Pub Date : 2024-01-10DOI: 10.1177/10597123231225511
Mark M James
{"title":"Review of Thomas Fuchs—In Defense of the Human Being","authors":"Mark M James","doi":"10.1177/10597123231225511","DOIUrl":"https://doi.org/10.1177/10597123231225511","url":null,"abstract":"","PeriodicalId":55552,"journal":{"name":"Adaptive Behavior","volume":"8 6","pages":""},"PeriodicalIF":1.6,"publicationDate":"2024-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139439945","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-29DOI: 10.1177/10597123231222688
Shitao Zhang, Shanli Zhang, Hui Yang, Xiaodi Liu
The trust degree between individuals plays an important role in social network group decision-making (SNGDM). The majority of current literature assumes that the trust degree between individuals is constant. However, the trust values among decision-makers (DMs) are subject to change over time. Thus, it is necessary to identify potential dynamic trust that is compatible with the actual SNGDM to support the consensus reaching. For this purpose, this article investigates consensus building that considers dynamic trust among DMs in SNGDM with linguistic distribution assessments (LDAs). Firstly, the three-dimensional trust degree among DMs is constructed from three perspectives: the trust relationship from social networks, the confidence level of DMs, and the similarity of DMs' preferences. Secondly, an optimization model is developed with the objective of maximizing consensus to determine how trust degree is assigned to each perspective, thereby determining the weights of DMs. Then, a double feedback-based consensus mechanism incorporating both opinion evolution and trust evolution is developed. Under the guidance of consensus mechanism, an improved SNGDM approach with LDAs is presented. Finally, we demonstrate our proposed approach through a case study of sustainable supplier selection in a circular economy. Comparative analysis and sensitive analysis verify our approach’s effectiveness.
{"title":"Three-dimensional dynamic trust-driven consensus model for social network group decision-making with application to sustainable supplier selection in a circular economy","authors":"Shitao Zhang, Shanli Zhang, Hui Yang, Xiaodi Liu","doi":"10.1177/10597123231222688","DOIUrl":"https://doi.org/10.1177/10597123231222688","url":null,"abstract":"The trust degree between individuals plays an important role in social network group decision-making (SNGDM). The majority of current literature assumes that the trust degree between individuals is constant. However, the trust values among decision-makers (DMs) are subject to change over time. Thus, it is necessary to identify potential dynamic trust that is compatible with the actual SNGDM to support the consensus reaching. For this purpose, this article investigates consensus building that considers dynamic trust among DMs in SNGDM with linguistic distribution assessments (LDAs). Firstly, the three-dimensional trust degree among DMs is constructed from three perspectives: the trust relationship from social networks, the confidence level of DMs, and the similarity of DMs' preferences. Secondly, an optimization model is developed with the objective of maximizing consensus to determine how trust degree is assigned to each perspective, thereby determining the weights of DMs. Then, a double feedback-based consensus mechanism incorporating both opinion evolution and trust evolution is developed. Under the guidance of consensus mechanism, an improved SNGDM approach with LDAs is presented. Finally, we demonstrate our proposed approach through a case study of sustainable supplier selection in a circular economy. Comparative analysis and sensitive analysis verify our approach’s effectiveness.","PeriodicalId":55552,"journal":{"name":"Adaptive Behavior","volume":"99 10","pages":""},"PeriodicalIF":1.6,"publicationDate":"2023-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139146899","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-29DOI: 10.1177/10597123231218756
Tyler Duffrin, J. Wagman
Studies have shown that, to a large extent, performance of a given perceptual task is independent of the specific sensitivities of the anatomical components used to perform that task. Consequently, the object of calibration—what it is that people become calibrated to when performing a given perceptual task—may be likewise independent of the specific sensitivities of the anatomical components used to perform that task. The experiment reported here used a transfer of calibration paradigm to investigate this hypothesis as well as the more specific hypothesis that the object of calibration is independent of the sensitivity of a given anatomical component to the particulars of a given energy form. In a pretest and posttest, participants perceived the distance of an occluded surface by two different modalities—by exploring that surface with a wooden rod and by doing so with and Enactive Torch, a vibrotactile sensory-substitution device. In a practice session, we manipulated which modality participants used to perform this task (Rod or Enactive Torch) and whether feedback about performance was provided. We found that, when feedback was provided during the practice session, recalibration of perception of surface distance transferred from the rod to the Enactive Torch, and vice versa. This pattern of results is consistent with the hypothesis that the object of calibration in this perceptual task is (potentially) independent of the particular form of mechanical energy generated when exploring the surface.
{"title":"Transfer of Recalibration in Perceiving Surface Distance With a Haptic Sensory Substitution Device","authors":"Tyler Duffrin, J. Wagman","doi":"10.1177/10597123231218756","DOIUrl":"https://doi.org/10.1177/10597123231218756","url":null,"abstract":"Studies have shown that, to a large extent, performance of a given perceptual task is independent of the specific sensitivities of the anatomical components used to perform that task. Consequently, the object of calibration—what it is that people become calibrated to when performing a given perceptual task—may be likewise independent of the specific sensitivities of the anatomical components used to perform that task. The experiment reported here used a transfer of calibration paradigm to investigate this hypothesis as well as the more specific hypothesis that the object of calibration is independent of the sensitivity of a given anatomical component to the particulars of a given energy form. In a pretest and posttest, participants perceived the distance of an occluded surface by two different modalities—by exploring that surface with a wooden rod and by doing so with and Enactive Torch, a vibrotactile sensory-substitution device. In a practice session, we manipulated which modality participants used to perform this task (Rod or Enactive Torch) and whether feedback about performance was provided. We found that, when feedback was provided during the practice session, recalibration of perception of surface distance transferred from the rod to the Enactive Torch, and vice versa. This pattern of results is consistent with the hypothesis that the object of calibration in this perceptual task is (potentially) independent of the particular form of mechanical energy generated when exploring the surface.","PeriodicalId":55552,"journal":{"name":"Adaptive Behavior","volume":"192 1","pages":""},"PeriodicalIF":1.6,"publicationDate":"2023-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139211038","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-18DOI: 10.1177/10597123231215524
J. Fernandez-Leon, Luca Sarramone
Under the “spatial modulation continuous attractor network” (SCAN) model, insightful theoretical discussions have been proposed arguing that no direct sensory input signaling velocity to grid cells is required during locomotion, and no place cell activity seems to constitute a summation of grid cells. The model focuses less on explaining the dynamic relationship between place and grid cells as a fundamental component for coding space and time. This commentary highlights, however, that the place-grid coupled dynamics could represent the core mechanism that keeps coherent spatial coded information. This coupling mode between grid- and place-cells seems weak in SCAN, but it is irreducible and crucial for cognitive mapping.
{"title":"Making Room for the Place-Grid Coupled Dynamics","authors":"J. Fernandez-Leon, Luca Sarramone","doi":"10.1177/10597123231215524","DOIUrl":"https://doi.org/10.1177/10597123231215524","url":null,"abstract":"Under the “spatial modulation continuous attractor network” (SCAN) model, insightful theoretical discussions have been proposed arguing that no direct sensory input signaling velocity to grid cells is required during locomotion, and no place cell activity seems to constitute a summation of grid cells. The model focuses less on explaining the dynamic relationship between place and grid cells as a fundamental component for coding space and time. This commentary highlights, however, that the place-grid coupled dynamics could represent the core mechanism that keeps coherent spatial coded information. This coupling mode between grid- and place-cells seems weak in SCAN, but it is irreducible and crucial for cognitive mapping.","PeriodicalId":55552,"journal":{"name":"Adaptive Behavior","volume":"20 3","pages":""},"PeriodicalIF":1.6,"publicationDate":"2023-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139262279","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-02DOI: 10.1177/10597123231208034
Matheus Belizário Brito, Gisele Chiozi Gotardi, Sérgio Tosi Rodrigues, Daniela Godoi Jacomassi, Cédrick T Bonnet, Paula Fávaro Polastri
We investigated whether the adaptation of postural control to perform saccadic tasks is still maintained in challenging situations such as when the posture is challenged with a large movement of the moving room and with the addition of a second perturbation as a visual task of memorization. Thirty young adults (20.0 ± 1.3 years) were randomly assigned to the control and experimental groups. Participants stood upright on a force plate inside a moving room wearing eye-tracking. The room moved back and forth (anterior–posterior direction), at low (.6 cm—first and third trials) and high (3.5 cm—second trial) amplitude, and frequency of .2 Hz. In each trial, participants performed left-right horizontal saccades on a target (1.1 Hz). The experimental group also performed a concomitant number memorization task. There were no differences between groups in the coupling between center of pressure (CoP) displacements and visual stimulus in any condition. There was also no difference in the performance of the saccadic task. In the memorization task, CoP displacements in response to the visual stimulus frequency (room motion) were not affected. The performance in the memorization task was similar between room conditions. Overall, increasing cognitive involvement by adding a working memory task does not deteriorate the postural stabilization of young adults to accomplish accurate gaze shifts. Also, it does not interfere with adaptive visual reweighting due to changes in the moving room amplitude. In conclusion, young adults are flexible in optimizing their postural control to succeed in multiple tasks even under perturbation.
{"title":"Functional relation between postural sway and saccadic eye movements is strong and not altered by moving visual environment and concomitant memory task","authors":"Matheus Belizário Brito, Gisele Chiozi Gotardi, Sérgio Tosi Rodrigues, Daniela Godoi Jacomassi, Cédrick T Bonnet, Paula Fávaro Polastri","doi":"10.1177/10597123231208034","DOIUrl":"https://doi.org/10.1177/10597123231208034","url":null,"abstract":"We investigated whether the adaptation of postural control to perform saccadic tasks is still maintained in challenging situations such as when the posture is challenged with a large movement of the moving room and with the addition of a second perturbation as a visual task of memorization. Thirty young adults (20.0 ± 1.3 years) were randomly assigned to the control and experimental groups. Participants stood upright on a force plate inside a moving room wearing eye-tracking. The room moved back and forth (anterior–posterior direction), at low (.6 cm—first and third trials) and high (3.5 cm—second trial) amplitude, and frequency of .2 Hz. In each trial, participants performed left-right horizontal saccades on a target (1.1 Hz). The experimental group also performed a concomitant number memorization task. There were no differences between groups in the coupling between center of pressure (CoP) displacements and visual stimulus in any condition. There was also no difference in the performance of the saccadic task. In the memorization task, CoP displacements in response to the visual stimulus frequency (room motion) were not affected. The performance in the memorization task was similar between room conditions. Overall, increasing cognitive involvement by adding a working memory task does not deteriorate the postural stabilization of young adults to accomplish accurate gaze shifts. Also, it does not interfere with adaptive visual reweighting due to changes in the moving room amplitude. In conclusion, young adults are flexible in optimizing their postural control to succeed in multiple tasks even under perturbation.","PeriodicalId":55552,"journal":{"name":"Adaptive Behavior","volume":"26 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135875553","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-30DOI: 10.1177/10597123231208462
Kumar Gaurav, Prabhat Ranjan
Any odor cue can be traced to find its release source. So-called “source localization” has been observed in animals in many important tasks including finding food or mates. In particular, the scientific community for a long time focused on unraveling the complex behavior of moths while in pursuit of sex pheromones emitted by their distant female counterpart. These studies have provided many insights including details of the flight paths, sensory organs, and pheromone processing. In turn, this knowledge has provided inspiration to engineers and researchers to devise source-seeking algorithms, whereas sensory organs/-mechanisms led to insect-machine hybrid systems. Therefore, this review revolves around these last two approaches specifically (1) the implementation of moth-inspired algorithms in robotic platforms and the (2) use of biosensors such as antennae or insect-machine hybrid systems.
{"title":"Moth-inspired odor source localization using robotic platforms: A comprehensive review","authors":"Kumar Gaurav, Prabhat Ranjan","doi":"10.1177/10597123231208462","DOIUrl":"https://doi.org/10.1177/10597123231208462","url":null,"abstract":"Any odor cue can be traced to find its release source. So-called “source localization” has been observed in animals in many important tasks including finding food or mates. In particular, the scientific community for a long time focused on unraveling the complex behavior of moths while in pursuit of sex pheromones emitted by their distant female counterpart. These studies have provided many insights including details of the flight paths, sensory organs, and pheromone processing. In turn, this knowledge has provided inspiration to engineers and researchers to devise source-seeking algorithms, whereas sensory organs/-mechanisms led to insect-machine hybrid systems. Therefore, this review revolves around these last two approaches specifically (1) the implementation of moth-inspired algorithms in robotic platforms and the (2) use of biosensors such as antennae or insect-machine hybrid systems.","PeriodicalId":55552,"journal":{"name":"Adaptive Behavior","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136019065","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-23DOI: 10.1177/10597123231206604
Samuel C Bellini-Leite
State-of-the-art Large Language Models have recently exhibited extraordinary linguistic abilities which have surprisingly extended to reasoning. However, responses that are unreliable, false, or invented are still a frequent issue. It has been argued that scaling up strategies, as in increasing model size or hardware power, might not be enough to resolve the issue. Recent research has implemented Type 2 strategies (such as Chain-of-Thought and Tree-of-Thought), as strategies that mimic Type 2 reasoning, from Dual Process Theory, to interact with Large Language Models for improved results. The current paper reviews these strategies in light of the Predicting and Reflecting Framework for understanding Dual Process Theory and suggests what Psychology, drawing from research in executive functions, thinking disposition and creativity, can further contribute to possible implementations that address hallucination and reliability issues.
{"title":"Dual Process Theory for Large Language Models: An overview of using Psychology to address hallucination and reliability issues","authors":"Samuel C Bellini-Leite","doi":"10.1177/10597123231206604","DOIUrl":"https://doi.org/10.1177/10597123231206604","url":null,"abstract":"State-of-the-art Large Language Models have recently exhibited extraordinary linguistic abilities which have surprisingly extended to reasoning. However, responses that are unreliable, false, or invented are still a frequent issue. It has been argued that scaling up strategies, as in increasing model size or hardware power, might not be enough to resolve the issue. Recent research has implemented Type 2 strategies (such as Chain-of-Thought and Tree-of-Thought), as strategies that mimic Type 2 reasoning, from Dual Process Theory, to interact with Large Language Models for improved results. The current paper reviews these strategies in light of the Predicting and Reflecting Framework for understanding Dual Process Theory and suggests what Psychology, drawing from research in executive functions, thinking disposition and creativity, can further contribute to possible implementations that address hallucination and reliability issues.","PeriodicalId":55552,"journal":{"name":"Adaptive Behavior","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135412120","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-29DOI: 10.1177/10597123231204627
Feza Kerestecioğlu, Ümit Şen, Çağrı Işıkver, Ahmet Göktekin
Local strategies, which are based on cost minimization, to achieve circular formations of autonomous robot groups are presented. It is assumed that the group members have no communication capabilities or any means of interchanging information among themselves, and that they can only rely on their sensors, which provide relative positions of their nearby group members. It is verified on simulations that via appropriately defined cost functions arc, arc-triangle and circle formations are obtained, which can be maintained during navigation.
{"title":"Circular formations of non-communicating robot groups via local strategies","authors":"Feza Kerestecioğlu, Ümit Şen, Çağrı Işıkver, Ahmet Göktekin","doi":"10.1177/10597123231204627","DOIUrl":"https://doi.org/10.1177/10597123231204627","url":null,"abstract":"Local strategies, which are based on cost minimization, to achieve circular formations of autonomous robot groups are presented. It is assumed that the group members have no communication capabilities or any means of interchanging information among themselves, and that they can only rely on their sensors, which provide relative positions of their nearby group members. It is verified on simulations that via appropriately defined cost functions arc, arc-triangle and circle formations are obtained, which can be maintained during navigation.","PeriodicalId":55552,"journal":{"name":"Adaptive Behavior","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135193916","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-15DOI: 10.1177/10597123231201655
Vittorio Giammarino, Matthew F Dunne, Kylie N Moore, Michael E Hasselmo, Chantal E Stern, Ioannis Ch Paschalidis
We develop a framework to learn bio-inspired foraging policies using human data. We conduct an experiment where humans are virtually immersed in an open field foraging environment and are trained to collect the highest amount of rewards. A Markov Decision Process (MDP) framework is introduced to model the human decision dynamics. Then, Imitation Learning (IL) based on maximum likelihood estimation is used to train Neural Networks (NN) that map human decisions to observed states. The results show that passive imitation substantially underperforms humans. We further refine the human-inspired policies via Reinforcement Learning (RL) using the on-policy Proximal Policy Optimization (PPO) algorithm which shows better stability than other algorithms and can steadily improve the policies pre-trained with IL. We show that the combination of IL and RL match human performance and that the artificial agents trained with our approach can quickly adapt to reward distribution shift. We finally show that good performance and robustness to reward distribution shift strongly depend on combining allocentric information with an egocentric representation of the environment.
{"title":"Combining imitation and deep reinforcement learning to human-level performance on a virtual foraging task","authors":"Vittorio Giammarino, Matthew F Dunne, Kylie N Moore, Michael E Hasselmo, Chantal E Stern, Ioannis Ch Paschalidis","doi":"10.1177/10597123231201655","DOIUrl":"https://doi.org/10.1177/10597123231201655","url":null,"abstract":"We develop a framework to learn bio-inspired foraging policies using human data. We conduct an experiment where humans are virtually immersed in an open field foraging environment and are trained to collect the highest amount of rewards. A Markov Decision Process (MDP) framework is introduced to model the human decision dynamics. Then, Imitation Learning (IL) based on maximum likelihood estimation is used to train Neural Networks (NN) that map human decisions to observed states. The results show that passive imitation substantially underperforms humans. We further refine the human-inspired policies via Reinforcement Learning (RL) using the on-policy Proximal Policy Optimization (PPO) algorithm which shows better stability than other algorithms and can steadily improve the policies pre-trained with IL. We show that the combination of IL and RL match human performance and that the artificial agents trained with our approach can quickly adapt to reward distribution shift. We finally show that good performance and robustness to reward distribution shift strongly depend on combining allocentric information with an egocentric representation of the environment.","PeriodicalId":55552,"journal":{"name":"Adaptive Behavior","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135436246","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-15DOI: 10.1177/10597123231202593
Arash Sadeghi Amjadi, Cem Bilaloğlu, Ali Emre Turgut, Seongin Na, Erol Şahin, Tomáš Krajník, Farshad Arvin
Aggregation, the gathering of individuals into a single group as observed in animals such as birds, bees, and amoeba, is known to provide protection against predators or resistance to adverse environmental conditions for the whole. Cue-based aggregation, where environmental cues determine the location of aggregation, is known to be challenging when the swarm density is low. Here, we propose a novel aggregation method applicable to real robots in low-density swarms. Previously, Landmark-Based Aggregation (LBA) method had used odometric dead-reckoning coupled with visual landmarks and yielded better aggregation in low-density swarms. However, the method’s performance was affected adversely by odometry drift, jeopardizing its application in real-world scenarios. In this article, a novel Reinforcement Learning-based Aggregation method, RLA, is proposed to increase aggregation robustness, thus making aggregation possible for real robots in low-density swarm settings. Systematic experiments conducted in a kinematic-based simulator and on real robots have shown that the RLA method yielded larger aggregates, is more robust to odometry noise than the LBA method, and adapts better to environmental changes while not being sensitive to parameter tuning, making it better deployable under real-world conditions.
{"title":"Reinforcement learning-based aggregation for robot swarms","authors":"Arash Sadeghi Amjadi, Cem Bilaloğlu, Ali Emre Turgut, Seongin Na, Erol Şahin, Tomáš Krajník, Farshad Arvin","doi":"10.1177/10597123231202593","DOIUrl":"https://doi.org/10.1177/10597123231202593","url":null,"abstract":"Aggregation, the gathering of individuals into a single group as observed in animals such as birds, bees, and amoeba, is known to provide protection against predators or resistance to adverse environmental conditions for the whole. Cue-based aggregation, where environmental cues determine the location of aggregation, is known to be challenging when the swarm density is low. Here, we propose a novel aggregation method applicable to real robots in low-density swarms. Previously, Landmark-Based Aggregation (LBA) method had used odometric dead-reckoning coupled with visual landmarks and yielded better aggregation in low-density swarms. However, the method’s performance was affected adversely by odometry drift, jeopardizing its application in real-world scenarios. In this article, a novel Reinforcement Learning-based Aggregation method, RLA, is proposed to increase aggregation robustness, thus making aggregation possible for real robots in low-density swarm settings. Systematic experiments conducted in a kinematic-based simulator and on real robots have shown that the RLA method yielded larger aggregates, is more robust to odometry noise than the LBA method, and adapts better to environmental changes while not being sensitive to parameter tuning, making it better deployable under real-world conditions.","PeriodicalId":55552,"journal":{"name":"Adaptive Behavior","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135395694","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：