Artificial Life and Robotics最新文献_第5页

Pointgng: a deep learning architecture for 3D point cloud recognition using growing neural gas Pointgng：一个深度学习架构，用于3D点云识别，使用不断增长的神经气体

IF 0.8

Artificial Life and Robotics Pub Date : 2025-12-03 DOI: 10.1007/s10015-025-01097-z

Ryo Shibata, Rei Akasaka, Yuichro Toda, Takayuki Matsuno

{"title":"Pointgng: a deep learning architecture for 3D point cloud recognition using growing neural gas","authors":"Ryo Shibata, Rei Akasaka, Yuichro Toda, Takayuki Matsuno","doi":"10.1007/s10015-025-01097-z","DOIUrl":"10.1007/s10015-025-01097-z","url":null,"abstract":"<div><p>In recent years, there is a strong need for autonomous robots to solve labor shortages and perform tasks in harsh environments. These robots need to avoid obstacles and plan their paths by analyzing data acquired in real environments and generating environmental maps. Unsupervised learning using Growing Neural Gas (GNG) is an algorithm that dynamically constructs a graph structure based on 3D point clouds acquired from sensors. GNG is characterized by its high robustness to downsampling and inhomogeneous data. On the other hand, although clustering based on the constructed topological structure is possible, it is not possible to recognize objects after clustering. To perform a wide range of tasks, the ability to recognize objects is essential, and deep learning methods are effective for this purpose. In particular, PointNet was the first point cloud deep learning model to deal with the irregularity and order invariance of point clouds. In this study, we propose a new deep learning model, PointGNG, which integrates GNG with PointNet++ and extracts local structural features using adjacency-based neighborhood information. Using this method, the proposed method achieved accuracy comparable to PointNet++ on the ModelNet40 benchmark. A slight improvement in accuracy was also observed for other datasets that include background information. This study demonstrates that the integration of unsupervised learning and deep learning with GNG is effective for efficient processing of point cloud data and object recognition. Furthermore, we evaluated the robustness of the proposed model and examined how the choice of training dataset affects its adaptability to real-world environments.</p></div>","PeriodicalId":46050,"journal":{"name":"Artificial Life and Robotics","volume":"31 1","pages":"337 - 346"},"PeriodicalIF":0.8,"publicationDate":"2025-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147336159","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

Communication emergence under reward delay: the role of direct utility in temporally extended communication games 奖励延迟下的交流涌现：直接效用在时间延长的交流博弈中的作用

IF 0.8

Artificial Life and Robotics Pub Date : 2025-11-27 DOI: 10.1007/s10015-025-01091-5

Naoki Inoue, Kei Wakabayashi

引用次数: 0

Deep reinforcement learning for multi-agent coordination 多智能体协调的深度强化学习

IF 0.8

Artificial Life and Robotics Pub Date : 2025-11-26 DOI: 10.1007/s10015-025-01089-z

Kehinde O. Aina, Sehoon Ha

{"title":"Deep reinforcement learning for multi-agent coordination","authors":"Kehinde O. Aina, Sehoon Ha","doi":"10.1007/s10015-025-01089-z","DOIUrl":"10.1007/s10015-025-01089-z","url":null,"abstract":"<div><p>We address the challenge of coordinating multiple robots in narrow and confined environments, where congestion and interference often hinder collective task performance. Drawing inspiration from insect colonies, which achieve robust coordination through stigmergy—modifying and interpreting environmental traces—we propose a <i>stigmergic multi-agent deep reinforcement learning (S-MADRL)</i> framework that leverages virtual pheromones to model local and social interactions, enabling decentralized emergent coordination without explicit communication. To overcome the convergence and scalability limitations of existing algorithms such as MADQN, MADDPG, and MAPPO, we leverage curriculum learning, which decomposes complex tasks into progressively harder sub-problems. Simulation results show that our framework achieves the most effective coordination of up to eight agents, where robots self-organize into asymmetric workload distributions that reduce congestion and modulate group performance. This emergent behavior, analogous to strategies observed in nature, demonstrates a scalable solution for decentralized multi-agent coordination under crowded environments with communication constraints.</p></div>","PeriodicalId":46050,"journal":{"name":"Artificial Life and Robotics","volume":"31 2","pages":"484 - 494"},"PeriodicalIF":0.8,"publicationDate":"2025-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10015-025-01089-z.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147938435","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Causal discovery in Additive Noise Models using beam search 用波束搜索发现加性噪声模型中的因果关系

IF 0.8

Artificial Life and Robotics Pub Date : 2025-11-25 DOI: 10.1007/s10015-025-01095-1

Hans Jarett J. Ong, Brian Godwin S. Lim, Renzo Roel P. Tan, Kazushi Ikeda

{"title":"Causal discovery in Additive Noise Models using beam search","authors":"Hans Jarett J. Ong, Brian Godwin S. Lim, Renzo Roel P. Tan, Kazushi Ikeda","doi":"10.1007/s10015-025-01095-1","DOIUrl":"10.1007/s10015-025-01095-1","url":null,"abstract":"<div><p>Causal discovery from observational data is a fundamental challenge. Greedy search algorithms like Regression with Subsequent Independence Test (RESIT), commonly used for learning Additive Noise Models (ANMs), are susceptible to making irreversible errors, especially in high-variance contexts. Such settings can be caused by unmeasured confounders or by high statistical noise from finite samples. To address this, we introduce a novel generalization of RESIT that replaces its local, greedy search with a more robust beam search, framing the task as a path search on a state-space graph. Through extensive simulation experiments, we demonstrate that structural accuracy, measured by Structural Hamming Distance (SHD) and Structural Intervention Distance (SID), consistently improves as the beam width (<i>w</i>) increases. Crucially, we also show that this performance gain comes at a manageable, approximately linear increase in computational cost relative to <i>w</i>. Furthermore, our analysis across different sample sizes shows these gains are most statistically significant in intermediate regimes (<span>(n=250, 500)</span>). This suggests that at these sample sizes, the statistical noise is high enough to mislead the greedy search into a suboptimal ordering, an error our wider beam search corrects, while performance converges at large sample sizes (<span>(n=1000)</span>). Our framework provides a practical, tunable algorithm that bridges the gap between fast but brittle local search methods and computationally infeasible global searches, thereby enhancing the reliability of causal discovery in complex, high-variance settings where such local errors are common.</p></div>","PeriodicalId":46050,"journal":{"name":"Artificial Life and Robotics","volume":"31 1","pages":"317 - 326"},"PeriodicalIF":0.8,"publicationDate":"2025-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147342303","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

Self-corrective behavior for turn repetition in pill bugs 药丸虫重复回合的自我纠正行为

IF 0.8

Artificial Life and Robotics Pub Date : 2025-11-25 DOI: 10.1007/s10015-025-01092-4

Yuta Miyama, Ayaka Fujimoto, Toru Moriyama

引用次数: 0

A study on constraint extraction and exception exclusion in care worker scheduling 护工调度中约束提取与例外排除的研究

IF 0.8

Artificial Life and Robotics Pub Date : 2025-11-17 DOI: 10.1007/s10015-025-01082-6

Koki Suenaga, Tomohiro Furuta, Satoshi Ono

引用次数: 0

ChatRAD: a robotic animation display system with text-to-image generative AI ChatRAD：一个具有文本到图像生成AI的机器人动画显示系统

IF 0.8

Artificial Life and Robotics Pub Date : 2025-11-11 DOI: 10.1007/s10015-025-01074-6

Masahiro Ishikane, Yanchun Li, Yuki Minami, Shinsaku Izumi, Masato Ishikawa

{"title":"ChatRAD: a robotic animation display system with text-to-image generative AI","authors":"Masahiro Ishikane, Yanchun Li, Yuki Minami, Shinsaku Izumi, Masato Ishikawa","doi":"10.1007/s10015-025-01074-6","DOIUrl":"10.1007/s10015-025-01074-6","url":null,"abstract":"<div><p>A multi-agent system is a system in which multiple agents cooperate to achieve a global objective. Each agent within the system can move independently and exchange information with other agents to collaborate in executing tasks. As an entertainment application of multi-agent systems, previous research has been conducted to realize a mass game in which a group of small robots displays static images. Additionally, with the recent advancements in text-to-image generative models (e.g., stable diffusion), image generative AI has rapidly gained popularity across various fields. In this paper, we propose ChatRAD, a system that integrates image generative AI with a multi-agent system, allowing a group of robots to display animations based on text input from users. We describe the detailed structure and functionality of the system, as well as the control laws governing the robot swarm. Numerical experiments are conducted using multiple target animations to evaluate the system’s performance. Furthermore, to enhance the quality of the displayed animations, we apply Bayesian optimization for gain tuning and verify its effectiveness using image evaluation indices.</p></div>","PeriodicalId":46050,"journal":{"name":"Artificial Life and Robotics","volume":"30 4","pages":"803 - 811"},"PeriodicalIF":0.8,"publicationDate":"2025-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145529539","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

Development of a cable-driven four-legged soft robot with wave-like locomotion 具有波浪运动的缆索驱动四足软机器人的研制

IF 0.8

Artificial Life and Robotics Pub Date : 2025-11-07 DOI: 10.1007/s10015-025-01086-2

Tomoya Inagaki, Klara Bezha, Kazuyuki Ito

引用次数: 0

Enhancing jumping robot performance through arm swing mechanisms 通过手臂摆动机制提高跳跃机器人的性能

IF 0.8

Artificial Life and Robotics Pub Date : 2025-11-06 DOI: 10.1007/s10015-025-01087-1

Cong Yan, Hinata Kato, Hiroto Ikeda, Yanqiu Zheng, Fumihiko Asano, Isao Tokuda

{"title":"Enhancing jumping robot performance through arm swing mechanisms","authors":"Cong Yan, Hinata Kato, Hiroto Ikeda, Yanqiu Zheng, Fumihiko Asano, Isao Tokuda","doi":"10.1007/s10015-025-01087-1","DOIUrl":"10.1007/s10015-025-01087-1","url":null,"abstract":"<div><p>This paper investigates the contribution of arm swing mechanisms to jumping robot performance through mathematical modeling, numerical simulation, and experimental validation. While extensive research has demonstrated the significance of arm swing in human and animal jumping biomechanics, this feature remains underutilized in robotic systems. We address three key questions: how coordinated arm swing affects horizontal jumping distance, what optimal arm swing parameters maximize performance, and how these parameters interact with other jumping variables. Our mathematical model incorporating arm dynamics reveals that optimized arm swing can enhance horizontal jumping distance by up to 35% compared to restricted arm configurations. Parametric analysis identifies optimal ranges for key variables: initial body angles of 0.3–0.65 rad, shorter arm swing durations, and specific arm swing amplitudes that do not necessarily correspond to maximum possible ranges. Experimental validation with our physical prototype achieved a 10% improvement in jumping distance, demonstrating the practical feasibility of this approach despite real-world constraints. These findings advance our understanding of arm-assisted jumping mechanisms and establish design principles for developing legged robots with extended mobility in critical environments.</p></div>","PeriodicalId":46050,"journal":{"name":"Artificial Life and Robotics","volume":"31 1","pages":"119 - 129"},"PeriodicalIF":0.8,"publicationDate":"2025-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147337797","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

ViT-XAI: vision transformer and XAI enable robust detection and cause localization in swarm anomalies ViT-XAI：视觉转换器和XAI实现了对群体异常的鲁棒检测和定位

IF 0.8

Artificial Life and Robotics Pub Date : 2025-11-05 DOI: 10.1007/s10015-025-01084-4

Yohei Fukuyama, Masao Kubo, Hiroshi Sato

{"title":"ViT-XAI: vision transformer and XAI enable robust detection and cause localization in swarm anomalies","authors":"Yohei Fukuyama, Masao Kubo, Hiroshi Sato","doi":"10.1007/s10015-025-01084-4","DOIUrl":"10.1007/s10015-025-01084-4","url":null,"abstract":"<div><p>While detecting a decline in collective performance is often straightforward, localizing the root cause can be significantly more challenging—particularly in systems characterized by dynamic relationships and complex interdependencies. To address this challenge, several studies have attempted to utilize explainable AI (XAI) techniques to localize causative agents. However, these approaches have not achieved sufficient accuracy in root-cause localization. This study proposes a method that integrates the Vision Transformer (ViT) with Gradient Self-Attention Maps (Grad-SAM)—an XAI technique—to localize anomalous agents within a swarm system. To evaluate the effectiveness of the proposed approach, we conduct comparative experiments against conventional convolutional neural networks (CNNs) combined with Gradient-weighted Class Activation Mapping (Grad-CAM), using the Boid model as the swarm simulation environment. Our comparative experiments against CNN/Grad-CAM using the Boid model revealed that anomaly detection and cause localization are a dual challenge with different requirements for model architecture. While CNNs demonstrated superiority in anomaly detection, particularly in scenarios with rare anomalies, ViT showed a clear advantage in cause localization. Specifically, ViT’s Grad-SAM generates higher-resolution and more stable saliency maps than Grad-CAM, thereby achieving high robustness with minimal performance degradation under a practical fixed-threshold setting. Furthermore, it outperformed CNNs under more complex situations involving mixed anomalies and background noise, quantitatively demonstrating that the proposed method can be a more practical and reliable technique for cause localization.</p></div>","PeriodicalId":46050,"journal":{"name":"Artificial Life and Robotics","volume":"31 1","pages":"130 - 148"},"PeriodicalIF":0.8,"publicationDate":"2025-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147337051","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