Artificial Life and Robotics最新文献

{"title":"Topology and weight neuroevolution for social learning in robotic swarms","authors":"Motoaki Hiraga","doi":"10.1007/s10015-025-01078-2","DOIUrl":"10.1007/s10015-025-01078-2","url":null,"abstract":"<div><p>Social learning in robotic swarms enables robots to improve their behavior by exchanging or imitating the behavioral knowledge of their peers. This study focuses on embodied evolution, a form of social learning in which an evolutionary algorithm is distributed across a population of robots, allowing each robot to evolve its controllers onboard through local interactions. This study proposes a simple embodied evolution approach that enables robots to evolve both the topology and weights of their neural network controllers during operation. The proposed approach utilizes a topology and weight neuroevolution method that uses only mutations for genetic variation. The robot controllers are evolved using an embodied evolution framework in a two-target navigation task conducted in computer simulations. The experimental results in a simulated task environment demonstrate that the proposed approach exhibits better performance than conventional fixed-topology controllers.</p></div>","PeriodicalId":46050,"journal":{"name":"Artificial Life and Robotics","volume":"31 1","pages":"202 - 212"},"PeriodicalIF":0.8,"publicationDate":"2025-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147339938","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}

{"title":"Evolution and extraction of decision-making mechanisms in collective perception of a robotic swarm","authors":"Daichi Morimoto,&nbsp;Motoaki Hiraga,&nbsp;Kazuhiro Ohkura,&nbsp;Masaharu Munetomo","doi":"10.1007/s10015-025-01075-5","DOIUrl":"10.1007/s10015-025-01075-5","url":null,"abstract":"<div><p>This paper demonstrates the evolution and extraction approach for the controller of the robotic swarm. The collective perception task has received a lot of attention in the field of swarm robotics. In addition, recent studies showed that the evolutionary robotics (ER) approach successfully designed decision-making strategies for the task. This study focused on a detailed analysis of the evolved decision-making strategies. As in related work, the artificial neural network (ANN) was employed to approximate a decision-making mechanism. At first, we examined how the available information for ANN affects the performance of the collective perception task. Secondly, a visualization approach was proposed to extract evolved decision-making mechanisms from ANNs. The computer simulations showed that our visualization approach successfully extracted the evolved decision-making mechanisms as reusable or analyzable by any others.</p></div>","PeriodicalId":46050,"journal":{"name":"Artificial Life and Robotics","volume":"31 1","pages":"90 - 102"},"PeriodicalIF":0.8,"publicationDate":"2025-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10015-025-01075-5.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147337662","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}

{"title":"Investigating the relationship between chronic stress and facial features at distinct wavelengths using independent component analysis","authors":"Masahito Takano,&nbsp;Miyu Kimura,&nbsp;Kent Nagumo,&nbsp;Yasushi Nanai,&nbsp;Kosuke Oiwa,&nbsp;Akio Nozawa","doi":"10.1007/s10015-025-01072-8","DOIUrl":"10.1007/s10015-025-01072-8","url":null,"abstract":"<div><p>This study presents a novel approach for objective chronic stress assessment using multi-wavelength facial imagery and independent component analysis (ICA). We investigated the relationship between facial images captured across distinct spectral bands (infrared, near-infrared (780–900 nm, 900–1700 nm), and visible (<i>L</i>*, <i>a</i>*, <i>b</i>*)) and participants’ chronic stress scores. Applying ICA, we identified statistically independent facial features and found significant correlations between their component weights and chronic stress levels. Notably, visible and infrared wavelengths exhibited robust and more generalized correlations across participants compared to near-infrared. Our analysis revealed stress-correlated features predominantly in the perioral and periorbital regions, intriguing given their association with acute stress responses, yet suggesting distinct underlying physiological adaptations for chronic stress. This ICA-based method offers an interpretable and data-driven framework for uncovering subtle, persistent manifestations of chronic stress in the face, paving the way for scalable non-contact health monitoring solutions.</p></div>","PeriodicalId":46050,"journal":{"name":"Artificial Life and Robotics","volume":"30 4","pages":"794 - 802"},"PeriodicalIF":0.8,"publicationDate":"2025-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10015-025-01072-8.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145529558","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}

{"title":"Parameter dependency between upper body, lower limbs, and neural systems on walking performance: a modeling study","authors":"Kazuaki Yaegashi,&nbsp;Tomoya Kamimura,&nbsp;Akihito Sano","doi":"10.1007/s10015-025-01070-w","DOIUrl":"10.1007/s10015-025-01070-w","url":null,"abstract":"<div><p>Bipedal walking is a complex phenomenon generated through dynamic interactions between the upper body, lower limbs, and neural system. In this study, to explain the dynamic effect of these elements on walking, we propose a compass model with a vertical wobbling mass and control methods of legs imitating the neural system. The limit cycles of the model were numerically searched, and their stability, energy efficiency, and walking velocity were investigated. Consequently, specific types of solutions increased energy efficiency and walking velocity compared with a model without wobbling mass when the condition between the frequencies of the three elements satisfies the conditions for the resonance phenomenon. Moreover, we examined the relationship to actual human walking from the viewpoint of the vertical ground reaction force. We found that some solutions similar to actual human walking involved high walking performance. These results suggest that in actual human walking, three elements are adjusted appropriately in response to environmental interactions to walk efficiently.</p></div>","PeriodicalId":46050,"journal":{"name":"Artificial Life and Robotics","volume":"31 1","pages":"83 - 89"},"PeriodicalIF":0.8,"publicationDate":"2025-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147337652","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}

{"title":"EAW-YOLO11: enhanced YOLO11 network for underwater object detection","authors":"Cong Thanh Dang,&nbsp;Hiroshi Sato,&nbsp;Masao Kubo","doi":"10.1007/s10015-025-01067-5","DOIUrl":"10.1007/s10015-025-01067-5","url":null,"abstract":"<div><p>Underwater robotic systems face significant challenges in object detection due to the complexity of marine environments. To address these challenges, our previous work introduced EAW-YOLO11, an enhanced object detection network based on the YOLO11 architecture and specifically designed for underwater scenarios. In this model, we propose two novel modules: the EC3k2 module with Efficient Multi-scale Attention (EMA) for improved feature extraction and the C2AIFI module for effective feature integration. In addition, we adopt the Wise-IoU v3 loss function to enhance localization performance. In this extended study, we further refine EAW-YOLO11 to address the overfitting issues observed in the initial version, specifically adjusting the momentum parameter during training. Experimental results on the URPC2019 dataset show that EAW-YOLO11 achieves a 2.1% increase in mAP@0.5 compared to the baseline YOLO11, demonstrating strong performance even in blurred and low-visibility conditions. Further ablation studies and qualitative evaluations confirm that EAW-YOLO11 is a promising solution for real-world underwater robotic applications, including marine exploration and autonomous navigation. The code will be released at https://github.com/successdang99/EAW-YOLO11.</p></div>","PeriodicalId":46050,"journal":{"name":"Artificial Life and Robotics","volume":"30 4","pages":"773 - 785"},"PeriodicalIF":0.8,"publicationDate":"2025-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145529538","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}

{"title":"Reactive persistent surveillance by heterogeneous multi-agents with energy constraint","authors":"Shohei Kobayashi,&nbsp;Takehiro Higuchi","doi":"10.1007/s10015-025-01066-6","DOIUrl":"10.1007/s10015-025-01066-6","url":null,"abstract":"<div><p>When natural disasters occur, accurately assessing the situation in a changing environment requires rapid and persistent observation. This paper focuses on the problem of conducting persistent observations using heterogeneous multi-agents with different observation capabilities and maximum operational time. To enable long-term operations covering vast environments, agents must replenish energy resources such as batteries and fuel. In this research, we discuss a method for selecting the direction of movement for observation by calculating utility values based on mutual information and remaining energy. Since mutual information reflects the different observation capabilities of each agent type, agents can move to locations where they can obtain the most information through their own observations. Through utility value-based action determination, agents fundamentally decide their movement directions based on mutual information, but as their energy levels decrease, they become more likely to choose the shortest path to a supply station. To validate the proposed method, we conducted numerical experiments involving persistent observation simulations in two changing environments: a simplified artificial environment and an environment representing a large-scale disaster in progress. The experimental results confirm that our proposed method successfully enables heterogeneous multi-agents to perform reactive observations while resupplying energy.</p></div>","PeriodicalId":46050,"journal":{"name":"Artificial Life and Robotics","volume":"30 4","pages":"764 - 772"},"PeriodicalIF":0.8,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145529557","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}

{"title":"Form closure-based path-planning in obstacle-aided locomotion for snake robots","authors":"Irja Gravdahl,&nbsp;Jostein Løwer,&nbsp;Kristin Ytterstad Pettersen,&nbsp;Øyvind Stavdahl","doi":"10.1007/s10015-025-01069-3","DOIUrl":"10.1007/s10015-025-01069-3","url":null,"abstract":"<div><p>Snake robots are hyperredundant manipulators with a wide range of potential applications ranging from search-and-rescue to ocean and outer space exploration. When snake robots use obstacles in the environment to push themselves forward it is referred to as obstacle-aided locomotion (OAL). The problem of finding a path that optimally exploits available obstacles in the environment for OAL currently does not have a general solution. A snake robot in contact with a set of obstacles is fundamentally similar to an object being grasped by a robotic hand. By interpreting the environment-robot contact as a grasp, we can employ the <i>form closure</i> concept for assessing the robustness of a given configuration; if the snake robot’s “grasp” of its environment has continual form closure when following a given path, the robot is guaranteed to not drift off that path. This presents a potential technique for analyzing the path-planning problem for OAL. This paper assesses the form closure of a rigid object on a planar surface by means of a novel method as well as a traditional method based on the grasp matrix. Furthermore, it introduces the notion of a <i>form closure margin</i> as a measure of how much a configuration must change before form closure is lost, and proposes three metrics that quantify this property. Finally, the applicability of the proposed metrics is demonstrated through their application to optimal path-planning for three specific scenarios. The results indicate that the proposed algorithm has strong potential to contribute to robust path-planning for OAL.</p></div>","PeriodicalId":46050,"journal":{"name":"Artificial Life and Robotics","volume":"31 1","pages":"185 - 201"},"PeriodicalIF":0.8,"publicationDate":"2025-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10015-025-01069-3.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147342862","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}

{"title":"Anisotropic texture control in 3D food printing through pitch adjustment and internal structural design","authors":"Yorito Igeta,&nbsp;Koki Fujiwara,&nbsp;Jun Ogawa,&nbsp;Hidemitsu Furukawa","doi":"10.1007/s10015-025-01065-7","DOIUrl":"10.1007/s10015-025-01065-7","url":null,"abstract":"<div><p>This study proposes a novel method for controlling anisotropic texture in 3D food printing using a single type of food ink. By adjusting the layer pitch and internal structure during printing, localized variations in hardness were achieved. Specifically, by introducing a “variable pitch technique”, rupture tests revealed that the hardness in the <i>Z</i>-direction increased as the pitch decreased, with values of 3.34 ± 0.29 N at 0.3 mm, 3.00 ± 0.33 N at 0.6 mm, and 1.89 ± 0.37 N at 0.9 mm. Additionally, wheel-shaped samples with different internal structures exhibited distinct fracture behaviors, confirming that internal design is effective for texture modulation. This technique enables personalized control of food texture based on individual chewing abilities, contributing to the realization of customized food experiences for medical and other special dietary needs.</p></div>","PeriodicalId":46050,"journal":{"name":"Artificial Life and Robotics","volume":"30 4","pages":"786 - 793"},"PeriodicalIF":0.8,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10015-025-01065-7.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145529673","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}

{"title":"Centralization vs. decentralization in multi-robot sweep coverage with ground robots and UAVs","authors":"Aryo Jamshidpey,&nbsp;Mostafa Wahby,&nbsp;Michael Allwright,&nbsp;Weixu Zhu,&nbsp;Marco Dorigo,&nbsp;Mary Katherine Heinrich","doi":"10.1007/s10015-025-01049-7","DOIUrl":"10.1007/s10015-025-01049-7","url":null,"abstract":"<div><p>In swarm robotics, decentralized control is often proposed as a more scalable and fault-tolerant alternative to centralized control. However, centralized behaviors are often faster and more efficient than their decentralized counterparts. In any given application, the goals and constraints of the task being solved should guide the choice to use centralized control, decentralized control, or a combination of the two. Currently, the exact trade-offs that exist between centralization and decentralization are not well defined. In this paper, we compare the performance of centralization and decentralization in the example task of sweep coverage, across five different types of multi-robot control structures: random walk, decentralized with beacons, hybrid formation control using self-organizing hierarchy, centralized formation control, and predetermined. In all five approaches, the coverage task is completed by a group of ground robots. In each approach, except for the random walk, the ground robots are assisted by UAVs, acting as supervisors or beacons. We compare the approaches in terms of three performance metrics for which centralized approaches are expected to have an advantage—coverage completeness, coverage uniformity, and sweep completion time—and two metrics for which decentralized approaches are expected to have an advantage—scalability (4, 8, or 16 ground robots) and fault tolerance (0%, 25%, 50%, or 75% ground robot failure). As expected, the results showed that the more centralized approaches greatly outperformed the decentralized ones in terms of coverage completeness, coverage uniformity, and sweep completion time. The decentralized approaches were less affected by robot failures and had better performance gains when the number of robots increased, but unexpectedly, these advantages only made their performance comparable to that of the more centralized approaches, not better than. Finally, we discuss future work on investigating additional conditions (e.g., bottlenecks, supervisor failures, and more complex environments), and on combining the advantages of both centralization and decentralization into one system.</p></div>","PeriodicalId":46050,"journal":{"name":"Artificial Life and Robotics","volume":"31 1","pages":"3 - 24"},"PeriodicalIF":0.8,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147341242","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}

{"title":"Growth stage detection for food consumption management in smart cricket farming using a deep learning technique","authors":"Nitipoom Nutnoi,&nbsp;Witoon Yindeesuk,&nbsp;Surachart Kamoldilok,&nbsp;Keerayoot Srinuanjan,&nbsp;Pichet Limsuwan","doi":"10.1007/s10015-025-01064-8","DOIUrl":"10.1007/s10015-025-01064-8","url":null,"abstract":"<div><p>This research proposed a novel method for tracking and predicting the growth stages of two-spotted crickets, reared in a temperature-controlled box at different growth stages using the YOLOv5s model. The images of crickets feeding inside the rearing box were taken with an infrared camera above the feeding point every hour. Images of the cricket were used to train a YOLOv5s model to detect crickets for each growth stage in the rearing box. The experimental results showed that the trained deep learning had an average accuracy of 95.7%. The relationship between the ratio of crickets at each growth stage throughout the 45-day rearing period was plotted and discussed. The results also showed a clear relationship between the amount of food consumed by crickets per day and their growth stage, which could be useful for appropriately managing food consumption according to the growth stage of crickets.</p></div>","PeriodicalId":46050,"journal":{"name":"Artificial Life and Robotics","volume":"30 4","pages":"733 - 741"},"PeriodicalIF":0.8,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145529656","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}