1,721,063 research outputs found
Optimizing the Sensory Apparatus of Voxel-Based Soft Robots Through Evolution and Babbling
Full text linkThe 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
A Bin-Packing Formulation for Radiotherapy Treatment Scheduling
No full textThe scheduling of radiation therapy is a complex problem that significantly impacts patient outcomes and the use of healthcare resources. This paper proposes a novel formalization of the radiotherapy scheduling problem (RTSP) as a modified one-dimensional bin-packing problem (BPP). This formalization offers several advantages, including leveraging state-of-the-art solvers for the one-dimensional BPP and extending the formulation to various BPP variants that align with the complexities of the RTSP. Preliminary results on a synthetic instance demonstrate the feasibility of the proposed approach
On the Entanglement between Evolvability and Fitness: an Experimental Study on Voxel-based Soft Robots
Full text linkThe concept of evolvability, that is the capacity to produce heritable and adaptive phenotypic variation, is crucial in the current understanding of evolution. However, while its meaning is intuitive, there is no consensus on how to quantitatively measure it. As a consequence, it is hard to evaluate the interplay between evolvability and fitness and its dependency on key factors like the evolutionary algorithm (EA) or the representation of the individuals. Here, we propose to use MAP-Elites, a well-established Quality Diversity EA, as a support structure for measuring evolvability and for highlighting its interplay with fitness. We map the solutions generated during the evolutionary process to a MAP-Elites-like grid and then visualize their fitness and evolvability as maps. This procedures does not affect the EA execution and can hence be applied to any EA: it only requires to have two descriptors for the solutions that can be used to meaningfully characterize them. We apply this general methodology to the case of Voxel-based Soft Robots, a kind of modular robots with a body composed of uniform elements whose volume is individually varied by the robot brain. Namely, we optimize the robots for the task of locomotion using evolutionary computation. We consider four representations, two for the brain only and two for both body and brain of the VSR, and two EAs (MAP-Elites and a simple evolutionary strategy) and examine the evolvability and fitness maps. The experiments suggest that our methodology permits to discover interesting patterns in the maps: fitness maps appear to depend more on the representation of the solution, whereas evolvability maps appear to depend more on the EA. As an aside, we find that MAP-Elites is particularly effective in the simultaneous evolution of the body and the brain of Voxel-based Soft Robots
MULTIFLOW: Shifting Towards Task-Agnostic Vision-Language Pruning
No full textWhile excellent in transfer learning, Vision-Language models (VLMs) come with high computational costs due to their large number of parameters. To address this issue, removing parameters via model pruning is a viable solution. However, existing techniques for VLMs are task-specific, and thus require pruning the network from scratch for each new task of interest. In this work, we explore a new direction: Task-Agnostic Vision-Language Pruning (TA-VLP). Given a pretrained VLM, the goal is to find a unique pruned counterpart transferable to multiple unknown downstream tasks. In this challenging setting, the transferable representations already encoded in the pretrained model are a key aspect to preserve. Thus, we propose Multimodal Flow Pruning (MULTIFLOW), a first, gradient-free, pruning framework for TA-VLP where: (i) the importance of a parameter is expressed in terms of its magnitude and its information flow, by incorporating the saliency of the neurons it connects; and (ii) pruning is driven by the emergent (multimodal) distribution of the VLM parameters after pretraining. We benchmark eight state-of-the-art pruning algorithms in the context of TA-VLP, experimenting with two VLMs, three vision-language tasks, and three pruning ratios. Our experimental results show that MULTIFLOW outperforms recent sophisticated, combinatorial competitors in the vast majority of the cases, paving the way towards addressing TA- VLP. The code is publicly available at https://github.com/FarinaMatteo/multiflow
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
Totipotent neural controllers for modular soft robots: Achieving specialization in body–brain co-evolution through Hebbian learning
Full text linkMulti-cellular organisms typically originate from a single cell, the zygote, that then develops into a multitude of structurally and functionally specialized cells. The potential of generating all the specialized cells that make up an organism is referred to as cellular “totipotency”, a concept introduced by the German plant physiologist Haberlandt in the early 1900s. In an attempt to reproduce this mechanism in synthetic organisms, we present a model based on a kind of modular robot called Voxel-based Soft Robot (VSR), where both the body, i.e., the arrangement of voxels, and the brain, i.e., the Artificial Neural Network (ANN) controlling each module, are subject to an evolutionary process aimed at optimizing the locomotion capabilities of the robot. In an analogy between totipotent cells and totipotent ANN-controlled modules, we then include in our model an additional level of adaptation provided by Hebbian learning, which allows the ANNs to adapt their weights during the execution of the locomotion task. Our in silico experiments reveal two main findings. Firstly, we confirm the common intuition that Hebbian plasticity effectively allows better performance and adaptation. Secondly and more importantly, we verify for the first time that the performance improvements yielded by plasticity are in essence due to a form of specialization at the level of single modules (and their associated ANNs): thanks to plasticity, modules specialize to react in different ways to the same set of stimuli, i.e., they become functionally and behaviorally different even though their ANNs are initialized in the same way. This mechanism, which can be seen as a form of totipotency at the level of ANNs, can have, in our view, profound implications in various areas of Artificial Intelligence (AI) and applications thereof, such as modular robotics and multi-agent systems
Regularized Evolutionary Algorithm for Dynamic Neural Topology Search
No full textDesigning neural networks for object recognition requires considerable architecture engineering. As a remedy, neuro-evolutionary network architecture search, which automatically searches for optimal network architectures using evolutionary algorithms, has recently become very popular. Although very effective, evolutionary algorithms rely heavily on having a large population of individuals (i.e., network architectures) and are therefore memory expensive. In this work, we propose a Regularized Evolutionary Algorithm with low memory footprint to evolve a dynamic image classifier. In details, we introduce novel custom operators that regularize the evolutionary process of a micro-population of 10 individuals. We conduct experiments on three different digits datasets (MNIST, USPS, SVHN) and show that our evolutionary method obtains competitive results with the current state-of-the-art
Beyond Body Shape and Brain: Evolving the Sensory Apparatus of Voxel-Based Soft Robots
Full text linkBiological and artificial embodied agents behave by acquiring information through sensors, processing that information, and acting on the environment. The sensory apparatus, i.e., the location on the body of the sensors and the kind of information the sensors are able to capture, has a great impact on the agent ability of exhibiting complex behaviors. While in nature, the sensory apparatus is the result of a long-lasting evolution, in artificial agents (robots) it is usually the result of a design choice. However, when the agents are complex and the design space is large, making that choice can be hard. In this paper, we explore the possibility of evolving the sensory apparatus of voxel-based soft robots (VSRs), a kind of simulated robots composed of multiple deformable components. VSRs, due to their intrinsic modularity, allow for great freedom in how to shape the robot body, brain, and sensory apparatus. We consider a set of sensors that allow the agent to sense itself and the environment (using vision and touch) and we show, experimentally, that the effectiveness of the sensory apparatus depends on the shape of the body and on the actuation capability, i.e., the VSR strength. Then we show that evolutionary optimization is able to evolve an effective sensory apparatus, even when constraints on the availability of the sensors are posed. By extending the adaptation to the sensory apparatus, beyond the body shape and the brain, we believe that our study takes a step forward to the ambitious path towards self-building robots
NEvoFed: A Decentralized Approach to Federated NeuroEvolution of Heterogeneous Neural Networks
No full text
- …
