Artificial Life and Robotics最新文献_第4页

Interactive design and evaluation process for ear-EEG SSVEP-BCI 耳-脑SSVEP-BCI交互设计与评价过程

IF 0.8

Artificial Life and Robotics Pub Date : 2026-01-08 DOI: 10.1007/s10015-025-01105-2

Sodai Kondo, Hisaya Tanaka

{"title":"Interactive design and evaluation process for ear-EEG SSVEP-BCI","authors":"Sodai Kondo, Hisaya Tanaka","doi":"10.1007/s10015-025-01105-2","DOIUrl":"10.1007/s10015-025-01105-2","url":null,"abstract":"<div><p>The steady-state visual evoked potential (SSVEP) is a neural response with excellent information transmission capability, which makes it an attractive input source for brain-computer interfaces (BCI). The SSVEP is obtained from an electroencephalogram (EEG), which is typically measured on the scalp. Ear-EEG is more convenient and comfortable for the user because the ear is hairless, but the ear-EEG signal suffers from more attenuation than the conventional EEG signal. Designing an ear-EEG SSVEP-BCI and evaluating its performance is a long and extensive process owing to the need for long-term tests with multiple subjects. We previously developed a method for predicting the performance of an ear-EEG SSVEP-BCI using a small number of trials but did not sufficiently explore its versatility and applicability. In this study, we developed an interactive BCI design and evaluation process using multiple methods and datasets. The results showed that the K-nearest neighbors and curve-fitting methods could both be used to successfully predict the BCI accuracy. In particular, we demonstrated that the BCI accuracy could be predicted even when the training and test data were independent of each other.</p></div>","PeriodicalId":46050,"journal":{"name":"Artificial Life and Robotics","volume":"31 1","pages":"327 - 336"},"PeriodicalIF":0.8,"publicationDate":"2026-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10015-025-01105-2.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147337959","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

HARVEE: research on AI-based hybrid system generating cooperative behavior between human and abstract object HARVEE：基于人工智能的混合系统在人与抽象对象之间产生合作行为的研究

IF 0.8

Artificial Life and Robotics Pub Date : 2026-01-06 DOI: 10.1007/s10015-025-01111-4

Ayano Yasui

引用次数: 0

Development of a biomimetic robot hand with faithful bone reproduction and simplified soft-tissue constraints 具有忠实骨复制和简化软组织约束的仿生机械手的研制

IF 0.8

Artificial Life and Robotics Pub Date : 2026-01-06 DOI: 10.1007/s10015-025-01102-5

Haruto Kimata, Satoshi Suenaga, Shuhei Ikemoto

引用次数: 0

Simulation and modular controller integration for self-reconfigurable robots with docking/undocking behaviors 具有对接/解对接行为的自重构机器人仿真与模块化控制器集成

IF 0.8

Artificial Life and Robotics Pub Date : 2026-01-05 DOI: 10.1007/s10015-025-01103-4

Guang Yang, Xixun Wang, Koki Harada, Shuhei Sugiura, Ryota Kinjo, Hiroshi Oku, Ryo Ariizumi, Fumitoshi Matsuno

{"title":"Simulation and modular controller integration for self-reconfigurable robots with docking/undocking behaviors","authors":"Guang Yang, Xixun Wang, Koki Harada, Shuhei Sugiura, Ryota Kinjo, Hiroshi Oku, Ryo Ariizumi, Fumitoshi Matsuno","doi":"10.1007/s10015-025-01103-4","DOIUrl":"10.1007/s10015-025-01103-4","url":null,"abstract":"<div><p>Modular self-reconfigurable robots (MSRRs) offer structural adaptability for diverse tasks and environments. However, simulating such robots presents challenges in handling dynamic topology and closed-loop connections. PhysX, a modern high-performance physics engine widely adopted in robotics simulators including Isaac Sim, provides efficient and stable simulation through its articulation system for tree-structured robots. Yet, this articulation mechanism inherently prohibits closed-loop topologies, which are common in MSRRs. To address this, we propose a hybrid simulation and control framework for MSRRs. First, we propose the <i>Soft-Constraint Joint (SCJ)</i>, a constraint mechanism implemented via articulation-excluded joints that enables loop formation and dynamic module connection without violating articulation assumptions. Second, we present a modular control architecture where each controller module encapsulates motion logic and can be automatically activated based on physical configuration. The proposed framework supports stable and scalable simulation of modular robots with seamless integration of perception, reconfiguration, and control. Experiments validate the effectiveness of the framework in handling multiple robot morphologies and in achieving reliable sim-to-real transfer.</p></div>","PeriodicalId":46050,"journal":{"name":"Artificial Life and Robotics","volume":"31 1","pages":"218 - 227"},"PeriodicalIF":0.8,"publicationDate":"2026-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147337291","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

Investigating vehicle size input strategies in deep reinforcement learning for cooperative autonomous driving 基于深度强化学习的协同自动驾驶车辆尺寸输入策略研究

IF 0.8

Artificial Life and Robotics Pub Date : 2025-12-29 DOI: 10.1007/s10015-025-01090-6

Akito Takenaka, Tomohiro Harada, Yukiya Miura, Kiyohiko Hattori, Johei Matuoka

{"title":"Investigating vehicle size input strategies in deep reinforcement learning for cooperative autonomous driving","authors":"Akito Takenaka, Tomohiro Harada, Yukiya Miura, Kiyohiko Hattori, Johei Matuoka","doi":"10.1007/s10015-025-01090-6","DOIUrl":"10.1007/s10015-025-01090-6","url":null,"abstract":"<div><p>This study explores cooperative control among multiple autonomous vehicles of varying sizes in a shared environment using deep reinforcement learning (DRL). Although our previous study demonstrated the feasibility of cooperative control in such mixed-size environments, it did not incorporate vehicle size information, meaning that vehicles were unaware of their own sizes or those of others. In this study, we propose a DRL method that explicitly considers vehicle size to enable more effective cooperative control. We integrate two approaches to utilizing size information: using only the vehicle’s own size, and using both the vehicle’s own size and neighboring vehicles’ sizes. Three encoding methods for representing size are also investigated. Simulation experiments are conducted using standard passenger cars, medium-duty trucks, and compact vehicles. Models are trained in two environments with different levels of vehicle type diversity and evaluated on unseen course layouts. Performance is assessed by collision rates and average lap times. The results show that incorporating vehicle size information improves generalization, especially when using only the vehicle’s own size and a relative encoding. This configuration achieves more stable cooperative behavior in environments with previously unseen vehicle types.</p></div>","PeriodicalId":46050,"journal":{"name":"Artificial Life and Robotics","volume":"31 2","pages":"585 - 597"},"PeriodicalIF":0.8,"publicationDate":"2025-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147938389","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

Parallelization of MOPSO/D on multi-core CPUs with virtual global best and overlap-aware partitioning 基于虚拟全局最优和重叠感知分区的多核cpu上的MOPSO/D并行化

IF 0.8

Artificial Life and Robotics Pub Date : 2025-12-20 DOI: 10.1007/s10015-025-01093-3

Mikiko Sato, Mitsuhiko Uchida, Yuji Sato

{"title":"Parallelization of MOPSO/D on multi-core CPUs with virtual global best and overlap-aware partitioning","authors":"Mikiko Sato, Mitsuhiko Uchida, Yuji Sato","doi":"10.1007/s10015-025-01093-3","DOIUrl":"10.1007/s10015-025-01093-3","url":null,"abstract":"<div><p>This paper proposes a parallelization method for accelerating MOPSO/D without degrading its solution accuracy. The approach uses particle swarm optimization (PSO) for solving multi-objective optimization problems. To address the computational overhead associated with increasing the swarm size, we introduce two distinct approaches within the decomposition-based MOPSO (MOPSO/D) framework. First, we present a virtual global best (Vgbest) method that enables efficient sharing of the best solutions found during the optimization process across parallel processing units. Second, we propose a method that divides the objective space so that subproblems assigned to each particle can be explored in parallel. Since partitioning the objective space tends to degrade solution accuracy near region boundaries, we propose a method for compensating by sharing historical local best solutions among neighboring cores. The distributed parallel MOPSO/D with the Vgbest method is implemented in Python on a multi-core CPU and evaluated using standard benchmark problems. Experimental results indicate that the proposed methods effectively reduce computation time, achieving up to approximately 2.15 times speedup, while generally maintaining comparable solution accuracy.</p></div>","PeriodicalId":46050,"journal":{"name":"Artificial Life and Robotics","volume":"31 2","pages":"536 - 546"},"PeriodicalIF":0.8,"publicationDate":"2025-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10015-025-01093-3.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147938373","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

Fault-tolerant control for multi-robot networks with redundant communication modules 具有冗余通信模块的多机器人网络容错控制

IF 0.8

Artificial Life and Robotics Pub Date : 2025-12-14 DOI: 10.1007/s10015-025-01094-2

Toru Murayama

引用次数: 0

UAV real-time visual navigation and obstacle perception based on dual-attention mechanisms and multimodal fusion 基于双注意机制和多模态融合的无人机实时视觉导航与障碍物感知

IF 0.8

Artificial Life and Robotics Pub Date : 2025-12-13 DOI: 10.1007/s10015-025-01099-x

Le Han, Hui Zhang, Nan An, Rui Wu

{"title":"UAV real-time visual navigation and obstacle perception based on dual-attention mechanisms and multimodal fusion","authors":"Le Han, Hui Zhang, Nan An, Rui Wu","doi":"10.1007/s10015-025-01099-x","DOIUrl":"10.1007/s10015-025-01099-x","url":null,"abstract":"<div><p>With the widespread application of unmanned aerial vehicle (UAV), the real-time perception and dynamic obstacle avoidance capabilities of visual navigation systems in complex environments have emerged as critical bottlenecks limiting autonomous operations. In dense obstacle scenarios, traditional visual navigation algorithms often fail due to insufficient feature extraction or temporal modeling deviations, proving inadequate for precise avoidance requirements in dynamic environments. This paper proposes DualAtt-DepthViT, a deep visual algorithm for UAV navigation that addresses challenges in obstacle perception and real-time control by integrating dual-attention mechanisms with multimodal weighted fusion. First, the spatial attention module dynamically focuses on obstacle edges and critical regions in depth images, significantly enhancing refined perception capability of local features. Simultaneously, the hierarchical weighting of historical motion states through hierarchical spatiotemporal attention LSTM ensures temporal consistency between short-term emergency avoidance and long-term path planning. Second, we introduce a multimodal adaptive fusion strategy that optimizes weight allocation for image, position, and attitude data through end-to-end learning, effectively mitigating information redundancy and conflicts inherent in conventional uniform fusion approaches. Furthermore, leveraging the global spatial modeling capacity of vision transformer (ViT) combined with the dynamic temporal prediction advantages of LSTM, our framework establishes an end-to-end mapping from obstacle semantic understanding to motion control. Experiments in the Flightmare simulation scenario show that the success rate of obstacle avoidance of this algorithm is improved by <span>(text {23.5%})</span> and the energy consumption is reduced by <span>(text {17.8%})</span> compared to the traditional model.</p></div>","PeriodicalId":46050,"journal":{"name":"Artificial Life and Robotics","volume":"31 2","pages":"622 - 634"},"PeriodicalIF":0.8,"publicationDate":"2025-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147938251","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

No tower information needed: an autonomous inspection route generation method based on target detection 不需要塔台信息：一种基于目标检测的自主检测路线生成方法

IF 0.8

Artificial Life and Robotics Pub Date : 2025-12-11 DOI: 10.1007/s10015-025-01088-0

Wei Wang, Qi Wang

{"title":"No tower information needed: an autonomous inspection route generation method based on target detection","authors":"Wei Wang, Qi Wang","doi":"10.1007/s10015-025-01088-0","DOIUrl":"10.1007/s10015-025-01088-0","url":null,"abstract":"<div><p>With the development of UAV technology, UAVs play an important role in power transmission line inspection work. In recent years, solutions that synthesize tower coordinates and features to generate inspection routes have gained popularity. However, such solutions rely on a prior tower knowledge such as latitude, longitude, and altitude, even though such information may be difficult to obtain accurately. To address this situation, this report proposes an autonomous planning method for inspection routes based on target detection. (1) We propose a lightweight detector based on YOLOv8. (2) Based on the detection results, we design a path planner that contains three stages, to complete the initial tower information estimation and correction, as well as the subsequent towers information estimation. The designed Yolo model can be run at 56 fps on an onboard computer equipped with RK3588. Multiple flight experiments of continuous tower inspection also proved the effectiveness of the designed navigation information estimator, which provides an important reference for the development of power inspection technology.</p></div>","PeriodicalId":46050,"journal":{"name":"Artificial Life and Robotics","volume":"31 1","pages":"149 - 158"},"PeriodicalIF":0.8,"publicationDate":"2025-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10015-025-01088-0.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147338349","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

CRAGE and GNN-based AI architecture for autonomous transitions in modular robots 基于CRAGE和gnn的模块化机器人自主过渡AI架构

IF 0.8

Artificial Life and Robotics Pub Date : 2025-12-10 DOI: 10.1007/s10015-025-01096-0

Kenichiro Satonaka, Ryusei Nishii, Ryota Kinjo, Seiichi Ohashi, Tomoya Negoro, Yuki Takagi, Hiroshi Oku, Yuki Tanigaki, Koki Harada, Ryo Ariizumi, Tomohiro Simomura, Guang Yang, Xixun Wang, Fumitoshi Matsuno

{"title":"CRAGE and GNN-based AI architecture for autonomous transitions in modular robots","authors":"Kenichiro Satonaka, Ryusei Nishii, Ryota Kinjo, Seiichi Ohashi, Tomoya Negoro, Yuki Takagi, Hiroshi Oku, Yuki Tanigaki, Koki Harada, Ryo Ariizumi, Tomohiro Simomura, Guang Yang, Xixun Wang, Fumitoshi Matsuno","doi":"10.1007/s10015-025-01096-0","DOIUrl":"10.1007/s10015-025-01096-0","url":null,"abstract":"<div><p>The Moonshot R&D project, “Self-evolving AI robot system for lunar exploration and human outpost construction,” aims to realize AI modular robots that integrate advanced physical capabilities with self-evolving AI learning. Modular robots face significant challenges in achieving optimal and rapid shape transitions due to the vast number of possible configurations. To tackle this challenge, we first developed a Graph Neural Network (GNN) designed to learn abstract structural features inherent to modular robots—such as functional equivalence and geometric symmetry. To enable effective training of such a GNN, we developed a novel isomorphism determination method called Canonical Robot Adaptive Graph Encode (CRAGE), which converts structural graphs into canonical strings for efficient and consistent comparison. This graph-to-string encoding makes it possible to identify structurally equivalent configurations with high accuracy and speed. Moreover, CRAGE allows for the rapid and scalable generation of high-quality training data for robot structures, isomorphism classification, and deformation path planning—providing essential input for the GNN. Experiments show that CRAGE achieves 100% accuracy in small- to medium-scale structures while reducing processing time by over 90% compared to conventional methods. GNNs trained on CRAGE-generated data accurately predicted Lv2 structural equivalence from Lv1 inputs, achieving up to 100% classification accuracy and demonstrating strong generalization across structural variations. Together, CRAGE and the GNN form a unified framework for fast and scalable transition planning, contributing to the realization of autonomous self-evolving modular robots.</p></div>","PeriodicalId":46050,"journal":{"name":"Artificial Life and Robotics","volume":"31 1","pages":"265 - 279"},"PeriodicalIF":0.8,"publicationDate":"2025-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147338237","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