Van de Maele Toon, Verbelen Tim, Çatal Ozan, De Boom Cedric, Dhoedt Bart
IDLab, Department of Information Technology, Ghent University-imec, Ghent, Belgium.
Front Neurorobot. 2021 Mar 5;15:642780. doi: 10.3389/fnbot.2021.642780. eCollection 2021.
Occlusions, restricted field of view and limited resolution all constrain a robot's ability to sense its environment from a single observation. In these cases, the robot first needs to actively query multiple observations and accumulate information before it can complete a task. In this paper, we cast this problem of active vision as active inference, which states that an intelligent agent maintains a generative model of its environment and acts in order to minimize its surprise, or expected free energy according to this model. We apply this to an object-reaching task for a 7-DOF robotic manipulator with an in-hand camera to scan the workspace. A novel generative model using deep neural networks is proposed that is able to fuse multiple views into an abstract representation and is trained from data by minimizing variational free energy. We validate our approach experimentally for a reaching task in simulation in which a robotic agent starts without any knowledge about its workspace. Each step, the next view pose is chosen by evaluating the expected free energy. We find that by minimizing the expected free energy, exploratory behavior emerges when the target object to reach is not in view, and the end effector is moved to the correct reach position once the target is located. Similar to an owl scavenging for prey, the robot naturally prefers higher ground for exploring, approaching its target once located.
遮挡、有限的视野和分辨率都限制了机器人从单一观察中感知其环境的能力。在这些情况下，机器人首先需要主动查询多个观察结果并积累信息，然后才能完成任务。在本文中，我们将这种主动视觉问题视为主动推理，即智能体维护其环境的生成模型并采取行动以根据该模型将其意外或预期自由能降至最低。我们将此应用于一个具有7自由度机器人操纵器的物体抓取任务，该操纵器配备了一个手内摄像头以扫描工作空间。我们提出了一种使用深度神经网络的新型生成模型，该模型能够将多个视图融合成一个抽象表示，并通过最小化变分自由能从数据中进行训练。我们在模拟中对一个抓取任务进行了实验验证，在该模拟中，一个机器人代理在对其工作空间没有任何了解的情况下开始。每一步，通过评估预期自由能来选择下一个视图姿态。我们发现，通过最小化预期自由能，当要到达的目标物体不在视野中时会出现探索行为，一旦找到目标，末端执行器就会移动到正确的到达位置。与寻找猎物的猫头鹰类似，机器人自然更喜欢在较高的位置进行探索，一旦找到目标就靠近它。
