检索结果-内蒙古大学图书馆

Few-Shot Quality-Diversity Optimization

IEEE robotics AND AUTOMATION LETTERS 2022年第2期7卷 4424-4431页

作者： Salehi, Achkan Coninx, Alexandre Doncieux, Stephane Sorbonne Univ CNRS ISIR F-75005 Paris France

In the past few years,a considerable amount of research has been dedicated to the exploitation of previous learning experiences and the design of Few-shot and Meta Learning approaches, in problem domains ranging from Computer Vision to Reinforcement Learning based control. A notable exception, where to the best of our knowledge, little to no effort has been made in this direction is Quality-Diversity (QD) optimization. QD methods have been shown to be effective tools in dealing with deceptive minima and sparse rewards in Reinforcement Learning. However, they remain costly due to their reliance on inherently sample inefficient evolutionary processes. We show that, given examples from a task distribution, information about the paths taken by optimization in parameter space can be leveraged to build a prior population, which when used to initialize QD methods in unseen environments, allows for few-shot adaptation. Our proposed method does not require backpropagation. It is simple to implement and scale, and furthermore, it is agnostic to the underlying models that are being trained. Experiments carried in both sparse and dense reward settings using robotic manipulation and navigation benchmarks show that it considerably reduces the number of generations that are required for QD optimization in these environments.

关键词： Optimization Task analysis Statistics Sociology Training Reinforcement learning Navigation evolutionary robotics reinforcement learning transfer learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal Legged Locomotion Framework With Automated Residual Reinforcement Learning

引用

IEEE robotics AND AUTOMATION LETTERS 2022年第4期7卷 10312-10319页

作者： Yu, Chen Rosendo, Andre ShanghaiTech Univ Sch Informat Sci & Technol Shanghai 201210 Peoples R China

While quadruped robots usually have good stability and load capacity, bipedal robots offer a higher level of flexibility / adaptability to different tasks and environments. A multi-modal legged robot can take the best of both worlds. In this paper, we propose a multi-modal locomotion framework that is composed of a hand-crafted transition motion and a learning-based bipedal controller-learnt by a novel algorithm called Automated Residual Reinforcement Learning. This framework aims to endow arbitrary quadruped robots with the ability to walk bipedally. In particular, we 1) design an additional supporting structure for a quadruped robot and a sequential multi-modal transition strategy;2) propose a novel class of Reinforcement Learning algorithms for bipedal control and evaluate their performances in both simulation and the real world. Experimental results show that our proposed algorithms have the best performance in simulation and maintain a good performance in a real-world robot. Overall, our multi-modal robot could successfully switch between biped and quadruped, and walk in both modes.

关键词： evolutionary robotics legged robots multi-modal locomotion reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

On the evolution of mechanisms for three -option collective decision -making in a swarm of simulated robots 23

On the evolution of mechanisms for three -option collective ...

引用

Genetic and evolutionary Computation Conference (GECCO)

作者： Almansoori, Ahmed Alkilabi, Muhanad Tuci, Elio Univ Namur Namur Belgium Univ Karbala Karbala Iraq

ISBN: (纸本)9798400701191

To act cohesively as a group, robot swarms must be able to make decisions collectively. Collective decision-making refers to a process in which once a group decision is reached, it cannot be attributed to any single individual. Although extensive research has been conducted in swarm robotics using hand-coded design techniques to develop individual mechanisms for collective decision-making, the proposed mechanisms are generally limited in terms of robustness, scalability, and adaptability. In this paper, we employ evolutionary computation techniques to synthesise neural network-based decision-modules underpinning the individual opinion selection in robots. We describe the group dynamics underlying the decision process that leads to consensus in a three-option perceptual discrimination task. We test the robustness, scalability and adaptability of the decision-module in a variety of conditions. We show that the decision-making mechanisms underpinned by the evolved decision-module are more effective in supporting the collective decision-making process than the hand-coded voter and majority models, both in terms of accuracy and with respect to time to convergence to consensus.

关键词： swarm robotics evolutionary robotics collective decision-making collective perception

来源：评论

学校读者我要写书评

暂无评论

Diversity Search for the Generation of Diverse Grasping Trajectories

Diversity Search for the Generation of Diverse Grasping Traj...

引用

Genetic and evolutionary Computation Conference (GECCO)

作者： Huber, Johann Sane, Oumar Coninx, Miranda Ben Amar, Faiz Doncieux, Stephane Sorbonne Univ ISIR Inst Syst Intelligents & Robot Paris France Sorbonne Univ ISIR Inst Syst Intelligents & Robot CNRS Paris France

ISBN: (纸本)9798400701207

Robotic grasping refers to making a robotic system pick an object by applying forces and torques on its surface. Despite the recent advances in data-driven approaches, grasping still needs to be solved. In this work, we consider grasping as a Diversity Search problem, where we attempt to find as many solutions as possible that verify a sparse binary criterion. We propose a variant of a state-of-the-art QD method for grasping based on a divide-and-conquer paradigm to handle grasping discontinuities. Experiments conducted on 3 different robot-gripper setups and several standard objects show that this variant outperforms state-of-the-art for generating diverse repertoires of grasping trajectories.

关键词： diversity search novelty search evolutionary robotics

来源：评论

学校读者我要写书评

暂无评论

evolutionary robotics approach to odor source localization

引用

NEUROCOMPUTING 2013年 121卷 481-497页

作者： de Croon, G. C. H. E. O'Connor, L. M. Nicol, C. Izzo, D. Delft Univ Technol Fac Aerosp Engn NL-2600 AA Delft Netherlands Carleton Univ Dept Mech & Aerosp Engn Ottawa ON K1S 5B6 Canada

An evolutionary robotics (ER) approach to the task of odor source localization is investigated. In particular, Continuous Time Recurrent Neural Networks (CTRNNs) are evolved for odor source localization in simulated turbulent odor plumes. In the experiments, the simulated robot is equipped with a single chemical sensor and a wind direction sensor. Three main contributions are made. First, it is shown that the ER approach can be successfully applied to odor source localization in both low-turbulent and high-turbulent conditions. Second, it is demonstrated that a small neural network is able to successfully perform all three sub-tasks of odor source localization: (i) finding the odor plume, (ii) moving toward the odor source, and (iii) identifying the odor source. Third, the analysis of the evolved behaviors reveals two novel odor source localization strategies. These strategies are successfully re-implemented as finite state machines, validating the insights from the analysis of the neural controllers. (C) 2013 Elsevier B.V. All rights reserved.

关键词： Odor source localization Neural controller evolutionary robotics Continuous time recurrent neural network

来源：评论

学校读者我要写书评

暂无评论

Evolving collective step-climbing behavior in multi-legged robotic swarm

引用

ARTIFICIAL LIFE AND robotics 2022年第2期27卷 333-340页

作者： Morimoto, Daichi Hiraga, Motoaki Shiozaki, Naoya Ohkura, Kazuhiro Munetomo, Masaharu Hiroshima Univ Hiroshima Japan Hokkaido Univ Informat Initiat Ctr Sapporo Hokkaido Japan

This paper focuses on generating the collective step-climbing behavior of a multi-legged robotic swarm. Most studies on swarm robotics develop collective behaviors in a flat environment using mobile robots equipped with wheels. However, these types of robots could only show relatively simple behavior, which limits a task that could be addressed by a robotic swarm. This paper deals with a step-climbing task, in which a robotic swarm climbs a step that is too high for a single robot. The robots have to use other robots as a foothold to achieve the task. To generate such three-dimensional behavior, a robotic swarm is conducted using the multi-legged robot inspired by ants. The robot controller is obtained by the combination of the neuroevolution approach with manual designed methods. The results of the computer simulations show that the designed controller successfully achieve the step-climbing task.

关键词： Swarm robotics evolutionary robotics Multi-legged robot

来源：评论

学校读者我要写书评

暂无评论

Evolving Modularity in Soft Robots Through an Embodied and Self-Organizing Neural Controller

引用

ARTIFICIAL LIFE 2022年第3期28卷 322-347页

作者： Pigozzi, Federico Medvet, Eric Univ Trieste Dept Engn & Architecture Trieste Italy

Modularity 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.

关键词： Embodied AI self-organization evolutionary robotics neuroevolution modularity

来源：评论

学校读者我要写书评

暂无评论

Quality-Diversity Meta-Evolution: Customizing Behavior Spaces to a Meta-Objective

引用

IEEE TRANSACTIONS ON evolutionary COMPUTATION 2022年第5期26卷 1171-1181页

作者： Bossens, David M. Tarapore, Danesh Univ Southampton Sch Elect & Comp Sci Southampton SO17 1BJ Hants England

Quality-diversity (QD) algorithms evolve behaviorally diverse and high-performing solutions. To illuminate the elite solutions for a space of behaviors, QD algorithms require the definition of a suitable behavior space. If the behavior space is high-dimensional, a suitable dimensionality reduction technique is required to maintain a limited number of behavioral niches. While current methodologies for automated behavior spaces focus on changing the geometry of the behavior space or on unsupervised learning of its key features, there remains a need for customizing behavioral diversity to a particular meta-objective specified by the end user. In the newly emerging framework of QD Meta-Evolution, or QD-Meta for short, one evolves a population of QD algorithms, each with different algorithmic and representational characteristics, to optimize the algorithms and their resulting archives to a user-defined meta-objective. Despite promising results compared to traditional QD algorithms, QD-Meta has yet to be compared to state-of-the-art behavior space automation methods, such as centroidal voronoi tessellations multidimensional archive of phenotypic elites (CVT-MAP-Elites) and autonomous robots realizing their abilities (AURORAs). This article performs an empirical study of QD-Meta on function optimization and multilegged robot locomotion benchmarks. Results demonstrate that QD-Meta archives provide improved average performance and faster adaptation to a priori unknown changes to the environment when compared to CVT-MAP-Elites and AURORA. A qualitative analysis shows how the resulting archives are tailored to the meta-objectives provided by the end user.

关键词： Databases Statistics Sociology Robots Magnetosphere Ion radiation effects Genetics evolutionary robotics meta-evolution quality-diversity (QD) algorithms

来源：评论

学校读者我要写书评

暂无评论

Evolving topology and weights of specialized and non-specialized neuro-controllers for robot motion in various environments

引用

NEURAL COMPUTING & APPLICATIONS 2022年第19期34卷 17071-17086页

作者： Salih, Adham Moshaiov, Amiram Tel Aviv Univ Sch Mech Engn Tel Aviv Israel ORT Braude Coll Engn Mech Engn Dept Karmiel Israel Tel Aviv Univ Sagol Sch Neurosci Tel Aviv Israel

This paper deals with the topology and weight evolution of Neuro-Controllers (NCs). It focuses on meta-problems of developing motion controllers that can operate successfully in several given motion-problems, where each of these motion problems defers by the arena and task. Here, the evolution aims to find both specialized and non-specialized controllers. The non-specialized controllers are evolved to provide a successful motion for the entire set of the given motion-problems, whereas each specialized controller is evolved to be optimal in at least one of these problems. The meta-problem is defined as a many-objective optimization problem, in which the kth objective is to maximize the motion performance in the kth motion problem. Following the problem description, a decomposition-based evolutionary algorithm, which is termed NEWS/D, is presented. This algorithm, which has recently been proposed by the authors, is specially designed to allow the topology and weight evolution of NCs under a large number of objectives. Next, the algorithm is applied to find NCs for three meta-problems, i.e., three sets of motion problems. The results of the experiments show that the obtained three sets of NCs include both specialized and non-specialized controllers. In addition, the proposed approach of many-objective topology and weight evolution of NCs is analyzed in comparison with other approaches, including three versions of decomposition-based fixed topology optimization. It is shown here that for the same number of evaluations, NEWS/D achieved better results than those of the other approaches. Finally, a topology analysis is carried out for the specialized NCs, which suggests that the solution includes multiple equivalent NCs. The numerical implications of this phenomenon are left for future work.

关键词： Many-objective optimization Decomposition approach Neuro-evolution Topology and weight evolution Robot motion control evolutionary robotics

来源：评论

学校读者我要写书评

暂无评论

Morphological-Novelty in Modular Robot Evolution

Morphological-Novelty in Modular Robot Evolution

引用

2023 IEEE Symposium Series on Computational Intelligence, SSCI 2023

作者： Weissl, Oliver Eiben, A.E. Vrije Universiteit Amsterdam Netherlands

ISBN: (纸本)9781665430654

This study investigates how the introduction of morphological novelty affects the fitness and diversity of a population of modular robots. Novelty is usually measured in behavioral space, while the approach discussed in this paper assesses novelty solely using morphologies. The proposed algorithm is inspired by the histogram of oriented gradients, in combination with elements of principal component analysis, and the Wasserstein distance. The experiments conducted utilize novelty in parent selection, with different configurations. Analyzing the results, the introduction of morphological novelty promotes beneficial effects on fitness and diversity when applied correctly. © 2023 IEEE.

关键词： evolutionary robotics Evolvable Morphologies Morphological Traits Novelty Search

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：