2022 IEEE International Conference on Development and Learning (ICDL)最新文献_第2页

The Impact of Action in Visual Representation Learning 动作对视觉表征学习的影响

2022 IEEE International Conference on Development and Learning (ICDL) Pub Date : 2022-09-12 DOI: 10.1109/ICDL53763.2022.9962210

Alexandre Devillers, Valentin Chaffraix, Frederic Armetta, S. Duffner, Mathieu Lefort

{"title":"The Impact of Action in Visual Representation Learning","authors":"Alexandre Devillers, Valentin Chaffraix, Frederic Armetta, S. Duffner, Mathieu Lefort","doi":"10.1109/ICDL53763.2022.9962210","DOIUrl":"https://doi.org/10.1109/ICDL53763.2022.9962210","url":null,"abstract":"Sensori-motor theories, inspired by work in neuroscience, psychology and cognitive science, claim that actions, through learning and mastering of a predictive model, are a key element in the perception of the environment. On the computational side, in the domains of representation learning and reinforcement learning, models are increasingly using self-supervised pretext tasks, such as predictive or contrastive ones, in order to increase the performance on their main task. These pretext tasks are action-related even if the action itself is usually not used in the model. In this paper, we propose to study the influence of considering action in the learning of visual representations in deep neural network models, an aspect which is often underestimated w.r.t. sensori-motor theories. More precisely, we quantity two independent factors: 1-whether or not to use the action during the learning of visual characteristics, and 2-whether or not to integrate the action in the representations of the current images. Other aspects will be kept as simple and comparable as possible, that is why we will not consider any specific action policies and combine simple architectures (VAE and LSTM), while using datasets derived from MNIST. In this context, our results show that explicitly including action in the learning process and in the representations improves the performance of the model, which opens interesting perspectives to improve state-of-the-art models of representation learning.","PeriodicalId":274171,"journal":{"name":"2022 IEEE International Conference on Development and Learning (ICDL)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130807859","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

RADAR: Reactive and Deliberative Adaptive Reasoning - Learning When to Think Fast and When to Think Slow 雷达:反应性和深思性的适应性推理——学会何时快速思考，何时慢速思考

2022 IEEE International Conference on Development and Learning (ICDL) Pub Date : 2022-09-12 DOI: 10.1109/ICDL53763.2022.9962202

Ørjan Strand, Didrik Spanne Reilstad, Zhenying Wu, Bruno C. da Silva, J. Tørresen, K. Ellefsen

引用次数: 1

What Kind of Player are You? Continuous Learning of a Player Profile for Adaptive Robot Teleoperation 你是什么样的玩家?自适应机器人遥操作中玩家特征的持续学习

2022 IEEE International Conference on Development and Learning (ICDL) Pub Date : 2022-09-12 DOI: 10.1109/ICDL53763.2022.9962211

Mélanie Jouaiti, K. Dautenhahn

引用次数: 1

Dream to Pose in a Tendon-Driven Manipulator with Muscle Synergy 梦想在肌肉协同的肌腱驱动操纵器中摆姿势

2022 IEEE International Conference on Development and Learning (ICDL) Pub Date : 2022-09-12 DOI: 10.1109/ICDL53763.2022.9962220

Matthew Ishige, T. Taniguchi, Yoshihiro Kawahara

{"title":"Dream to Pose in a Tendon-Driven Manipulator with Muscle Synergy","authors":"Matthew Ishige, T. Taniguchi, Yoshihiro Kawahara","doi":"10.1109/ICDL53763.2022.9962220","DOIUrl":"https://doi.org/10.1109/ICDL53763.2022.9962220","url":null,"abstract":"Bio-inspired tendon-driven manipulators have the potential to achieve human-level dexterity. However, their control is more complex than prevailing robotic hands because the relation between actuation and hand motion (Jacobian) is hard to obtain. On the other hand, humans maneuver their complex hands skillfully and conduct adaptive object grasping and manipulation. We conjecture that the foundation of this ability is a visual posing of hands (i.e., a skill to make arbitrary hand poses with visual and proprioceptive feedback). Children develop this skill before or in parallel with learning grasping and manipulation. Inspired by this developmental process, this study explored a method to equip compliant tendon-driven manipulators with the visual posing. To overcome the complexity of the system, we used a learning-based approach. Specifically, we adopted PlaNet, model-based reinforcement learning that leverages a dynamics model on a compact latent representation. To further accelerate learning, we restricted the control space using the idea of muscle synergy found in the human body control. We validated the effectiveness of the proposed method in a simulation. We also demonstrated that the posing skill acquired using our method is useful for object grasping. This study will contribute to achieving human-level dexterity in manipulations.","PeriodicalId":274171,"journal":{"name":"2022 IEEE International Conference on Development and Learning (ICDL)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132939544","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

I Have Seen that Before: Memory Augmented Neural Network for Learning Affordances by Analogy 我以前见过:基于类比学习能力的记忆增强神经网络

2022 IEEE International Conference on Development and Learning (ICDL) Pub Date : 2022-09-12 DOI: 10.1109/ICDL53763.2022.9962191

Paul Schydlo, Laura Santos, Atabak Dehban, A. John, J. Santos-Victor

引用次数: 0

Leveraging symmetry detection to speed up haptic object exploration in robots 利用对称检测加速机器人的触觉对象探索

2022 IEEE International Conference on Development and Learning (ICDL) Pub Date : 2022-09-12 DOI: 10.1109/ICDL53763.2022.9962206

Aramis Augusto Bonzini, L. Seminara, Simone Macciò, A. Carfì, L. Jamone

引用次数: 1

Embodied Attention in Word-Object Mapping: A Developmental Cognitive Robotics Model 词-对象映射中的具身注意:一个发展的认知机器人模型

2022 IEEE International Conference on Development and Learning (ICDL) Pub Date : 2022-09-12 DOI: 10.1109/ICDL53763.2022.9962189

Luca Raggioli, A. Cangelosi

引用次数: 2

Getting Priorities Right: Intrinsic Motivation with Multi-Objective Reinforcement Learning 正确获得优先级:多目标强化学习的内在动机

2022 IEEE International Conference on Development and Learning (ICDL) Pub Date : 2022-09-12 DOI: 10.1109/ICDL53763.2022.9962187

Yusuf Al-Husaini, Matthias Rolf

{"title":"Getting Priorities Right: Intrinsic Motivation with Multi-Objective Reinforcement Learning","authors":"Yusuf Al-Husaini, Matthias Rolf","doi":"10.1109/ICDL53763.2022.9962187","DOIUrl":"https://doi.org/10.1109/ICDL53763.2022.9962187","url":null,"abstract":"Intrinsic motivation is a common method to facilitate exploration in reinforcement learning agents. Curiosity is thereby supposed to aid the learning of a primary goal. However, indulging in curiosity may also stand in conflict with more urgent or essential objectives such as self-sustenance. This paper addresses the problem of balancing curiosity, and correctly prioritising other needs in a reinforcement learning context. We demonstrate the use of the multi-objective reinforcement learning framework C-MORE to integrate curiosity, and compare results to a standard linear reinforcement learning integration. Results clearly demonstrate that curiosity can be modelled with the priority-objective reinforcement learning paradigm. In particular, C-MORE is found to explore robustly while maintaining self-sustenance objectives, whereas the linear approach is found to over-explore and take unnecessary risks. The findings demonstrate a significant weakness of the common linear integration method for intrinsic motivation, and the need to acknowledge the potential conflicts between curiosity and other objectives in a multi-objective framework.","PeriodicalId":274171,"journal":{"name":"2022 IEEE International Conference on Development and Learning (ICDL)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124801304","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A connectionist model of associating proprioceptive and tactile modalities in a humanoid robot 人形机器人本体感觉和触觉模式的联结主义模型

2022 IEEE International Conference on Development and Learning (ICDL) Pub Date : 2022-09-12 DOI: 10.1109/ICDL53763.2022.9962195

Kristína Malinovská, I. Farkaš, Jana Harvanová, M. Hoffmann

引用次数: 3

Real-Time Acoustic Touch Localization in Human-Robot Interaction based on Steered Response Power 基于转向响应功率的人机交互实时声触摸定位

2022 IEEE International Conference on Development and Learning (ICDL) Pub Date : 2022-09-12 DOI: 10.1109/ICDL53763.2022.9962225

Juan José Gamboa-Montero, M. Basiri, J. C. Castillo, Sara Marques-Villarroya, M. Salichs

引用次数: 0