We consider shared workspace scenarios with humans and robots acting to achieve independent goals, termed as parallel play. We model these as general-sum games and construct a framework that utilizes the Nash equilibrium solution concept to consider the interactive effect of both agents while planning. We find multiple Pareto-optimal equilibria in these tasks. We hypothesize that people act by choosing an equilibrium based on social norms and their personalities. To enable coordination, we infer the equilibrium online using a probabilistic model that includes these two factors and use it to select the robot's action. We apply our approach to a close-proximity pick-and-place task involving a robot and a simulated human with three potential behaviors - defensive, selfish, and norm-following. We showed that using a Bayesian approach to infer the equilibrium enables the robot to complete the task with less than half the number of collisions while also reducing the task execution time as compared to the best baseline. We also performed a study with human participants interacting either with other humans or with different robot agents and observed that our proposed approach performs similar to human-human parallel play interactions. The code is available at https://github.com/shray/bayes-nash
Bayesian inference for data-efficient, explainable, and safe robotic motion planning: A review
University of Eastern Finland(东芬兰大学);School of Computing(计算机学院);Shenzhen Technology University(深圳技术大学);College of Big Data and Internet(大数据与互联网学院);Chengdu University of Information Technology(成都信息工程大学);College of Blockchain industry(区块链产业学院);College of Health Science and Environmental Engineering(健康科学与环境工程学院)
Bayesian Learning for the Robust Verification of Autonomous Robots
University of Warwick(华威大学);University of York(约克大学);Centrum Wiskunde & Informatica(荷兰国家数学与计算机科学研究所);Eindhoven University of Technology(埃因霍温理工大学);University of Glasgow(格拉斯哥大学)
Bayesian Inverse Physics for Neuro-Symbolic Robot Learning
Robotics Research Group University of Bremen(不莱梅大学机器人研究组);Robotics Innovation Center DFKI GmbH(DFKI机器人创新中心);Technical University of Chemnitz(化学工业大学);Technical University of Darmstadt(图尔恩技术大学);Systems AI for Robot Learning DFKI GmbH(DFKI机器人学习系统AI);Robotics Research Group, University of Bremen(不莱梅大学机器人研究组);Robotics Innovation Center, DFKI GmbH(DFKI机器人创新中心)
Human Machine Co-Adaptation Model and Its Convergence Analysis
College of Medical Information and Artificial Intelligence, Shandong First Medical University(山东第一医科大学医学信息与人工智能学院);Shandong Academy of Medical Sciences(山东省医学科学院);University of Technology Sydney(悉尼科技大学);South Western Sydney LHD(西南悉尼本地卫生区;利物浦医院);Liverpool Hospital
COBRA-PPM: A Causal Bayesian Reasoning Architecture Using Probabilistic Programming for Robot Manipulation Under Uncertainty
Oxford Robotics Institute, Dept. Engineering Science, University of Oxford, UK(牛津大学机器人研究所);Microsoft Research, Redmond, WA, USA(微软研究院);Bristol Robotics Laboratory, School of Engineering, University of the West of England, Bristol, UK(布里斯托尔机器人实验室)
Spatial Concept-Based Navigation with Human Speech Instructions via Probabilistic Inference on Bayesian Generative Model
College of Information Science and Engineering, Ritsumeikan University(立命馆大学信息科学与工程学院);National Institute of Informatics(国立情报学研究所);The Graduate University for Advanced Studies, SOKENDAI(综合研究大学院大学)
Bayesian Optimization for Developmental Robotics with Meta-Learning by Parameters Bounds Reduction
LIRIS, CNRS UMR 5205 Ecole Centrale de Lyon(里昂中央理工学院 LIRIS 实验室(法国国家科学研究中心 UMR 5205))
在机器人技术中,方法和软件通常需要优化超参数,以便有效地执行特定任务,例如从不同对象的同质堆中进行工业装箱。我们提出了一个发展框架的基础上长期记忆和推理模块(贝叶斯优化,视觉相似性和参数边界减少),允许机器人使用元学习机制,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(存储在情节和过程存储器中),以通过使用从具有新任务的机器人实现的最佳优化计算的减少的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进行装箱)。作为例子,我们已经面对系统的9个连续的超参数的约束优化的专业软件(Kamido)在工业机器人手臂装箱任务,每次都需要正确地处理新的对象的一个步骤。我们使用模拟器为8个不同的对象创建装箱任务(7个在模拟中,一个在真实设置中,没有和有来自其他类似对象的经验的元学习)尽管优化预算很小,但仍实现了良好的结果,当使用元学习时,性能更好(总体成功率为84.3% vs 78.9%,每次优化的小预算为30次迭代)(p值=0.036)。