment with three tasks, ranging from cave crawling to beam toppling, and study how the encoding influences the learning outcome. Our results show that the direct encoding corresponds to increased ability to learn, mostly in terms of learning speed. The same is not always true for the indirect one. We link these results to different shades of the Baldwin effect, consisting of morphologies being selected for increasing an agent’s ability to learn during its lifetime
Evolving Hebbian Learning Rules in Voxel-based Soft Robots
Full text linkAccording to Hebbian theory, synaptic plasticity is the ability of neurons to strengthen or weaken the synapses among them in response to stimuli. It plays a fundamental role in the processes of learning and memory of biological neural networks. With plasticity, biological agents can adapt on multiple timescales and outclass artificial agents, the majority of which still rely on static Artificial Neural Network (ANN) controllers. In this work, we focus on Voxel-based Soft Robots (VSRs), a class of simulated artificial agents, composed as aggregations of elastic cubic blocks. We propose a Hebbian ANN controller where every synapse is associated with a Hebbian rule that controls the way the weight is adapted during the VSR lifetime. For a given task and morphology, we optimize the controller for the task of locomotion by evolving, rather than the weights, the parameters of the Hebbian rules. Our results show that the Hebbian controller is comparable, often better than a non-Hebbian baseline and that it is more adaptable to unforeseen damages. We also provide novel insights into the inner workings of plasticity and demonstrate that “true” learning does take place, as the evolved controllers improve over the lifetime and generalize well
On the Mutual Influence of Human and Artificial Life: an Experimental Investigation
Full text linkOur modern world is teeming with non-biological agents, whose growing complexity brings them so close to living beings that they can be cataloged as artificial creatures, i.e., a form of Artificial Life (ALife). Ranging from disembodied intelligent agents to robots of conspicuous dimensions, all these artifacts are united by the fact that they are designed, built, and possibly trained by humans taking inspiration from natural elements. Hence, humans play a fundamental role in relation to ALife, both as creators and as final users, which calls attention to the need of studying the mutual influence of human and artificial life. Here we attempt an experimental investigation of the reciprocal effects of the human-ALife interaction. To this extent, we design an artificial world populated by life-like creatures, and resort to open-ended evolution to foster the creatures adaptation. We allow bidirectional communication between the system and humans, who can observe the artificial world and voluntarily choose to perform positive or negative actions towards the creatures populating it; those actions may have a short- or long-term impact on the artificial creatures. Our experimental results show that the creatures are capable of evolving under the influence of humans, even though the impact of the interaction remains uncertain. In addition, we find that ALife gives rise to disparate feelings in humans who interact with it, who are not always aware of the importance of their conduct
Mining Road Traffic Rules with Signal Temporal Logic and Grammar-Based Genetic Programming
Full text linkTraffic systems, where human and autonomous drivers interact, are a very relevant instance of complex systems and produce behaviors that can be regarded as trajectories over time. Their monitoring can be achieved by means of carefully stated properties describing the expected behavior. Such properties can be expressed using Signal Temporal Logic (STL), a specification language for expressing temporal properties in a formal and human-readable way. However, manually authoring these properties is a hard task, since it requires mastering the language and knowing the system to be monitored. Moreover, in practical cases, the expected behavior is not known, but it has instead to be inferred from a set of trajectories obtained by observing the system. Often, those trajectories come devoid of human-assigned labels that can be used as an indication of compliance with expected behavior. As an alternative to manual authoring, automatic mining of STL specifications from unlabeled trajectories would enable the monitoring of autonomous agents without sacrificing human-readability. In this work, we propose a grammar-based evolutionary computation approach for mining the structure and the parameters of an STL specification from a set of unlabeled trajectories. We experimentally assess our approach on a real-world road traffic dataset consisting of thousands of vehicle trajectories. We show that our approach is effective at mining STL specifications that model the system at hand and are interpretable for humans. To the best of our knowledge, this is the first such study on a set of unlabeled real-world road traffic data. Being able to mine interpretable specifications from this kind of data may improve traffic safety, because mined specifications may be helpful for monitoring traffic and planning safety promotion strategies
Evolutionary Machine Learning in Robotics
Full text linkIn this chapter, we survey the most significant applications of EML to robotics. We first highlight the salient characteristics of the field in terms of what can be optimized and with what aims and constraints. Then we survey the large literature concerning the optimization, by the means of evolutionary computation, of artificial neural networks, traditionally considered a form of machine learning, used for controlling the robots: for easing the comprehension, we categorize the various approaches along different axes, as, e.g., the robotic task, the representation of the solutions, the evolutionary algorithm being employed. We then survey the many usages of evolutionary computation for optimizing the morphology of the robots, including those that tackle the challenging task of optimizing the morphology and the controller at the same time. Finally, we discuss the reality gap problem that consists in a potential mismatch between the quality of solutions found in simulations and their quality observed in reality
Evolving modular soft robots without explicit inter-module communication using local self-attention
Full text linkModularity in robotics holds great potential. In principle, modular robots can be disassembled and reassembled in different robots, and possibly perform new tasks. Nevertheless, actually exploiting modularity is yet an unsolved problem: controllers usually rely on inter-module communication, a practical requirement that makes modules not perfectly interchangeable and thus limits their flexibility. Here, we focus on Voxel-based Soft Robots (VSRs), aggregations of mechanically identical elastic blocks. We use the same neural controller inside each voxel, but without any inter-voxel communication, hence enabling ideal conditions for modularity: modules are all equal and interchangeable. We optimize the parameters of the neural controller—shared among the voxels—by evolutionary computation. Crucially, we use a local self-attention mechanism inside the controller to overcome the absence of inter-module communication channels, thus enabling our robots to truly be driven by the collective intelligence of their modules. We show experimentally that the evolved robots are effective in the task of locomotion: thanks to self-attention, instances of the same controller embodied in the same robot can focus on different inputs. We also find that the evolved controllers generalize to unseen morphologies, after a short fine-tuning, suggesting that an inductive bias related to the task arises from true modularity
On the impact of body material properties on neuroevolution for embodied agents
Full text linkArtificial agents required to perform non-trivial tasks are commonly controlled with Artificial Neural Networks (ANNs), which need to be carefully fine-tuned. This is where ANN optimization comes into play, often in the form of Neuroevolution (NE). Among artificial agents, the embodied ones, are characterized by a strong body-brain entanglement, i.e., a strong interdependence between the physical properties of the body and the controller. In this work, we aim at characterizing said interconnection, experimentally evaluating the impact body material properties have on NE for embodied agents. We consider the case of Voxel-based Soft Robots (VSRs), a class of simulated modular soft robots which achieve movement through the rhythmical contraction and expansion of their modules. We experiment varying several physical properties of VSRs and assess the effectiveness of the evolved controllers for the task of locomotion, together with their robustness and adaptability. Our results confirm the existence of a deep body-brain interrelationship for embodied agents, and highlight how NE fruitfully exploits the physical properties of the agents to give rise to a wide gamut of effective and adaptable behaviors
- …
