Artificial Life and Robotics最新文献

{"title":"Bio-inspired projected gradient method for leader selection in minimum cost problem","authors":"Nam-Jin Park,&nbsp;Yeong-Ung Kim,&nbsp;Hyo-Sung Ahn","doi":"10.1007/s10015-025-01042-0","DOIUrl":"10.1007/s10015-025-01042-0","url":null,"abstract":"<div><p>Inspired by the independent and efficient synaptic connections in biological neural networks, this paper introduces the Diagonal Projected Gradient Method (DPGM), a bio-inspired approach to optimize leader selection in networks. Existing methods, such as the Trace-constraint-based Projected Gradient Method (TPGM) and the Orthonormal-constraint-based Projected Gradient Method (OPGM), impose constraints on the input matrix but suffer from redundancy and overlap in input connections, leading to distorted importance indices and suboptimal leader selection. DPGM employs a diagonal input matrix, ensuring that each input affects exactly one node, akin to how synapses independently influence specific neurons. By optimizing the input vector rather than a full matrix, this method simplifies the optimization process and mirrors the efficiency of biological systems, allowing the importance index to reflect the independent influence of each node accurately. We provide a convergence analysis of the proposed method and demonstrate through simulations on real-world networks that DPGM outperforms TPGM and OPGM in leader selection, resulting in improved control efficiency.</p></div>","PeriodicalId":46050,"journal":{"name":"Artificial Life and Robotics","volume":"31 1","pages":"25 - 33"},"PeriodicalIF":0.8,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147339199","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":"Vehicle motion planning for ride comfort without passenger feedback using linear MPC","authors":"Takumi Todaka,&nbsp;Kaito Sato,&nbsp;Kenji Sawada,&nbsp;Katsuhiko Sando","doi":"10.1007/s10015-025-01040-2","DOIUrl":"10.1007/s10015-025-01040-2","url":null,"abstract":"<div><p>Ride comfort is an emerging focus in autonomous driving, yet integrating passenger behavior into vehicle motion planning remains challenging due to the impracticality of real-time passenger state feedback and high computational demands. This paper proposes a solution that approximates Ideal Motion Planning (IMP)—which traditionally requires nonlinear model predictive control (NMPC) and passenger state feedback—using linear model predictive control (LMPC) with weight tuning via Bayesian optimization. Our method eliminates the need for passenger state feedback and reduces the computation time, allowing real-time implementation. Although simplifying the cost function to prioritize tracking and stability, we achieve vehicle motion that maintains ride comfort equivalent to IMP, as demonstrated in simulations. This approach offers a practical pathway to improve passenger comfort in autonomous vehicles without additional sensory input.</p></div>","PeriodicalId":46050,"journal":{"name":"Artificial Life and Robotics","volume":"30 4","pages":"584 - 593"},"PeriodicalIF":0.8,"publicationDate":"2025-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10015-025-01040-2.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145529604","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":"Development of a MaskNet-based posture estimation method for robot vision systems","authors":"Yu Iwai,&nbsp;Soma Fumoto,&nbsp;Masato Kitamura,&nbsp;Takeshi Nishida","doi":"10.1007/s10015-025-01041-1","DOIUrl":"10.1007/s10015-025-01041-1","url":null,"abstract":"<div><p>Real-time posture estimation based on incomplete three-dimensional (3D) measurements is crucial for vision systems used in industrial robots. Conventional systems rely on manual pre-registering of multiple partial point cloud models for each workpiece and often fail when the 3D sensor is repositioned or its viewpoint changes. To overcome this bottleneck, we extend a fast MaskNet + singular‑value‑decomposition framework. However, its time‑series estimates still fluctuate owing to sensor and inference noise. To improve accuracy under realistic conditions, MaskNet was retrained on a large ray‑casting‑augmented CAD dataset that simulates random sensor viewpoints, and a Kalman filter was introduced to suppress temporal noise. The new training enhances mask‑vector accuracy, and the Kalman filter suppresses temporal fluctuations. Experiments confirm that the proposed method operates in real time on standard hardware, requires no pre‑registration after sensor movement, and can be seamlessly incorporated into a robot vision system for reliable target‑picking tasks.</p></div>","PeriodicalId":46050,"journal":{"name":"Artificial Life and Robotics","volume":"30 4","pages":"594 - 602"},"PeriodicalIF":0.8,"publicationDate":"2025-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145529674","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":"Detection of anomalous individuals in swarm using explainable AI","authors":"Hiroshi Sato,&nbsp;Yohei Fukuyama,&nbsp;Masao Kubo,&nbsp;Haruta Isobe,&nbsp;Tomoyashu Deguchi","doi":"10.1007/s10015-025-01038-w","DOIUrl":"10.1007/s10015-025-01038-w","url":null,"abstract":"<div><p>Effective swarm management requires detecting individuals that negatively impact overall performance. This paper proposes a method using Explainable AI (XAI) to both detect swarm-level anomalies and identify the causative agents. We train a convolutional neural network (CNN)-based neural network to classify swarms as normal or abnormal, then use Grad-CAM (an XAI technique) to pinpoint the responsible individuals. We simulate swarms using the Boid model, introducing “anomaly agents” with slightly altered parameters for Alignment, Cohesion, and Separation. A novel model, adding a Lambda Layer to VGG16, is proposed and compared with standard CNNs (VGG16, ResNet50, DenseNet121, EfficientNetB0). The Lambda Layer model achieved the highest accuracy in both anomaly detection and agent identification. Experimental results show high accuracy in identifying agents with altered Alignment and Separation parameters. However, identifying agents with altered Cohesion is more challenging due to their proximity to normal agents, leading to increased misidentifications. The results demonstrate the effectiveness of combining CNNs and XAI for anomaly detection and root cause analysis in swarms.</p></div>","PeriodicalId":46050,"journal":{"name":"Artificial Life and Robotics","volume":"30 4","pages":"577 - 583"},"PeriodicalIF":0.8,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145529561","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":"Cooperative transportation of an object with a nonholonomic constraint by a swarm of nonholonomic robots","authors":"Yuto Fukao,&nbsp;Takahiro Endo,&nbsp;Fumitoshi Matsuno,&nbsp;Yoshihiro Morimoto,&nbsp;Tomoaki Shimizu,&nbsp;Daisuke Mizuno","doi":"10.1007/s10015-025-01039-9","DOIUrl":"10.1007/s10015-025-01039-9","url":null,"abstract":"<div><p>In this paper, we propose a novel distributed method for cooperative transportation of an object with passive fixed wheels using a swarm of nonholonomic differential-drive wheeled robots. Because each robot and the transported object have wheels fixed to them and do not slide along the axle direction, their velocity constraints are nonholonomic. Therefore, when the robots transport the object, all velocity constraints of the robots and the object must be satisfied simultaneously. Then, we propose a method that enables transporting the object while satisfying the constraints. Each robot finds the object’s instant center of rotation from the object’s desired velocity and angular velocity, and each robot finds its velocity input and angular velocity input to move while attaching to the object and directing each robot’s axle to the instant center of rotation. Each robot moves with its velocity input and angular velocity input, and robots transport the object. We verified the effectiveness of the proposed method in dynamic simulations.</p></div>","PeriodicalId":46050,"journal":{"name":"Artificial Life and Robotics","volume":"31 1","pages":"103 - 112"},"PeriodicalIF":0.8,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147336440","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":"How swarm size affects soldier crab swarming behavior","authors":"Claudio Feliciani,&nbsp;Hisashi Murakami,&nbsp;Takenori Tomaru,&nbsp;Yuto Uesugi,&nbsp;Sakurako Tanida,&nbsp;Yuta Nishiyama,&nbsp;Xiaolu Jia,&nbsp;Tamao Maeda","doi":"10.1007/s10015-025-01037-x","DOIUrl":"10.1007/s10015-025-01037-x","url":null,"abstract":"<div><p>Collective vigilance has commonly been considered as one of the possible hypotheses explaining swarming in (social) animals. According to this theory, by engaging in cooperative monitoring of the environment, groups of social animals can enhance threat detection and overall survival. At the same time, this enables them to spend more time foraging and engaging in social activities. In this study, we report a behavior observed in soldier crabs challenging some aspects of collective vigilance. Laboratory experiments were performed at three swarm density levels (low, medium, and high) to check whether crabs are able to collectively adapt their motion to the changing environment (a moving light). Results show that only medium densities allow dynamic realignment with the moving light, whereas no collective motion is shown at low densities, and changes do not occur at high density. Experimental results were qualitatively backed by ecological observations, in which we show that above a specific threshold of swarm sizes, individuals fail to detect external threats (such as a passing bus) and/or do not change behavior in response to this environmental stimulus. In general, our results hint at the fact that the ability of swarms to collectively adapt to external conditions depends on swarm density. Further, we show that the ability to self-organize has a non-linear relationship with swarm density. Our study highlights the importance of considering complex systems from a closer microscopic perspective based on the ability of individuals to detect changes in the surrounding environment along with the interactions among them.</p></div>","PeriodicalId":46050,"journal":{"name":"Artificial Life and Robotics","volume":"31 1","pages":"69 - 76"},"PeriodicalIF":0.8,"publicationDate":"2025-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10015-025-01037-x.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147342654","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":"Synergistic development model of population growth and infrastructure networks based on the slime mold network","authors":"Megumi Uza,&nbsp;Airi Kinjo,&nbsp;Itsuki Kunita","doi":"10.1007/s10015-025-01035-z","DOIUrl":"10.1007/s10015-025-01035-z","url":null,"abstract":"<div><p>Developing efficient transportation infrastructure networks capable of accommodating increases in population and demand is essential in urban planning. The conventional approaches to urban planning involve simulations using mathematical models that incorporate temporal changes. The current models are often based on static factors like existing land and road networks. However, land use and road networks need to be adapted to environmental and systemic changes to better capture urban dynamics. In this study, we aimed to address this by proposing a novel synergistic development model of population growth and infrastructure networks inspired by the adaptive network formation of slime mold <i>Physarum polycephalum</i>. The proposed model builds on the Physarum solver by incorporating two dynamic processes: adding new source points and deleting sink points with low flow. Adding source points simulates population growth and increases infrastructure demand, whereas deleting sink points enhances network efficiency by removing redundant paths. The numerical simulations were conducted under various conditions to evaluate the effect of these processes on network formation. The results indicate that deleting sink points accelerates the convergence of the network by eliminating unnecessary paths. However, an increased flow can result in higher energy loss if the number of paths is insufficient. These findings indicate that adaptive feedback mechanisms, inspired by biological systems, play a crucial role in optimizing infrastructure networks in response to population growth, offering insights for flexible urban development strategies.</p></div>","PeriodicalId":46050,"journal":{"name":"Artificial Life and Robotics","volume":"30 3","pages":"523 - 533"},"PeriodicalIF":0.8,"publicationDate":"2025-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145168109","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":"Target specific multi-image 3D scrambling algorithm for security cameras","authors":"Abhijeet Ravankar,&nbsp;Arpit Rawankar,&nbsp;Ankit A. Ravankar","doi":"10.1007/s10015-025-01033-1","DOIUrl":"10.1007/s10015-025-01033-1","url":null,"abstract":"<div><p>With the proliferation of security cameras, image content protection is a major challenge. Image scrambling has increasingly been used for content protection as it does not degrade the quality of image. However, security cameras pose challenges of real-time implementation and target specific content protection. To this end, this paper presents a target specific, linear transform-based multi-image scrambling algorithm. The algorithm can scramble the image in 2D and 3D. Scrambling in 3D enables inter-image pixel scrambling which prevents brute-force attacks. The algorithm can be implemented using MMA (matrix–matrix multiply add) operation for parallel computing. A faster algorithm is proposed for serial computation. Both square and rectangular images can be scrambled. Along with complete image, targeted areas of the image can be scrambled in real time. The quality of scrambling is evaluated using PSNR (peak-signal-to-noise ratio) parameter. Experiment results with actual security cameras with motion detection feature shows that the proposed algorithm can be used in real time with high pixel irregularity for content protection.</p></div>","PeriodicalId":46050,"journal":{"name":"Artificial Life and Robotics","volume":"30 3","pages":"372 - 382"},"PeriodicalIF":0.8,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145165510","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":"Robots reading recipes: large language models as translators between humans and machines","authors":"Oliver Wang,&nbsp;Grant Cheng,&nbsp;Luc Caspar,&nbsp;Akira Yokota,&nbsp;Mahdi Khosravy,&nbsp;Olaf Witkowski","doi":"10.1007/s10015-025-01031-3","DOIUrl":"10.1007/s10015-025-01031-3","url":null,"abstract":"<div><p>Large Language Models (LLMs) are a type of machine learning model trained on vast amounts of natural language that have demonstrated novel capabilities in tasks such as text prediction and generation. These tasks allow LLMs to be remarkably suited for understanding the semantics of natural language, which in turn enables applications such as planning real world tasks, writing code for computers, and translating between human languages. Even though LLMs could provide more flexibility in interpreting user requests and have shown to possess some commonsense knowledge, their capabilities for translating natural language instructions into code to control robot actions is only starting to be explored. More specifically, in this paper we are interested in the control of robots tasked with preparing cocktails. Within this context, it is assumed that the LLM has access to a repository of well-formatted recipes. This means that each recipe is written according to the following layout: a list of ingredients, then a subsequent description of how to prepare and mix the various items. Moreover, a set of low-level modules responsible for robot manipulation and vision-related tasks is also provided to the LLM in the shape of an application programming interface (API). Consequently, the main focus of the LLM is on generating a sequence of calls to the API, along with the right parameters, to produce the cocktail requested by users in natural language. Here, we show that it is feasible for LLMs to perform this type of translation on a small number of custom modules, and that certain techniques provide a measurable benefit to the accuracy and consistency of this task without fine-tuning. We found in particular that the use of an ensemble-voting strategy, where multiple trials are repeated and the most common answer is selected, increases accuracy to a certain extent. In addition, there is moderate support for the use of natural language parsing to adjust the prompt of the LLM prior to translation. Lastly, building on previous knowledge we also provide a set of guidelines to help design prompts to improve the accuracy of the resulting sequence of actions. In general, these results suggest that while LLMs can be used as translators of robot instructions, they are best applied in conjunction with these other strategies. The impact of these findings could influence future robotics development, as it provides directions for implementing LLMs more effectively and broadening the accessibility of robotic control to users without an extensive software background.</p></div>","PeriodicalId":46050,"journal":{"name":"Artificial Life and Robotics","volume":"30 3","pages":"407 - 416"},"PeriodicalIF":0.8,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10015-025-01031-3.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145165228","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":"Novelty-based multi-objectivization for unbounded search space optimization","authors":"Ryuki Ishizawa,&nbsp;Hiroyuki Sato,&nbsp;Keiki Takadama","doi":"10.1007/s10015-025-01034-0","DOIUrl":"10.1007/s10015-025-01034-0","url":null,"abstract":"<div><p>Unlike the conventional swarm or evolutionary optimizations that are generally assumed the “pre-defined” bounded search space, this paper addresses the optimization for the “unbounded” search space. For this purpose, this paper proposes novelty-based multi-objectivization with local and rough area search (NM-LRS), which adds the novelty criterion in the given optimization criteria to roughly search the unbounded search space for obtaining the “potential area” where the optimal solution is most likely located and then searches the “potential area” to find the optimal solution by a local area search. To investigate the effectiveness of the proposed methods, the experiment compares the proposed methods with the conventional optimization methods for the unbounded multi-modal optimization and has revealed the following implications: (i) the peak ratio (<i>i</i>.<i>e</i>., the ratio of the founded peaks of the multi-modal function) of NM-LRS is higher than that of the conventional methods; and (ii) NM-LRS is robust for the location of the initial search area in the most functions.</p></div>","PeriodicalId":46050,"journal":{"name":"Artificial Life and Robotics","volume":"30 3","pages":"383 - 397"},"PeriodicalIF":0.8,"publicationDate":"2025-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10015-025-01034-0.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145164142","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}