Pub Date : 2020-10-26DOI: 10.1109/ICDL-EpiRob48136.2020.9278033
Inês Lourenço, R. Ventura, B. Wahlberg
The concept of time perception is used to describe the phenomenological experience of time. There is strong evidence that dopaminergic neurons are involved in the timing mechanisms responsible for time perception. The phasic activity of these neurons resembles the behavior of the reward prediction error in temporal-difference learning models. Therefore, these models are used to replicate the neuronal behaviour of the dopamine system and corresponding timing mechanisms. However, time perception has also been shown to be shaped by time estimation mechanisms from external stimuli. In this paper we propose a framework that combines these two principles, in order to provide temporal cognition abilities to intelligent systems such as robots. A time estimator based on observed environmental stimuli is combined with a reinforcement learning approach, using a feature representation called Microstimuli to replicate dopaminergic behaviour. The elapsed time perceived by the robot is estimated by modeling sensor measurements as Gaussian processes to capture the second-order statistics of the natural environment. The proposed framework is evaluated on a simulated robot that performs a temporal discrimination task originally performed by mice. The ability of the robot to replicate the timing mechanisms of the mice is demonstrated by the fact that both exhibit the same ability to classify the duration of intervals.
{"title":"Teaching Robots to Perceive Time: A Twofold Learning Approach","authors":"Inês Lourenço, R. Ventura, B. Wahlberg","doi":"10.1109/ICDL-EpiRob48136.2020.9278033","DOIUrl":"https://doi.org/10.1109/ICDL-EpiRob48136.2020.9278033","url":null,"abstract":"The concept of time perception is used to describe the phenomenological experience of time. There is strong evidence that dopaminergic neurons are involved in the timing mechanisms responsible for time perception. The phasic activity of these neurons resembles the behavior of the reward prediction error in temporal-difference learning models. Therefore, these models are used to replicate the neuronal behaviour of the dopamine system and corresponding timing mechanisms. However, time perception has also been shown to be shaped by time estimation mechanisms from external stimuli. In this paper we propose a framework that combines these two principles, in order to provide temporal cognition abilities to intelligent systems such as robots. A time estimator based on observed environmental stimuli is combined with a reinforcement learning approach, using a feature representation called Microstimuli to replicate dopaminergic behaviour. The elapsed time perceived by the robot is estimated by modeling sensor measurements as Gaussian processes to capture the second-order statistics of the natural environment. The proposed framework is evaluated on a simulated robot that performs a temporal discrimination task originally performed by mice. The ability of the robot to replicate the timing mechanisms of the mice is demonstrated by the fact that both exhibit the same ability to classify the duration of intervals.","PeriodicalId":114948,"journal":{"name":"2020 Joint IEEE 10th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134310072","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}
Pub Date : 2020-10-26DOI: 10.1109/ICDL-EpiRob48136.2020.9278075
Ziyan Gao, A. Elibol, N. Chong
Robotic manipulation has been generally applied to particular settings and a limited number of known objects. In order to manipulate novel objects, robots need to be capable of discovering the physical properties of objects, such as the center of mass, and reorienting objects to the desired pose required for subsequent actions. In this work, we proposed a computationally efficient 2-stage framework for planar pushing, allowing a robot to push novel objects to a specified pose with a small amount of pushing steps. We developed three modules: Coarse Action Predictor (CAP), Forward Dynamic Estimator (FDE), and Physical Property Estimator (PPE). The CAP module predicts a mixture of Gaussian distribution of actions. FDE learns the causality between action and successive object state. PPE based on Recurrent Neural Network predicts the physical center of mass (PCOM) from the robot-object interaction. Our preliminary experiments show promising results to meet the practical application requirements of manipulating novel objects.
{"title":"A 2-Stage Framework for Learning to Push Unknown Objects","authors":"Ziyan Gao, A. Elibol, N. Chong","doi":"10.1109/ICDL-EpiRob48136.2020.9278075","DOIUrl":"https://doi.org/10.1109/ICDL-EpiRob48136.2020.9278075","url":null,"abstract":"Robotic manipulation has been generally applied to particular settings and a limited number of known objects. In order to manipulate novel objects, robots need to be capable of discovering the physical properties of objects, such as the center of mass, and reorienting objects to the desired pose required for subsequent actions. In this work, we proposed a computationally efficient 2-stage framework for planar pushing, allowing a robot to push novel objects to a specified pose with a small amount of pushing steps. We developed three modules: Coarse Action Predictor (CAP), Forward Dynamic Estimator (FDE), and Physical Property Estimator (PPE). The CAP module predicts a mixture of Gaussian distribution of actions. FDE learns the causality between action and successive object state. PPE based on Recurrent Neural Network predicts the physical center of mass (PCOM) from the robot-object interaction. Our preliminary experiments show promising results to meet the practical application requirements of manipulating novel objects.","PeriodicalId":114948,"journal":{"name":"2020 Joint IEEE 10th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123838965","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}
Pub Date : 2020-10-08DOI: 10.1109/ICDL-EpiRob48136.2020.9278057
Zhanwen Chen, Shiyao Li, R. Rashedi, Xiaoman Zi, Morgan Elrod-Erickson, Bryan Hollis, Angela Maliakal, Xinyu Shen, Simeng Zhao, M. Kunda
Modern social intelligence includes the ability to watch videos and answer questions about social and theory-of-mind-related content, e.g., for a scene in Harry Potter, “Is the father really upset about the boys flying the car?” Social visual question answering (social VQA) is emerging as a valuable methodology for studying social reasoning in both humans (e.g., children with autism) and AI agents. However, this problem space spans enormous variations in both videos and questions. We discuss methods for creating and characterizing social VQA datasets, including 1) crowdsourcing versus in-house authoring, including sample comparisons of two new datasets that we created (TinySocial-Crowd and TinySocial-InHouse) and the previously existing Social-IQ dataset; 2) a new rubric for characterizing the difficulty and content of a given video; and 3) a new rubric for characterizing question types. We close by describing how having well-characterized social VQA datasets will enhance the explainability of AI agents and can also inform assessments and educational interventions for people.
{"title":"Characterizing Datasets for Social Visual Question Answering, and the New TinySocial Dataset","authors":"Zhanwen Chen, Shiyao Li, R. Rashedi, Xiaoman Zi, Morgan Elrod-Erickson, Bryan Hollis, Angela Maliakal, Xinyu Shen, Simeng Zhao, M. Kunda","doi":"10.1109/ICDL-EpiRob48136.2020.9278057","DOIUrl":"https://doi.org/10.1109/ICDL-EpiRob48136.2020.9278057","url":null,"abstract":"Modern social intelligence includes the ability to watch videos and answer questions about social and theory-of-mind-related content, e.g., for a scene in Harry Potter, “Is the father really upset about the boys flying the car?” Social visual question answering (social VQA) is emerging as a valuable methodology for studying social reasoning in both humans (e.g., children with autism) and AI agents. However, this problem space spans enormous variations in both videos and questions. We discuss methods for creating and characterizing social VQA datasets, including 1) crowdsourcing versus in-house authoring, including sample comparisons of two new datasets that we created (TinySocial-Crowd and TinySocial-InHouse) and the previously existing Social-IQ dataset; 2) a new rubric for characterizing the difficulty and content of a given video; and 3) a new rubric for characterizing question types. We close by describing how having well-characterized social VQA datasets will enhance the explainability of AI agents and can also inform assessments and educational interventions for people.","PeriodicalId":114948,"journal":{"name":"2020 Joint IEEE 10th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125546996","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}
Pub Date : 2020-09-18DOI: 10.1109/ICDL-EpiRob48136.2020.9278061
Simón C. Smith, S. Ramamoorthy
We propose an architecture for training generative models of counterfactual conditionals of the form, ‘can we modify event A to cause B instead of C?’, motivated by applications in robot control. Using an ‘adversarial training’ paradigm, an image-based deep neural network model is trained to produce small and realistic modifications to an original image in order to cause user-defined effects. These modifications can be used in the design process of image-based robust control - to determine the ability of the controller to return to a working regime by modifications in the input space, rather than by adaptation. In contrast to conventional control design approaches, where robustness is quantified in terms of the ability to reject noise, we explore the space of counterfactuals that might cause a certain requirement to be violated, thus proposing an alternative model that might be more expressive in certain robotics applications. So, we propose the generation of counterfactuals as an approach to explanation of black-box models and the envisioning of potential movement paths in autonomous robotic control. Firstly, we demonstrate this approach in a set of classification tasks, using the well known MNIST and CelebFaces Attributes datasets. Then, addressing multi-dimensional regression, we demonstrate our approach in a reaching task with a physical robot, and in a navigation task with a robot in a digital twin simulation.
{"title":"Counterfactual Explanation and Causal Inference In Service of Robustness in Robot Control","authors":"Simón C. Smith, S. Ramamoorthy","doi":"10.1109/ICDL-EpiRob48136.2020.9278061","DOIUrl":"https://doi.org/10.1109/ICDL-EpiRob48136.2020.9278061","url":null,"abstract":"We propose an architecture for training generative models of counterfactual conditionals of the form, ‘can we modify event A to cause B instead of C?’, motivated by applications in robot control. Using an ‘adversarial training’ paradigm, an image-based deep neural network model is trained to produce small and realistic modifications to an original image in order to cause user-defined effects. These modifications can be used in the design process of image-based robust control - to determine the ability of the controller to return to a working regime by modifications in the input space, rather than by adaptation. In contrast to conventional control design approaches, where robustness is quantified in terms of the ability to reject noise, we explore the space of counterfactuals that might cause a certain requirement to be violated, thus proposing an alternative model that might be more expressive in certain robotics applications. So, we propose the generation of counterfactuals as an approach to explanation of black-box models and the envisioning of potential movement paths in autonomous robotic control. Firstly, we demonstrate this approach in a set of classification tasks, using the well known MNIST and CelebFaces Attributes datasets. Then, addressing multi-dimensional regression, we demonstrate our approach in a reaching task with a physical robot, and in a navigation task with a robot in a digital twin simulation.","PeriodicalId":114948,"journal":{"name":"2020 Joint IEEE 10th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115020841","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}
Pub Date : 2020-09-03DOI: 10.1109/ICDL-EpiRob48136.2020.9278036
Aishwarya Pothula, Md Ashaduzzaman Rubel Mondol, Sanath Narasimhan, Sm Mazharul Islam, Deokgun Park
Even with impressive advances in application specific models, we still lack knowledge about how to build a model that can learn in a human-like way and do multiple tasks. To learn in a human-like way, we need to provide a diverse experience that is comparable to human's. In this paper, we introduce our ongoing effort to build a simulated environment for developmental robotics (SEDRo). SEDRo provides diverse human experiences ranging from those of a fetus to a 12th month old. A series of simulated tests based on developmental psychology will be used to evaluate the progress of a learning model. We anticipate SEDRo to lower the cost of entry and facilitate research in the developmental robotics community.
{"title":"SEDRo: A Simulated Environment for Developmental Robotics","authors":"Aishwarya Pothula, Md Ashaduzzaman Rubel Mondol, Sanath Narasimhan, Sm Mazharul Islam, Deokgun Park","doi":"10.1109/ICDL-EpiRob48136.2020.9278036","DOIUrl":"https://doi.org/10.1109/ICDL-EpiRob48136.2020.9278036","url":null,"abstract":"Even with impressive advances in application specific models, we still lack knowledge about how to build a model that can learn in a human-like way and do multiple tasks. To learn in a human-like way, we need to provide a diverse experience that is comparable to human's. In this paper, we introduce our ongoing effort to build a simulated environment for developmental robotics (SEDRo). SEDRo provides diverse human experiences ranging from those of a fetus to a 12th month old. A series of simulated tests based on developmental psychology will be used to evaluate the progress of a learning model. We anticipate SEDRo to lower the cost of entry and facilitate research in the developmental robotics community.","PeriodicalId":114948,"journal":{"name":"2020 Joint IEEE 10th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116239081","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}
Pub Date : 2020-08-31DOI: 10.1109/ICDL-EpiRob48136.2020.9278035
Filipe Gama, M. Shcherban, Matthias Rolf, M. Hoffmann
The mechanisms of infant development are far from understood. Learning about one's own body is likely a foundation for subsequent development. Here we look specifically at the problem of how spontaneous touches to the body in early infancy may give rise to first body models and bootstrap further development such as reaching competence. Unlike visually elicited reaching, reaching to own body requires connections of the tactile and motor space only, bypassing vision. Still, the problems of high dimensionality and redundancy of the motor system persist. In this work, we present an embodied computational model on a simulated humanoid robot with artificial sensitive skin on large areas of its body. The robot should autonomously develop the capacity to reach for every tactile sensor on its body. To do this efficiently, we employ the computational framework of intrinsic motivations and variants of goal babbling-as opposed to motor babbling-that prove to make the exploration process faster and alleviate the ill-posedness of learning inverse kinematics. Based on our results, we discuss the next steps in relation to infant studies: what information will be necessary to further ground this computational model in behavioral data.
{"title":"Active exploration for body model learning through self-touch on a humanoid robot with artificial skin","authors":"Filipe Gama, M. Shcherban, Matthias Rolf, M. Hoffmann","doi":"10.1109/ICDL-EpiRob48136.2020.9278035","DOIUrl":"https://doi.org/10.1109/ICDL-EpiRob48136.2020.9278035","url":null,"abstract":"The mechanisms of infant development are far from understood. Learning about one's own body is likely a foundation for subsequent development. Here we look specifically at the problem of how spontaneous touches to the body in early infancy may give rise to first body models and bootstrap further development such as reaching competence. Unlike visually elicited reaching, reaching to own body requires connections of the tactile and motor space only, bypassing vision. Still, the problems of high dimensionality and redundancy of the motor system persist. In this work, we present an embodied computational model on a simulated humanoid robot with artificial sensitive skin on large areas of its body. The robot should autonomously develop the capacity to reach for every tactile sensor on its body. To do this efficiently, we employ the computational framework of intrinsic motivations and variants of goal babbling-as opposed to motor babbling-that prove to make the exploration process faster and alleviate the ill-posedness of learning inverse kinematics. Based on our results, we discuss the next steps in relation to infant studies: what information will be necessary to further ground this computational model in behavioral data.","PeriodicalId":114948,"journal":{"name":"2020 Joint IEEE 10th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128943617","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}
Pub Date : 2020-08-30DOI: 10.1109/ICDL-EpiRob48136.2020.9278047
Vipul Nair, Paul E. Hemeren, Alessia Vignolo, Nicoletta Noceti, Elena Nicora, A. Sciutti, F. Rea, E. Billing, F. Odone, G. Sandini
Understanding which features humans rely on - in visually recognizing action similarity is a crucial step towards a clearer picture of human action perception from a learning and developmental perspective. In the present work, we investigate to which extent a computational model based on kinematics can determine action similarity and how its performance relates to human similarity judgments of the same actions. To this aim, twelve participants perform an action similarity task, and their performances are compared to that of a computational model solving the same task. The chosen model has its roots in developmental robotics and performs action classification based on learned kinematic primitives. The comparative experiment results show that both the model and human participants can reliably identify whether two actions are the same or not. However, the model produces more false hits and has a greater selection bias than human participants. A possible reason for this is the particular sensitivity of the model towards kinematic primitives of the presented actions. In a second experiment, human participants' performance on an action identification task indicated that they relied solely on kinematic information rather than on action semantics. The results show that both the model and human performance are highly accurate in an action similarity task based on kinematic-level features, which can provide an essential basis for classifying human actions.
{"title":"Action similarity judgment based on kinematic primitives","authors":"Vipul Nair, Paul E. Hemeren, Alessia Vignolo, Nicoletta Noceti, Elena Nicora, A. Sciutti, F. Rea, E. Billing, F. Odone, G. Sandini","doi":"10.1109/ICDL-EpiRob48136.2020.9278047","DOIUrl":"https://doi.org/10.1109/ICDL-EpiRob48136.2020.9278047","url":null,"abstract":"Understanding which features humans rely on - in visually recognizing action similarity is a crucial step towards a clearer picture of human action perception from a learning and developmental perspective. In the present work, we investigate to which extent a computational model based on kinematics can determine action similarity and how its performance relates to human similarity judgments of the same actions. To this aim, twelve participants perform an action similarity task, and their performances are compared to that of a computational model solving the same task. The chosen model has its roots in developmental robotics and performs action classification based on learned kinematic primitives. The comparative experiment results show that both the model and human participants can reliably identify whether two actions are the same or not. However, the model produces more false hits and has a greater selection bias than human participants. A possible reason for this is the particular sensitivity of the model towards kinematic primitives of the presented actions. In a second experiment, human participants' performance on an action identification task indicated that they relied solely on kinematic information rather than on action semantics. The results show that both the model and human performance are highly accurate in an action similarity task based on kinematic-level features, which can provide an essential basis for classifying human actions.","PeriodicalId":114948,"journal":{"name":"2020 Joint IEEE 10th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114570888","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}
Pub Date : 2020-08-11DOI: 10.1109/ICDL-EpiRob48136.2020.9278116
Angel Ayala, Francisco Cruz, D. Campos, Rodrigo Rubio, Bruno José Torres Fernandes, Richard Dazeley
Research on humanoid robotic systems involves a considerable amount of computational resources, not only for the involved design but also for its development and subsequent implementation. For robotic systems to be implemented in realworld scenarios, in several situations, it is preferred to develop and test them under controlled environments in order to reduce the risk of errors and unexpected behavior. In this regard, a more accessible and efficient alternative is to implement the environment using robotic simulation tools. This paper presents a quantitative comparison of Gazebo, Webots, and V-REP, three simulators widely used by the research community to develop robotic systems. To compare the performance of these three simulators, elements such as CPU, memory footprint, and disk access are used to measure and compare them to each other. In order to measure the use of resources, each simulator executes 20 times a robotic scenario composed by a NAO robot that must navigate to a goal position avoiding a specific obstacle. In general terms, our results show that Webots is the simulator with the lowest use of resources, followed by V-REP, which has advantages over Gazebo, mainly because of the CPU use.
{"title":"A Comparison of Humanoid Robot Simulators: A Quantitative Approach","authors":"Angel Ayala, Francisco Cruz, D. Campos, Rodrigo Rubio, Bruno José Torres Fernandes, Richard Dazeley","doi":"10.1109/ICDL-EpiRob48136.2020.9278116","DOIUrl":"https://doi.org/10.1109/ICDL-EpiRob48136.2020.9278116","url":null,"abstract":"Research on humanoid robotic systems involves a considerable amount of computational resources, not only for the involved design but also for its development and subsequent implementation. For robotic systems to be implemented in realworld scenarios, in several situations, it is preferred to develop and test them under controlled environments in order to reduce the risk of errors and unexpected behavior. In this regard, a more accessible and efficient alternative is to implement the environment using robotic simulation tools. This paper presents a quantitative comparison of Gazebo, Webots, and V-REP, three simulators widely used by the research community to develop robotic systems. To compare the performance of these three simulators, elements such as CPU, memory footprint, and disk access are used to measure and compare them to each other. In order to measure the use of resources, each simulator executes 20 times a robotic scenario composed by a NAO robot that must navigate to a goal position avoiding a specific obstacle. In general terms, our results show that Webots is the simulator with the lowest use of resources, followed by V-REP, which has advantages over Gazebo, mainly because of the CPU use.","PeriodicalId":114948,"journal":{"name":"2020 Joint IEEE 10th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132295935","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}
Pub Date : 2020-08-05DOI: 10.1109/ICDL-EpiRob48136.2020.9278050
Janderson Ferreira, Agostinho A. F. Júnior, Yves M. Galvão, Pablo V. A. Barros, Sergio M. M. Fernandes, Bruno José Torres Fernandes
Currently, path planning algorithms are used in many daily tasks. They are relevant to find the best route in traffic and make autonomous robots able to navigate. The use of path planning presents some issues in large and dynamic environments. Large environments make these algorithms spend much time finding the shortest path. On the other hand, dynamic environments request a new execution of the algorithm each time a change occurs in the environment, and it increases the execution time. The dimensionality reduction appears as a solution to this problem, which in this context means removing useless paths present in those environments. Most of the algorithms that reduce dimensionality are limited to the linear correlation of the input data. Recently, a Convolutional Neural Network (CNN) Encoder was used to overcome this situation since it can use both linear and non-linear information to reduce data. This paper analyzes in-depth the performance to eliminate the useless paths using this CNN Encoder model. To measure the mentioned model efficiency, we combined it with different path planning algorithms. Next, the final algorithms (combined and not combined) are checked in a database composed of five scenarios. Each scenario contains fixed and dynamic obstacles. Their proposed model, the CNN Encoder, associated with other existent path planning algorithms in the literature, was able to obtain a time decrease to find the shortest path compared to all path planning algorithms analyzed. the average decreased time was 54.43 %
{"title":"Performance Improvement of Path Planning algorithms with Deep Learning Encoder Model","authors":"Janderson Ferreira, Agostinho A. F. Júnior, Yves M. Galvão, Pablo V. A. Barros, Sergio M. M. Fernandes, Bruno José Torres Fernandes","doi":"10.1109/ICDL-EpiRob48136.2020.9278050","DOIUrl":"https://doi.org/10.1109/ICDL-EpiRob48136.2020.9278050","url":null,"abstract":"Currently, path planning algorithms are used in many daily tasks. They are relevant to find the best route in traffic and make autonomous robots able to navigate. The use of path planning presents some issues in large and dynamic environments. Large environments make these algorithms spend much time finding the shortest path. On the other hand, dynamic environments request a new execution of the algorithm each time a change occurs in the environment, and it increases the execution time. The dimensionality reduction appears as a solution to this problem, which in this context means removing useless paths present in those environments. Most of the algorithms that reduce dimensionality are limited to the linear correlation of the input data. Recently, a Convolutional Neural Network (CNN) Encoder was used to overcome this situation since it can use both linear and non-linear information to reduce data. This paper analyzes in-depth the performance to eliminate the useless paths using this CNN Encoder model. To measure the mentioned model efficiency, we combined it with different path planning algorithms. Next, the final algorithms (combined and not combined) are checked in a database composed of five scenarios. Each scenario contains fixed and dynamic obstacles. Their proposed model, the CNN Encoder, associated with other existent path planning algorithms in the literature, was able to obtain a time decrease to find the shortest path compared to all path planning algorithms analyzed. the average decreased time was 54.43 %","PeriodicalId":114948,"journal":{"name":"2020 Joint IEEE 10th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124470195","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}
Pub Date : 2020-07-30DOI: 10.1109/ICDL-EpiRob48136.2020.9278125
Pablo V. A. Barros, Ana Tanevska, Francisco Cruz, A. Sciutti
Designing the decision-making processes of artificial agents that are involved in competitive interactions is a challenging task. In a competitive scenario, the agent does not only have a dynamic environment but also is directly affected by the opponents' actions. Observing the Q-values of the agent is usually a way of explaining its behavior, however, it does not show the temporal-relation between the selected actions. We address this problem by proposing the Moody framework that creates an intrinsic representation for each agent based on the Pleasure/Arousal model. We evaluate our model by performing a series of experiments using the competitive multiplayer Chef's Hat card game and discuss how by observing the intrinsic state generated by our model allows us to obtain a holistic representation of the competitive dynamics within the game.
{"title":"Moody Learners - Explaining Competitive Behaviour of Reinforcement Learning Agents","authors":"Pablo V. A. Barros, Ana Tanevska, Francisco Cruz, A. Sciutti","doi":"10.1109/ICDL-EpiRob48136.2020.9278125","DOIUrl":"https://doi.org/10.1109/ICDL-EpiRob48136.2020.9278125","url":null,"abstract":"Designing the decision-making processes of artificial agents that are involved in competitive interactions is a challenging task. In a competitive scenario, the agent does not only have a dynamic environment but also is directly affected by the opponents' actions. Observing the Q-values of the agent is usually a way of explaining its behavior, however, it does not show the temporal-relation between the selected actions. We address this problem by proposing the Moody framework that creates an intrinsic representation for each agent based on the Pleasure/Arousal model. We evaluate our model by performing a series of experiments using the competitive multiplayer Chef's Hat card game and discuss how by observing the intrinsic state generated by our model allows us to obtain a holistic representation of the competitive dynamics within the game.","PeriodicalId":114948,"journal":{"name":"2020 Joint IEEE 10th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"126 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126011757","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}
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：