Pub Date : 2020-07-30DOI: 10.1109/ICDL-EpiRob48136.2020.9278071
Maxime Petit, E. Dellandréa, Liming Chen
In robotics, methods and softwares usually require optimizations of hyperparameters in order to be efficient for specific tasks, for instance industrial bin-picking from homogeneous heaps of different objects. We present a developmental framework based on long-term memory and reasoning modules (Bayesian Optimisation, visual similarity and parameters bounds reduction) allowing a robot to use meta-learning mechanism increasing the efficiency of such continuous and constrained parameters optimizations. The new optimization, viewed as a learning for the robot, can take advantage of past experiences (stored in the episodic and procedural memories) to shrink the search space by using reduced parameters bounds computed from the best optimizations realized by the robot with similar tasks of the new one (e.g. bin-picking from an homogenous heap of a similar object, based on visual similarity of objects stored in the semantic memory). As example, we have confronted the system to the constrained optimizations of 9 continuous hyperparameters for a professional software (Kamido) in industrial robotic arm bin-picking tasks, a step that is needed each time to handle correctly new object. We used a simulator to create bin-picking tasks for 8 different objects (7 in simulation and one with real setup, without and with meta-learning with experiences coming from other similar objects) achieving goods results despite a very small optimization budget, with a better performance reached when meta-learning is used (84.3 % vs 78.9 % of success overall, with a small budget of 30 iterations for each optimization) for every object tested (p-value=0.036).
在机器人技术中，方法和软件通常需要对超参数进行优化，以便有效地完成特定任务，例如，从不同对象的同质堆中进行工业拾取。我们提出了一个基于长期记忆和推理模块(贝叶斯优化、视觉相似性和参数边界缩减)的开发框架，允许机器人使用元学习机制来提高这种连续和约束参数优化的效率。新的优化，被视为机器人的学习，可以利用过去的经验(存储在情景和程序记忆中)，通过使用由机器人实现的最佳优化计算的简化参数边界来缩小搜索空间(例如，基于存储在语义记忆中的对象的视觉相似性，从相似对象的同质堆中拾取)。以工业机械臂捡筒任务为例，我们针对专业软件(Kamido)对系统进行了9个连续超参数的约束优化，这一步骤每次都需要正确处理新对象。我们使用模拟器为8个不同的对象(7个在模拟中，一个在真实设置中，没有元学习，有来自其他类似对象的经验)创建bin-picking任务，尽管优化预算非常小，但仍然获得了良好的结果，使用元学习时达到了更好的性能(84.3% vs 78.9%的总体成功率，每次优化的30次迭代的小预算)对于每个测试对象(p值=0.036)。
{"title":"Bayesian Optimization for Developmental Robotics with Meta-Learning by Parameters Bounds Reduction","authors":"Maxime Petit, E. Dellandréa, Liming Chen","doi":"10.1109/ICDL-EpiRob48136.2020.9278071","DOIUrl":"https://doi.org/10.1109/ICDL-EpiRob48136.2020.9278071","url":null,"abstract":"In robotics, methods and softwares usually require optimizations of hyperparameters in order to be efficient for specific tasks, for instance industrial bin-picking from homogeneous heaps of different objects. We present a developmental framework based on long-term memory and reasoning modules (Bayesian Optimisation, visual similarity and parameters bounds reduction) allowing a robot to use meta-learning mechanism increasing the efficiency of such continuous and constrained parameters optimizations. The new optimization, viewed as a learning for the robot, can take advantage of past experiences (stored in the episodic and procedural memories) to shrink the search space by using reduced parameters bounds computed from the best optimizations realized by the robot with similar tasks of the new one (e.g. bin-picking from an homogenous heap of a similar object, based on visual similarity of objects stored in the semantic memory). As example, we have confronted the system to the constrained optimizations of 9 continuous hyperparameters for a professional software (Kamido) in industrial robotic arm bin-picking tasks, a step that is needed each time to handle correctly new object. We used a simulator to create bin-picking tasks for 8 different objects (7 in simulation and one with real setup, without and with meta-learning with experiences coming from other similar objects) achieving goods results despite a very small optimization budget, with a better performance reached when meta-learning is used (84.3 % vs 78.9 % of success overall, with a small budget of 30 iterations for each optimization) for every object tested (p-value=0.036).","PeriodicalId":114948,"journal":{"name":"2020 Joint IEEE 10th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"123 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":"122486399","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 : 2020-07-29DOI: 10.1109/ICDL-EpiRob48136.2020.9278106
G. Schillaci, Alejandra Ciria, B. Lara
We present an intrinsic motivation architecture that generates behaviors towards self-generated and dynamic goals and that regulates goal selection and the balance between exploitation and exploration through multi-level monitoring of prediction error dynamics. This architecture modulates exploration noise and leverages computational resources according to the dynamics of the overall performance of the learning system. Results show that this architecture outperforms intrinsic motivation approaches where exploratory noise and goals are fixed. We suggest that the tracking of prediction error dynamics allows an artificial agent to be intrinsically motivated to seek new experiences but constrained to those that generate reducible prediction error. We argue about the potential relationship between emotional valence and rates of progress toward a goal.
{"title":"Tracking Emotions: Intrinsic Motivation Grounded on Multi - Level Prediction Error Dynamics","authors":"G. Schillaci, Alejandra Ciria, B. Lara","doi":"10.1109/ICDL-EpiRob48136.2020.9278106","DOIUrl":"https://doi.org/10.1109/ICDL-EpiRob48136.2020.9278106","url":null,"abstract":"We present an intrinsic motivation architecture that generates behaviors towards self-generated and dynamic goals and that regulates goal selection and the balance between exploitation and exploration through multi-level monitoring of prediction error dynamics. This architecture modulates exploration noise and leverages computational resources according to the dynamics of the overall performance of the learning system. Results show that this architecture outperforms intrinsic motivation approaches where exploratory noise and goals are fixed. We suggest that the tracking of prediction error dynamics allows an artificial agent to be intrinsically motivated to seek new experiences but constrained to those that generate reducible prediction error. We argue about the potential relationship between emotional valence and rates of progress toward a goal.","PeriodicalId":114948,"journal":{"name":"2020 Joint IEEE 10th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"89 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126027656","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 : 2019-12-28DOI: 10.1109/ICDL-EpiRob48136.2020.9278105
Cansu Sancaktar, Pablo Lanillos
We present a pixel-based deep active inference algorithm (PixelAI) inspired by human body perception and action. Our algorithm combines the free energy principle from neuroscience, rooted in variational inference, with deep convolutional decoders to scale the algorithm to directly deal with raw visual input and provide online adaptive inference. Our approach is validated by studying body perception and action in a simulated and a real Nao robot. Results show that our approach allows the robot to perform 1) dynamical body estimation of its arm using only monocular camera images and 2) autonomous reaching to “imagined” arm poses in visual space. This suggests that robot and human body perception and action can be efficiently solved by viewing both as an active inference problem guided by ongoing sensory input.
{"title":"End-to-End Pixel-Based Deep Active Inference for Body Perception and Action","authors":"Cansu Sancaktar, Pablo Lanillos","doi":"10.1109/ICDL-EpiRob48136.2020.9278105","DOIUrl":"https://doi.org/10.1109/ICDL-EpiRob48136.2020.9278105","url":null,"abstract":"We present a pixel-based deep active inference algorithm (PixelAI) inspired by human body perception and action. Our algorithm combines the free energy principle from neuroscience, rooted in variational inference, with deep convolutional decoders to scale the algorithm to directly deal with raw visual input and provide online adaptive inference. Our approach is validated by studying body perception and action in a simulated and a real Nao robot. Results show that our approach allows the robot to perform 1) dynamical body estimation of its arm using only monocular camera images and 2) autonomous reaching to “imagined” arm poses in visual space. This suggests that robot and human body perception and action can be efficiently solved by viewing both as an active inference problem guided by ongoing sensory input.","PeriodicalId":114948,"journal":{"name":"2020 Joint IEEE 10th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125169152","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：