Analogical proportions are statements of the form “a is to b as c is to d”, denoted a : b : : c : d, that may apply to any type of items a, b, c, d. Analogical proportions, as a building block for analogical reasoning, is then a tool of interest in artificial intelligence. Viewed as a relation between pairs ( a , b ) and ( c , d ), these proportions are supposed to obey three postulates: reflexivity, symmetry, and central permutation (i.e., b and c can be exchanged). The logical modeling of analogical proportions expresses that a and b differ in the same way as c and d, when the four items are represented by vectors encoding Boolean properties. When items are real numbers, numerical proportions – arithmetic and geometric proportions – can be considered as prototypical examples of analogical proportions. Taking inspiration of an old practice where numerical proportions were handled in a vectorial way and where sequences of numerical proportions of the form x 1 : x 2 : ⋯ : x n : : y 1 : y 2 : ⋯ : y n were in use, we emphasize a vectorial treatment of Boolean analogical proportions and we propose a Boolean logic counterpart to such sequences. This provides a linear algebra calculus of analogical inference and acknowledges the fact that analogical proportions should not be considered in isolation. Moreover, this also leads us to reconsider the postulates underlying analogical proportions (since central permutation makes no sense when n ⩾ 3) and then to formalize a weak form of analogical proportion which no longer obeys the central permutation postulate inherited from numerical proportions. But these weak proportions may still be combined in multiple weak analogical proportions.
类比比例是一种形式为“a与b之比就像c与d之比”的陈述，表示为a: b:: c: d，可以适用于任何类型的项目a, b, c, d。类比比例作为类比推理的基石，是人工智能的一个有趣工具。作为对(a, b)和(c, d)之间的关系，这些比例应该遵循三个假设:反身性、对称性和中心置换(即b和c可以交换)。类比比例的逻辑建模表示，当这四项用编码布尔属性的向量表示时，a和b的不同方式与c和d相同。当项目是实数时，数字比例——算术比例和几何比例——可以被视为类比比例的典型例子。从以向量方式处理数值比例的旧做法中获得灵感，其中使用形式为x 1: x 2:⋯:x n:: y 1: y 2:⋯:y n的数值比例序列，我们强调布尔类比比例的向量处理，并提出了布尔逻辑对应物。这提供了类比推理的线性代数演算，并承认类比比例不应孤立考虑的事实。此外，这也使我们重新考虑类比比例的基本假设(因为当n大于或等于3时中心排列没有意义)然后将类比比例的弱形式正式化它不再服从从数字比例继承的中心排列假设。但是这些弱比例仍然可以组合成多个弱类比比例。
{"title":"Multiple analogical proportions","authors":"H. Prade, G. Richard","doi":"10.3233/aic-210090","DOIUrl":"https://doi.org/10.3233/aic-210090","url":null,"abstract":"Analogical proportions are statements of the form “a is to b as c is to d”, denoted a : b : : c : d, that may apply to any type of items a, b, c, d. Analogical proportions, as a building block for analogical reasoning, is then a tool of interest in artificial intelligence. Viewed as a relation between pairs ( a , b ) and ( c , d ), these proportions are supposed to obey three postulates: reflexivity, symmetry, and central permutation (i.e., b and c can be exchanged). The logical modeling of analogical proportions expresses that a and b differ in the same way as c and d, when the four items are represented by vectors encoding Boolean properties. When items are real numbers, numerical proportions – arithmetic and geometric proportions – can be considered as prototypical examples of analogical proportions. Taking inspiration of an old practice where numerical proportions were handled in a vectorial way and where sequences of numerical proportions of the form x 1 : x 2 : ⋯ : x n : : y 1 : y 2 : ⋯ : y n were in use, we emphasize a vectorial treatment of Boolean analogical proportions and we propose a Boolean logic counterpart to such sequences. This provides a linear algebra calculus of analogical inference and acknowledges the fact that analogical proportions should not be considered in isolation. Moreover, this also leads us to reconsider the postulates underlying analogical proportions (since central permutation makes no sense when n ⩾ 3) and then to formalize a weak form of analogical proportion which no longer obeys the central permutation postulate inherited from numerical proportions. But these weak proportions may still be combined in multiple weak analogical proportions.","PeriodicalId":50835,"journal":{"name":"AI Communications","volume":"1992 1","pages":"211-228"},"PeriodicalIF":0.8,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89013405","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}
Several well known clustering algorithms have their own online counterparts, in order to deal effectively with the big data issue, as well as with the case where the data become available in a streaming fashion. However, very few of them follow the stochastic gradient descent philosophy, despite the fact that the latter enjoys certain practical advantages (such as the possibility of (a) running faster than their batch processing counterparts and (b) escaping from local minima of the associated cost function), while, in addition, strong theoretical convergence results have been established for it. In this paper a novel stochastic gradient descent possibilistic clustering algorithm, called O- PCM 2 is introduced. The algorithm is presented in detail and it is rigorously proved that the gradient of the associated cost function tends to zero in the L 2 sense, based on general convergence results established for the family of the stochastic gradient descent algorithms. Furthermore, an additional discussion is provided on the nature of the points where the algorithm may converge. Finally, the performance of the proposed algorithm is tested against other related algorithms, on the basis of both synthetic and real data sets.
{"title":"A new stochastic gradient descent possibilistic clustering algorithm","authors":"A. Koutsimpela, K. Koutroumbas","doi":"10.3233/aic-210125","DOIUrl":"https://doi.org/10.3233/aic-210125","url":null,"abstract":"Several well known clustering algorithms have their own online counterparts, in order to deal effectively with the big data issue, as well as with the case where the data become available in a streaming fashion. However, very few of them follow the stochastic gradient descent philosophy, despite the fact that the latter enjoys certain practical advantages (such as the possibility of (a) running faster than their batch processing counterparts and (b) escaping from local minima of the associated cost function), while, in addition, strong theoretical convergence results have been established for it. In this paper a novel stochastic gradient descent possibilistic clustering algorithm, called O- PCM 2 is introduced. The algorithm is presented in detail and it is rigorously proved that the gradient of the associated cost function tends to zero in the L 2 sense, based on general convergence results established for the family of the stochastic gradient descent algorithms. Furthermore, an additional discussion is provided on the nature of the points where the algorithm may converge. Finally, the performance of the proposed algorithm is tested against other related algorithms, on the basis of both synthetic and real data sets.","PeriodicalId":50835,"journal":{"name":"AI Communications","volume":"30 1","pages":"47-64"},"PeriodicalIF":0.8,"publicationDate":"2021-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85440793","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}
Markov Decision Process Models (MDPs) are a powerful tool for planning tasks and sequential decision-making issues. In this work we deal with MDPs with imprecise rewards, often used when dealing with situations where the data is uncertain. In this context, we provide algorithms for finding the policy that minimizes the maximum regret. To the best of our knowledge, all the regret-based methods proposed in the literature focus on providing an optimal stochastic policy. We introduce for the first time a method to calculate an optimal deterministic policy using optimization approaches. Deterministic policies are easily interpretable for users because for a given state they provide a unique choice. To better motivate the use of an exact procedure for finding a deterministic policy, we show some (theoretical and experimental) cases where the intuitive idea of using a deterministic policy obtained after “determinizing” the optimal stochastic policy leads to a policy far from the exact deterministic policy.
{"title":"Deterministic policies based on maximum regrets in MDPs with imprecise rewards","authors":"Pegah Alizadeh, Emiliano Traversi, A. Osmani","doi":"10.3233/aic-190632","DOIUrl":"https://doi.org/10.3233/aic-190632","url":null,"abstract":"Markov Decision Process Models (MDPs) are a powerful tool for planning tasks and sequential decision-making issues. In this work we deal with MDPs with imprecise rewards, often used when dealing with situations where the data is uncertain. In this context, we provide algorithms for finding the policy that minimizes the maximum regret. To the best of our knowledge, all the regret-based methods proposed in the literature focus on providing an optimal stochastic policy. We introduce for the first time a method to calculate an optimal deterministic policy using optimization approaches. Deterministic policies are easily interpretable for users because for a given state they provide a unique choice. To better motivate the use of an exact procedure for finding a deterministic policy, we show some (theoretical and experimental) cases where the intuitive idea of using a deterministic policy obtained after “determinizing” the optimal stochastic policy leads to a policy far from the exact deterministic policy.","PeriodicalId":50835,"journal":{"name":"AI Communications","volume":"1 1","pages":"229-244"},"PeriodicalIF":0.8,"publicationDate":"2021-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76909841","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}
In the diagnosis of chronic kidney disease, glomerulus as the blood filter provides important information for an accurate disease diagnosis. Thus automatic localization of the glomeruli is the necessary groundwork for future auxiliary kidney disease diagnosis, such as glomerular classification and area measurement. In this paper, we propose an efficient glomerular object locator in kidney whole slide image(WSI) based on proposal-free network and dynamic scale evaluation method. In the training phase, we construct an intensive proposal-free network which can learn efficiently the fine-grained features of the glomerulus. In the evaluation phase, a dynamic scale evaluation method is utilized to help the well-trained model find the most appropriate evaluation scale for each high-resolution WSI. We collect and digitalize 1204 renal biopsy microscope slides containing more than 41000 annotated glomeruli, which is the largest number of dataset to our best knowledge. We validate the each component of the proposed locator via the ablation study. Experimental results confirm that the proposed locator outperforms recently proposed approaches and pathologists by comparing F 1 and run time in localizing glomeruli from WSIs at a resolution of 0.25 μm/pixel and thus achieves state-of-the-art performance. Particularly, the proposed locator can be embedded into the renal intelligent auxiliary diagnosis system for renal clinical diagnosis by localizing glomeruli in high-resolution WSIs effectively.
{"title":"An efficient glomerular object locator for renal whole slide images using proposal-free network and dynamic scale evaluation method","authors":"Xueyu Liu, Ming Li, Yongfei Wu, Yilin Chen, Fang Hao, Daoxiang Zhou, Chen Wang, Chuan-lian Ma, Guangze Shi, Xiaoshuang Zhou","doi":"10.3233/aic-210073","DOIUrl":"https://doi.org/10.3233/aic-210073","url":null,"abstract":"In the diagnosis of chronic kidney disease, glomerulus as the blood filter provides important information for an accurate disease diagnosis. Thus automatic localization of the glomeruli is the necessary groundwork for future auxiliary kidney disease diagnosis, such as glomerular classification and area measurement. In this paper, we propose an efficient glomerular object locator in kidney whole slide image(WSI) based on proposal-free network and dynamic scale evaluation method. In the training phase, we construct an intensive proposal-free network which can learn efficiently the fine-grained features of the glomerulus. In the evaluation phase, a dynamic scale evaluation method is utilized to help the well-trained model find the most appropriate evaluation scale for each high-resolution WSI. We collect and digitalize 1204 renal biopsy microscope slides containing more than 41000 annotated glomeruli, which is the largest number of dataset to our best knowledge. We validate the each component of the proposed locator via the ablation study. Experimental results confirm that the proposed locator outperforms recently proposed approaches and pathologists by comparing F 1 and run time in localizing glomeruli from WSIs at a resolution of 0.25 μm/pixel and thus achieves state-of-the-art performance. Particularly, the proposed locator can be embedded into the renal intelligent auxiliary diagnosis system for renal clinical diagnosis by localizing glomeruli in high-resolution WSIs effectively.","PeriodicalId":50835,"journal":{"name":"AI Communications","volume":"65 1","pages":"245-258"},"PeriodicalIF":0.8,"publicationDate":"2021-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77486203","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}
Md Kamruzzaman Sarker, Lu Zhou, Aaron Eberhart, P. Hitzler
Neuro-Symbolic Artificial Intelligence – the combination of symbolic methods with methods that are based on artificial neural networks – has a long-standing history. In this article, we provide a structured overview of current trends, by means of categorizing recent publications from key conferences. The article is meant to serve as a convenient starting point for research on the general topic.
{"title":"Neuro-Symbolic Artificial Intelligence: Current Trends","authors":"Md Kamruzzaman Sarker, Lu Zhou, Aaron Eberhart, P. Hitzler","doi":"10.3233/aic-210084","DOIUrl":"https://doi.org/10.3233/aic-210084","url":null,"abstract":"Neuro-Symbolic Artificial Intelligence – the combination of symbolic methods with methods that are based on artificial neural networks – has a long-standing history. In this article, we provide a structured overview of current trends, by means of categorizing recent publications from key conferences. The article is meant to serve as a convenient starting point for research on the general topic.","PeriodicalId":50835,"journal":{"name":"AI Communications","volume":"71 1","pages":"197-209"},"PeriodicalIF":0.8,"publicationDate":"2021-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84435502","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}
Marin Lujak, Ivana Dusparic, Franziska Klügl-Frohnmeyer, G. Vizzari
Marin Lujak a,∗, Ivana Dusparic , Franziska Klügl c and Giuseppe Vizzari d a IMT Lille Douai, University of Lille, Douai, France E-mail: marin.lujak@imt-lille-douai.fr b School of Computer Science and Statistics, Trinity College Dublin, Ireland E-mail: ivana.dusparic@scss.tcd.ie c AASS, School of Science and Technology, Örebro University, Sweden E-mail: franziska.klugl@oru.se d Department of Informatics, Systems and Communication, University of Milano – Bicocca, Italy E-mail: giuseppe.vizzari@unimib.it
Marin Lujak a *， Ivana Dusparic, Franziska klggl c和Giuseppe Vizzari d a IMT，里尔杜埃大学，法国杜埃E-mail: marin.lujak@imt-lille-douai.fr b爱尔兰都柏林圣三一学院计算机科学与统计学院E-mail: ivana.dusparic@scss.tcd.ie c瑞典大学科学与技术学院，Örebro e- franziska.klugl@oru.se d意大利米兰大学信息、系统与通信系E-mail:giuseppe.vizzari@unimib.it
{"title":"Agents in Traffic and Transportation (ATT 2020)","authors":"Marin Lujak, Ivana Dusparic, Franziska Klügl-Frohnmeyer, G. Vizzari","doi":"10.3233/aic-201640","DOIUrl":"https://doi.org/10.3233/aic-201640","url":null,"abstract":"Marin Lujak a,∗, Ivana Dusparic , Franziska Klügl c and Giuseppe Vizzari d a IMT Lille Douai, University of Lille, Douai, France E-mail: marin.lujak@imt-lille-douai.fr b School of Computer Science and Statistics, Trinity College Dublin, Ireland E-mail: ivana.dusparic@scss.tcd.ie c AASS, School of Science and Technology, Örebro University, Sweden E-mail: franziska.klugl@oru.se d Department of Informatics, Systems and Communication, University of Milano – Bicocca, Italy E-mail: giuseppe.vizzari@unimib.it","PeriodicalId":50835,"journal":{"name":"AI Communications","volume":"233 1","pages":"1-3"},"PeriodicalIF":0.8,"publicationDate":"2021-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78297888","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}
Nested Rollout Policy Adaptation (NRPA) is a Monte Carlo search algorithm that learns a playout policy in order to solve a single player game. In this paper we apply NRPA to the vehicle routing problem. This problem is important for large companies that have to manage a fleet of vehicles on a daily basis. Real problems are often too large to be solved exactly. The algorithm is applied to standard problem of the literature and to the specific problems of EDF (Electricité De France, the main French electric utility company). These specific problems have peculiar constraints. NRPA gives better result than the algorithm previously used by EDF.
{"title":"Policy adaptation for vehicle routing","authors":"T. Cazenave, J. Lucas, T. Triboulet, Hyoseok Kim","doi":"10.3233/aic-201577","DOIUrl":"https://doi.org/10.3233/aic-201577","url":null,"abstract":"Nested Rollout Policy Adaptation (NRPA) is a Monte Carlo search algorithm that learns a playout policy in order to solve a single player game. In this paper we apply NRPA to the vehicle routing problem. This problem is important for large companies that have to manage a fleet of vehicles on a daily basis. Real problems are often too large to be solved exactly. The algorithm is applied to standard problem of the literature and to the specific problems of EDF (Electricité De France, the main French electric utility company). These specific problems have peculiar constraints. NRPA gives better result than the algorithm previously used by EDF.","PeriodicalId":50835,"journal":{"name":"AI Communications","volume":"1 1","pages":"21-35"},"PeriodicalIF":0.8,"publicationDate":"2021-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89676269","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}
The modeling of a new generation of agent-based simulation systems supporting pedestrian and crowd management taking into account affective states represents a new research frontier. Pedestrian behaviour involves human perception processes, based on subjective and psychological aspects. Following the concept of pedestrian environmental awareness, each walker adapts his/her crossing behaviour according to environmental conditions and his/her perception of safety. Different pedestrian behaviours can be related to subjective mobility and readiness to respond, and these factors are strongly dependent on the subjective interaction with the environment. Having additional inputs about pedestrian behaviour related to their perception processes could be useful in order to develop a more representative pedestrian dynamic model. In particular, the subjective perception of the safeness of crossing should be taken into consideration. In order to focus on the pedestrians’ perception of safe road crossing and walking, an experiment in an uncontrolled urban scenario has been carried out. Besides more conventional self-assessment questionnaires, physiological responses have been considered to evaluate the affective state of pedestrians during the interaction with the urban environment. Results from the analysis of the collected data show that physiological responses are reliable indicators of safety perception while road crossing and interacting with real urban environment, suggesting the design of agent-based models for pedestrian dynamics simulations taking in account the representation of affective states.
{"title":"Safety perception and pedestrian dynamics: Experimental results towards affective agents modeling","authors":"F. Gasparini, Marta Giltri, S. Bandini","doi":"10.3233/AIC-201576","DOIUrl":"https://doi.org/10.3233/AIC-201576","url":null,"abstract":"The modeling of a new generation of agent-based simulation systems supporting pedestrian and crowd management taking into account affective states represents a new research frontier. Pedestrian behaviour involves human perception processes, based on subjective and psychological aspects. Following the concept of pedestrian environmental awareness, each walker adapts his/her crossing behaviour according to environmental conditions and his/her perception of safety. Different pedestrian behaviours can be related to subjective mobility and readiness to respond, and these factors are strongly dependent on the subjective interaction with the environment. Having additional inputs about pedestrian behaviour related to their perception processes could be useful in order to develop a more representative pedestrian dynamic model. In particular, the subjective perception of the safeness of crossing should be taken into consideration. In order to focus on the pedestrians’ perception of safe road crossing and walking, an experiment in an uncontrolled urban scenario has been carried out. Besides more conventional self-assessment questionnaires, physiological responses have been considered to evaluate the affective state of pedestrians during the interaction with the urban environment. Results from the analysis of the collected data show that physiological responses are reliable indicators of safety perception while road crossing and interacting with real urban environment, suggesting the design of agent-based models for pedestrian dynamics simulations taking in account the representation of affective states.","PeriodicalId":50835,"journal":{"name":"AI Communications","volume":"2020 1","pages":"5-19"},"PeriodicalIF":0.8,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86918536","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}
To date, the research on agriculture vehicles in general and Agriculture Mobile Robots (AMRs) in particular has focused on a single vehicle (robot) and its agriculture-specific capabilities. Very little work has explored the coordination of fleets of such vehicles in the daily execution of farming tasks. This is especially the case when considering overall fleet performance, its efficiency and scalability in the context of highly automated agriculture vehicles that perform tasks throughout multiple fields potentially owned by different farmers and/or enterprises. The potential impact of automating AMR fleet coordination on commercial agriculture is immense. Major conglomerates with large and heterogeneous fleets of agriculture vehicles could operate on huge land areas without human operators to effect precision farming. In this paper, we propose the Agriculture Fleet Vehicle Routing Problem (AF-VRP) which, to the best of our knowledge, differs from any other version of the Vehicle Routing Problem studied so far. We focus on the dynamic and decentralised version of this problem applicable in environments involving multiple agriculture machinery and farm owners where concepts of fairness and equity must be considered. Such a problem combines three related problems: the dynamic assignment problem, the dynamic 3-index assignment problem and the capacitated arc routing problem. We review the state-of-the-art and categorise solution approaches as centralised, distributed and decentralised, based on the underlining decision-making context. Finally, we discuss open challenges in applying distributed and decentralised coordination approaches to this problem.
{"title":"Agriculture fleet vehicle routing: A decentralised and dynamic problem","authors":"Marin Lujak, E. Sklar, F. Semet","doi":"10.3233/aic-201581","DOIUrl":"https://doi.org/10.3233/aic-201581","url":null,"abstract":"To date, the research on agriculture vehicles in general and Agriculture Mobile Robots (AMRs) in particular has focused on a single vehicle (robot) and its agriculture-specific capabilities. Very little work has explored the coordination of fleets of such vehicles in the daily execution of farming tasks. This is especially the case when considering overall fleet performance, its efficiency and scalability in the context of highly automated agriculture vehicles that perform tasks throughout multiple fields potentially owned by different farmers and/or enterprises. The potential impact of automating AMR fleet coordination on commercial agriculture is immense. Major conglomerates with large and heterogeneous fleets of agriculture vehicles could operate on huge land areas without human operators to effect precision farming. In this paper, we propose the Agriculture Fleet Vehicle Routing Problem (AF-VRP) which, to the best of our knowledge, differs from any other version of the Vehicle Routing Problem studied so far. We focus on the dynamic and decentralised version of this problem applicable in environments involving multiple agriculture machinery and farm owners where concepts of fairness and equity must be considered. Such a problem combines three related problems: the dynamic assignment problem, the dynamic 3-index assignment problem and the capacitated arc routing problem. We review the state-of-the-art and categorise solution approaches as centralised, distributed and decentralised, based on the underlining decision-making context. Finally, we discuss open challenges in applying distributed and decentralised coordination approaches to this problem.","PeriodicalId":50835,"journal":{"name":"AI Communications","volume":"18 1","pages":"55-71"},"PeriodicalIF":0.8,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83291653","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}
Reinforcement learning is an efficient, widely used machine learning technique that performs well when the state and action spaces have a reasonable size. This is rarely the case regarding control-related problems, as for instance controlling traffic signals. Here, the state space can be very large. In order to deal with the curse of dimensionality, a rough discretization of such space can be employed. However, this is effective just up to a certain point. A way to mitigate this is to use techniques that generalize the state space such as function approximation. In this paper, a linear function approximation is used. Specifically, SARSA ( λ ) with Fourier basis features is implemented to control traffic signals in the agent-based transport simulation MATSim. The results are compared not only to trivial controllers such as fixed-time, but also to state-of-the-art rule-based adaptive methods. It is concluded that SARSA ( λ ) with Fourier basis features is able to outperform such methods, especially in scenarios with varying traffic demands or unexpected events.
{"title":"Reinforcement learning vs. rule-based adaptive traffic signal control: A Fourier basis linear function approximation for traffic signal control","authors":"Theresa Ziemke, L. N. Alegre, A. Bazzan","doi":"10.3233/aic-201580","DOIUrl":"https://doi.org/10.3233/aic-201580","url":null,"abstract":"Reinforcement learning is an efficient, widely used machine learning technique that performs well when the state and action spaces have a reasonable size. This is rarely the case regarding control-related problems, as for instance controlling traffic signals. Here, the state space can be very large. In order to deal with the curse of dimensionality, a rough discretization of such space can be employed. However, this is effective just up to a certain point. A way to mitigate this is to use techniques that generalize the state space such as function approximation. In this paper, a linear function approximation is used. Specifically, SARSA ( λ ) with Fourier basis features is implemented to control traffic signals in the agent-based transport simulation MATSim. The results are compared not only to trivial controllers such as fixed-time, but also to state-of-the-art rule-based adaptive methods. It is concluded that SARSA ( λ ) with Fourier basis features is able to outperform such methods, especially in scenarios with varying traffic demands or unexpected events.","PeriodicalId":50835,"journal":{"name":"AI Communications","volume":"7 1","pages":"89-103"},"PeriodicalIF":0.8,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74977315","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：