arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.03288cs.ROcs.AI
收藏

基于主动推理的对象中心场景表示

Object-Centric Scene Representations using Active Inference

IDLab(IDLab实验室);Ghent University(根特大学)

Toon Van de Maele, Tim Verbelen, Pietro Mazzaglia, Stefano Ferraro, Bart Dhoedt

摘要:

从原始传感数据中表示场景及其组成对象是使机器人能够与其环境交互的核心能力。在本文中,我们提出了一种新的方法场景理解,利用分层对象为中心的生成模型,使代理推断对象类别和姿态在allocentric参考框架使用主动推理,神经启发的框架动作和感知。为了评估主动视觉代理的行为,我们还提出了一个新的基准,给定一个特定对象的目标视点,代理需要找到最佳匹配的视点,给定一个工作空间,在3D中随机定位的对象。我们证明了我们的主动推理代理能够平衡认知觅食和目标驱动的行为,并大大优于监督和强化学习基线。

英文摘要:

Representing a scene and its constituent objects from raw sensory data is a core ability for enabling robots to interact with their environment. In this paper, we propose a novel approach for scene understanding, leveraging a hierarchical object-centric generative model that enables an agent to infer object category and pose in an allocentric reference frame using active inference, a neuro-inspired framework for action and perception. For evaluating the behavior of an active vision agent, we also propose a new benchmark where, given a target viewpoint of a particular object, the agent needs to find the best matching viewpoint given a workspace with randomly positioned objects in 3D. We demonstrate that our active inference agent is able to balance epistemic foraging and goal-driven behavior, and outperforms both supervised and reinforcement learning baselines by a large margin.

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。

↑