arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2112.01871cs.ROcs.AIcs.LG
收藏

机器人和人工智能体中的主动推理:综述与挑战

Active Inference in Robotics and Artificial Agents: Survey and Challenges

Robotics Institute, Delft University of Technology(代尔夫特理工大学机器人研究所);MRC Brain Networks Dynamics Unit, Oxford University(牛津大学MRC脑网络动力学研究中心);Oxford Robotics Institute, Oxford University(牛津大学牛津机器人研究所);Okinawa Institute of Science and Technology(冲绳科学技术大学院大学)

Pablo Lanillos, Cristian Meo, Corrado Pezzato, Ajith Anil Meera, Mohamed Baioumy, Wataru Ohata, Alexander Tschantz, Beren Millidge, Martijn Wisse, Christopher L. Buckley, Jun Tani

摘要:

主动推理是一个数学框架,起源于计算神经科学,作为大脑如何实现动作,感知和学习的理论。最近,它已被证明是一个很有前途的方法,状态估计和不确定性下的控制问题,以及在机器人和人工智能体的目标驱动行为的建设一般的基础。在这里,我们回顾了状态估计,控制,规划和学习的主动推理的最新理论和实现;描述了当前的成就,特别关注机器人技术。我们展示了相关实验,说明了它在适应性、泛化和鲁棒性方面的潜力。此外,我们将这种方法与其他框架,并讨论其预期的好处和挑战:一个统一的框架与功能的生物相容性,使用变分贝叶斯推理。

英文摘要:

Active inference is a mathematical framework which originated in computational neuroscience as a theory of how the brain implements action, perception and learning. Recently, it has been shown to be a promising approach to the problems of state-estimation and control under uncertainty, as well as a foundation for the construction of goal-driven behaviours in robotics and artificial agents in general. Here, we review the state-of-the-art theory and implementations of active inference for state-estimation, control, planning and learning; describing current achievements with a particular focus on robotics. We showcase relevant experiments that illustrate its potential in terms of adaptation, generalization and robustness. Furthermore, we connect this approach with other frameworks and discuss its expected benefits and challenges: a unified framework with functional biological plausibility using variational Bayesian inference.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑