Pub Date : 2020-10-26DOI: 10.1109/ICDL-EpiRob48136.2020.9278115
S. Paplu, Chinmaya Mishra, K. Berns
Automating robot behavior in a specific situation is an active area of research. There are several approaches available in the literature of robotics to cater for the automatic behavior of a robot. However, when it comes to humanoids or human-robot interaction in general, the area has been less explored. In this paper, a pseudo-randomization approach has been introduced to automatize the gestures and facial expressions of an interactive humanoid robot called ROBIN based on its mental state. A significant number of gestures and facial expressions have been implemented to allow the robot more options to perform a relevant action or reaction based on visual stimuli. There is a display of noticeable differences in the behaviour of the robot for the same stimuli perceived from an interaction partner. This slight autonomous behavioural change in the robot clearly shows a notion of automation in behaviour. The results from experimental scenarios and human-centered evaluation of the system help validate the approach.
{"title":"Pseudo- Randomization in Automating Robot Behaviour during Human-Robot Interaction","authors":"S. Paplu, Chinmaya Mishra, K. Berns","doi":"10.1109/ICDL-EpiRob48136.2020.9278115","DOIUrl":"https://doi.org/10.1109/ICDL-EpiRob48136.2020.9278115","url":null,"abstract":"Automating robot behavior in a specific situation is an active area of research. There are several approaches available in the literature of robotics to cater for the automatic behavior of a robot. However, when it comes to humanoids or human-robot interaction in general, the area has been less explored. In this paper, a pseudo-randomization approach has been introduced to automatize the gestures and facial expressions of an interactive humanoid robot called ROBIN based on its mental state. A significant number of gestures and facial expressions have been implemented to allow the robot more options to perform a relevant action or reaction based on visual stimuli. There is a display of noticeable differences in the behaviour of the robot for the same stimuli perceived from an interaction partner. This slight autonomous behavioural change in the robot clearly shows a notion of automation in behaviour. The results from experimental scenarios and human-centered evaluation of the system help validate the approach.","PeriodicalId":114948,"journal":{"name":"2020 Joint IEEE 10th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"71 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":"122709413","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-EpiRob48136.2020.9278082
Hiroki Mori, Masayuki Masuda, T. Ogata
This study proposed a hypothesis regarding the emergence of object-oriented action via tactile-based curiosity. The hypothesis is such that a curious exploration driven by tactile sensation leads tactile-rich object-oriented actions, while there are no explicit rewards or other designated intentional purposes. Experiments were with the curiosity model named the disagreement model from the reinforcement learning research field and with a simple physics robotic simulation with visual and tactile sensory information. The experimental results indicated that the tactile sensation induces object-oriented actions such as hitting and pecking by the body parts that have tactile sensors. We deduced that the hypothesis could be extended to discussions regarding the acquisition of dexterous skillful object manipulation in human development.
{"title":"Tactile-based curiosity maximizes tactile-rich object-oriented actions even without any extrinsic rewards","authors":"Hiroki Mori, Masayuki Masuda, T. Ogata","doi":"10.1109/ICDL-EpiRob48136.2020.9278082","DOIUrl":"https://doi.org/10.1109/ICDL-EpiRob48136.2020.9278082","url":null,"abstract":"This study proposed a hypothesis regarding the emergence of object-oriented action via tactile-based curiosity. The hypothesis is such that a curious exploration driven by tactile sensation leads tactile-rich object-oriented actions, while there are no explicit rewards or other designated intentional purposes. Experiments were with the curiosity model named the disagreement model from the reinforcement learning research field and with a simple physics robotic simulation with visual and tactile sensory information. The experimental results indicated that the tactile sensation induces object-oriented actions such as hitting and pecking by the body parts that have tactile sensors. We deduced that the hypothesis could be extended to discussions regarding the acquisition of dexterous skillful object manipulation in human development.","PeriodicalId":114948,"journal":{"name":"2020 Joint IEEE 10th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"9 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":"134455373","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-EpiRob48136.2020.9278037
Charles Wilmot, Bertram E. Shi, J. Triesch
We present a model of the self-calibration of active binocular vision comprising the simultaneous learning of visual representations, vergence, and pursuit eye movements. The model follows the principle of Active Efficient Coding (AEC), a recent extension of the classic Efficient Coding Hypothesis to active perception. In contrast to previous AEC models, the present model uses deep autoencoders to learn sensory representations. We also propose a new formulation of the intrinsic motivation signal that guides the learning of behavior. We demonstrate the performance of the model in simulations.
{"title":"Self-Calibrating Active Binocular Vision via Active Efficient Coding with Deep Autoencoders","authors":"Charles Wilmot, Bertram E. Shi, J. Triesch","doi":"10.1109/ICDL-EpiRob48136.2020.9278037","DOIUrl":"https://doi.org/10.1109/ICDL-EpiRob48136.2020.9278037","url":null,"abstract":"We present a model of the self-calibration of active binocular vision comprising the simultaneous learning of visual representations, vergence, and pursuit eye movements. The model follows the principle of Active Efficient Coding (AEC), a recent extension of the classic Efficient Coding Hypothesis to active perception. In contrast to previous AEC models, the present model uses deep autoencoders to learn sensory representations. We also propose a new formulation of the intrinsic motivation signal that guides the learning of behavior. We demonstrate the performance of the model in simulations.","PeriodicalId":114948,"journal":{"name":"2020 Joint IEEE 10th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"94 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":"126934203","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-EpiRob48136.2020.9278031
M. Kirtay, Olga A. Wudarczyk, D. Pischedda, A. Kuhlen, R. A. Rahman, J. Haynes, V. Hafner
Robots are getting increasingly more present in many spheres of human life, making the need for robots that can successfully engage in natural social interactions with humans paramount. Successful human-robot interaction could be achieved more effectively if robots could act predictably and could predict the humans' actions. If robots could represent human partners and generate behaviors that are in line with the partners' expectations based on human's mental models of interdependent action, human agents would be able to apply predictive and adaptive mechanisms acquired in human interactions to interact with robots effectively. How could robots be predictable and be capable of predicting human behavior? We propose that this could be achieved by having an internal representation of both oneself and the other agent, that is by equipping the robot with the ability to co-represent. Here, co-representation refers to the representation of the partner's actions alongside one's own actions. Although co-representation constitutes an essential process for successful human social interaction, as it supports understanding of others' actions, to date co-representation processes have only scarcely been integrated into robotic platforms. We highlight the state-of-the-art findings on co-representation in social robotics, discuss current research limitations and open issues for creating computational models of co-representation in robots, and put forward the idea that predictive learning might constitute a particularly promising framework to build models of co-representing robots. Overall, in this article, we offer an integrated view of the state-of-the-art findings in robotics literature on co-representation and outline directions for future research, with the aim to boost success in building robots equipped with co-representation models fit for smooth social interactions.
{"title":"Modeling robot co-representation: state-of-the-art, open issues, and predictive learning as a possible framework","authors":"M. Kirtay, Olga A. Wudarczyk, D. Pischedda, A. Kuhlen, R. A. Rahman, J. Haynes, V. Hafner","doi":"10.1109/ICDL-EpiRob48136.2020.9278031","DOIUrl":"https://doi.org/10.1109/ICDL-EpiRob48136.2020.9278031","url":null,"abstract":"Robots are getting increasingly more present in many spheres of human life, making the need for robots that can successfully engage in natural social interactions with humans paramount. Successful human-robot interaction could be achieved more effectively if robots could act predictably and could predict the humans' actions. If robots could represent human partners and generate behaviors that are in line with the partners' expectations based on human's mental models of interdependent action, human agents would be able to apply predictive and adaptive mechanisms acquired in human interactions to interact with robots effectively. How could robots be predictable and be capable of predicting human behavior? We propose that this could be achieved by having an internal representation of both oneself and the other agent, that is by equipping the robot with the ability to co-represent. Here, co-representation refers to the representation of the partner's actions alongside one's own actions. Although co-representation constitutes an essential process for successful human social interaction, as it supports understanding of others' actions, to date co-representation processes have only scarcely been integrated into robotic platforms. We highlight the state-of-the-art findings on co-representation in social robotics, discuss current research limitations and open issues for creating computational models of co-representation in robots, and put forward the idea that predictive learning might constitute a particularly promising framework to build models of co-representing robots. Overall, in this article, we offer an integrated view of the state-of-the-art findings in robotics literature on co-representation and outline directions for future research, with the aim to boost success in building robots equipped with co-representation models fit for smooth social interactions.","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":"117056967","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-EpiRob48136.2020.9278065
Motoyu Katsumura, K. Yano, T. Nakao, Atsushi Hamada, Katsuhiko Torii
Individuals with cerebral palsy use electric wheelchairs due to their abnormal gait caused by paralysis and other symptoms. However, it is difficult for them to operate the wheelchair joystick because of their suddenly occurring uncontrollable, involuntary movements and the difficulty they have maintaining their posture. In this study, we developed a control system, which suppresses the effects of involuntary movement. This system is capable of controlling electric wheelchairs as intended by individuals with tension-athetosis-type cerebral palsy. We demonstrated the experiments to compare the stability of operation by normal system and the proposed system. Finally, we showed the effectiveness of the proposed system in the straight running experiment.
{"title":"Involuntary movement suppression filter for electric wheelchair with athetosis-type cerebral palsy","authors":"Motoyu Katsumura, K. Yano, T. Nakao, Atsushi Hamada, Katsuhiko Torii","doi":"10.1109/ICDL-EpiRob48136.2020.9278065","DOIUrl":"https://doi.org/10.1109/ICDL-EpiRob48136.2020.9278065","url":null,"abstract":"Individuals with cerebral palsy use electric wheelchairs due to their abnormal gait caused by paralysis and other symptoms. However, it is difficult for them to operate the wheelchair joystick because of their suddenly occurring uncontrollable, involuntary movements and the difficulty they have maintaining their posture. In this study, we developed a control system, which suppresses the effects of involuntary movement. This system is capable of controlling electric wheelchairs as intended by individuals with tension-athetosis-type cerebral palsy. We demonstrated the experiments to compare the stability of operation by normal system and the proposed system. Finally, we showed the effectiveness of the proposed system in the straight running experiment.","PeriodicalId":114948,"journal":{"name":"2020 Joint IEEE 10th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"34 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":"133876982","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-EpiRob48136.2020.9278062
Matthias Rolf
Both biological and artificial agents need to coordinate their behavior to suit various needs at the same time. Reconciling conflicts of different needs and contradictory interests such as self-preservation and curiosity is the central difficulty arising in the design and modelling of need and value systems. Current models of multi-objective reinforcement learning do either not provide satisfactory power to describe such conflicts, or lack the power to actually resolve them. This paper aims to promote a clear understanding of these limitations, and to overcome them with a theory-driven approach rather than ad hoc solutions. The first contribution of this paper is the development of an example that demonstrates previous approaches' limitations concisely. The second contribution is a new, non-linear objective function design, MORE, that addresses these and leads to a practical algorithm. Experiments show that standard RL methods fail to grasp the nature of the problem and ad-hoc solutions struggle to describe consistent preferences. MORE consistently learns a highly satisfactory solution that balances contradictory needs based on a consistent notion of optimality.
{"title":"The Need for MORE: Need Systems as Non-Linear Multi-Objective Reinforcement Learning","authors":"Matthias Rolf","doi":"10.1109/ICDL-EpiRob48136.2020.9278062","DOIUrl":"https://doi.org/10.1109/ICDL-EpiRob48136.2020.9278062","url":null,"abstract":"Both biological and artificial agents need to coordinate their behavior to suit various needs at the same time. Reconciling conflicts of different needs and contradictory interests such as self-preservation and curiosity is the central difficulty arising in the design and modelling of need and value systems. Current models of multi-objective reinforcement learning do either not provide satisfactory power to describe such conflicts, or lack the power to actually resolve them. This paper aims to promote a clear understanding of these limitations, and to overcome them with a theory-driven approach rather than ad hoc solutions. The first contribution of this paper is the development of an example that demonstrates previous approaches' limitations concisely. The second contribution is a new, non-linear objective function design, MORE, that addresses these and leads to a practical algorithm. Experiments show that standard RL methods fail to grasp the nature of the problem and ad-hoc solutions struggle to describe consistent preferences. MORE consistently learns a highly satisfactory solution that balances contradictory needs based on a consistent notion of optimality.","PeriodicalId":114948,"journal":{"name":"2020 Joint IEEE 10th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"69 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":"128188179","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-EpiRob48136.2020.9278049
F. Mukhlish, J. Page, Michael Bain
Applying intelligence to a group of simple robots known as swarm robots has become an exciting technology in assisting or replacing humans to fulfil complex, dangerous and harsh missions. However, building a strategy for a swarm to thrive in a dynamic environment is challenging because of control decentralisation and interactions between agents. The decision-making process in a robotic task commonly takes place in sequential stages. By understanding the subsequent action-reaction process, a strategy to make optimal decisions in a respective environment can be learnt. Hence, using the concept of epigenetic inheritance, novel evolutionary-learning mechanisms for a swarm will be discussed in this paper. Reinforcement evolutionary learning using epigenetic inheritance (RELEpi) is proposed in this article. This method utilizes reward, temporal difference and epigenetic inheritance to approximate optimal action and behaviour policies. The proposed method opens possibilities to combine reward-based learning and evolutionary methods as a stacked process where histone value is used rather than fitness function. The formulation consists of methylation and epigenetic mechanisms, inspired by the epigenome studies. The methylation process helps the accumulation of the reward to histone value of the gene. Epigenetic mechanisms give the ability to mate genetic information along with their histone value.
{"title":"From Reward to Histone: Combining Temporal-Difference Learning and Epigenetic Inheritance for Swarm's Coevolving Decision Making","authors":"F. Mukhlish, J. Page, Michael Bain","doi":"10.1109/ICDL-EpiRob48136.2020.9278049","DOIUrl":"https://doi.org/10.1109/ICDL-EpiRob48136.2020.9278049","url":null,"abstract":"Applying intelligence to a group of simple robots known as swarm robots has become an exciting technology in assisting or replacing humans to fulfil complex, dangerous and harsh missions. However, building a strategy for a swarm to thrive in a dynamic environment is challenging because of control decentralisation and interactions between agents. The decision-making process in a robotic task commonly takes place in sequential stages. By understanding the subsequent action-reaction process, a strategy to make optimal decisions in a respective environment can be learnt. Hence, using the concept of epigenetic inheritance, novel evolutionary-learning mechanisms for a swarm will be discussed in this paper. Reinforcement evolutionary learning using epigenetic inheritance (RELEpi) is proposed in this article. This method utilizes reward, temporal difference and epigenetic inheritance to approximate optimal action and behaviour policies. The proposed method opens possibilities to combine reward-based learning and evolutionary methods as a stacked process where histone value is used rather than fitness function. The formulation consists of methylation and epigenetic mechanisms, inspired by the epigenome studies. The methylation process helps the accumulation of the reward to histone value of the gene. Epigenetic mechanisms give the ability to mate genetic information along with their histone value.","PeriodicalId":114948,"journal":{"name":"2020 Joint IEEE 10th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"3 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":"130156473","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-EpiRob48136.2020.9278100
Ozgur Baran Ozturkcu, Emre Ugur, Erhan Öztop
How the sensorimotor experience of an agent can be organized into abstract symbol-like structures to enable effective planning and control is an open question. In the literature, there are many studies that start by assuming the existence of some symbols and ‘ground’ those onto continuous sensorimotor signals. There are also works that aim to facilitate the emergence of symbol-like representations by using specially designed machine learning architectures. In this paper, we investigate whether a deep reinforcement learning system that learns a dynamic task would facilitate the formation of high-level neural representations that might be considered as precursors of symbolic representation, which could be exploited by higher level neural circuits for better control and planning. The results indicate that without even explicit design to promote such representations, neural responses emerge that may serve as the basis of abstract symbol-like representations.
{"title":"High-level representations through unconstrained sensorimotor learning","authors":"Ozgur Baran Ozturkcu, Emre Ugur, Erhan Öztop","doi":"10.1109/ICDL-EpiRob48136.2020.9278100","DOIUrl":"https://doi.org/10.1109/ICDL-EpiRob48136.2020.9278100","url":null,"abstract":"How the sensorimotor experience of an agent can be organized into abstract symbol-like structures to enable effective planning and control is an open question. In the literature, there are many studies that start by assuming the existence of some symbols and ‘ground’ those onto continuous sensorimotor signals. There are also works that aim to facilitate the emergence of symbol-like representations by using specially designed machine learning architectures. In this paper, we investigate whether a deep reinforcement learning system that learns a dynamic task would facilitate the formation of high-level neural representations that might be considered as precursors of symbolic representation, which could be exploited by higher level neural circuits for better control and planning. The results indicate that without even explicit design to promote such representations, neural responses emerge that may serve as the basis of abstract symbol-like representations.","PeriodicalId":114948,"journal":{"name":"2020 Joint IEEE 10th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"50 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":"114466023","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-EpiRob48136.2020.9278126
Qingpeng Zhu, J. Triesch, Bertram E. Shi
This paper describes a unified computational model for the joint development of early visual representations and the control of three types of eye movements, i.e., vergence, cyclovergence, and saccades. The model is based on the Active Efficient Coding (AEC) framework, an extension of Barlow's efficient coding hypothesis to active perception. AEC describes the joint learning of sensory encoding and behavioral control. The present work relaxes the assumptions made in our previous work by learning vergence, cyclovergence, and saccades all from random initialization. Our results also demonstrate the importance of the interaction between the learning of these eye movements in terms of learning speed and accuracy. Overall, we find that AEC provides a parsimonious framework to account for the simultaneous learning of active vision skills.
{"title":"Integration of Vergence, Cyclovergence, and Saccades through Active Efficient Coding","authors":"Qingpeng Zhu, J. Triesch, Bertram E. Shi","doi":"10.1109/ICDL-EpiRob48136.2020.9278126","DOIUrl":"https://doi.org/10.1109/ICDL-EpiRob48136.2020.9278126","url":null,"abstract":"This paper describes a unified computational model for the joint development of early visual representations and the control of three types of eye movements, i.e., vergence, cyclovergence, and saccades. The model is based on the Active Efficient Coding (AEC) framework, an extension of Barlow's efficient coding hypothesis to active perception. AEC describes the joint learning of sensory encoding and behavioral control. The present work relaxes the assumptions made in our previous work by learning vergence, cyclovergence, and saccades all from random initialization. Our results also demonstrate the importance of the interaction between the learning of these eye movements in terms of learning speed and accuracy. Overall, we find that AEC provides a parsimonious framework to account for the simultaneous learning of active vision skills.","PeriodicalId":114948,"journal":{"name":"2020 Joint IEEE 10th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"19 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":"128191558","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-EpiRob48136.2020.9278056
J. A. Knoll, Van-Nam Hoang, Jacob Honer, Samuel Church, Thanh-Hai Tran, J. Weng
Traditional methods for stereo-disparity detection use explicit search between the left and right images. Although such methods are simple and intuitive for understanding, they suffer from degeneracies when the search window contains weak texture. Developmental Networks (DNs) are task-nonspecific and modality-nonspecific learning engines. Because they are general-purpose learners, they have a potential to deal with many types of degeneracies in intelligent systems. This work presents two novel mechanisms to deal with degeneracies: volume dimension and subwindow voting. While developmental stereo-disparity detection has been tested on simulated stereo images in our prior publications, it has never been tested on the real world. This paper reports our system, $3mathrm{DEye}$, which is the first to have filled this void. The algorithm, software, graphical user interface, training, performance, and update rates on CPU and GPU, respectively, on a Sony G8142 mobile phone are reported. Many deep learning methods that use error back-propagation suffer from the controversy of “post-selection” using the test set [1], to select one from many networks to report. In contrast, all randomly initialized DNs are performance-equivalent, no “post-selection” using test set. Possible future improvements for practical real-world and real-time applications are discussed.
{"title":"Fast Developmental Stereo-Disparity Detectors","authors":"J. A. Knoll, Van-Nam Hoang, Jacob Honer, Samuel Church, Thanh-Hai Tran, J. Weng","doi":"10.1109/ICDL-EpiRob48136.2020.9278056","DOIUrl":"https://doi.org/10.1109/ICDL-EpiRob48136.2020.9278056","url":null,"abstract":"Traditional methods for stereo-disparity detection use explicit search between the left and right images. Although such methods are simple and intuitive for understanding, they suffer from degeneracies when the search window contains weak texture. Developmental Networks (DNs) are task-nonspecific and modality-nonspecific learning engines. Because they are general-purpose learners, they have a potential to deal with many types of degeneracies in intelligent systems. This work presents two novel mechanisms to deal with degeneracies: volume dimension and subwindow voting. While developmental stereo-disparity detection has been tested on simulated stereo images in our prior publications, it has never been tested on the real world. This paper reports our system, $3mathrm{DEye}$, which is the first to have filled this void. The algorithm, software, graphical user interface, training, performance, and update rates on CPU and GPU, respectively, on a Sony G8142 mobile phone are reported. Many deep learning methods that use error back-propagation suffer from the controversy of “post-selection” using the test set [1], to select one from many networks to report. In contrast, all randomly initialized DNs are performance-equivalent, no “post-selection” using test set. Possible future improvements for practical real-world and real-time applications are discussed.","PeriodicalId":114948,"journal":{"name":"2020 Joint IEEE 10th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"3 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":"116871399","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：