公司简介
自组织是我们这个世界上最引人注目的现象之一。甚至进化也可以被看作是大自然在对资源的永恒争夺中,在凡人的约束下实现自我组织的方式。因此,一旦解决方案建立起来,进化就是一个增量过程。机器人可以被认为没有这些令人窒息的限制。相反,它们可能是不朽的,不受能量限制。那么,我们的问题是如何在这样一个对每个机器人开放的世界中组织自组织,以实现个体的开放式发展。我们的机器人有一个固定的形态(到目前为止还没有考虑结构自组织),它的“大脑”由两个人工神经网络组成,一个用于控制,另一个用于认知,即“理解”机器人对控制的反应。我们方法的要点是,两个网络中的学习都是自监督的,由完全域不变的目标函数驱动,完全依赖于机器人的传感器值。目标主要是使机器人敏感,以便传感器值的小变化引起电机值的大变化,从而产生更大的感官响应,以此类推。这将使机器人产生过度活跃、混乱的行为。 The way into complete chaos is counteracted by both the physics of the robot itself (inertia, cross relations, ...) and the decline of understanding in the chaotic regime. As a solution of these conflicting effects the robot develops a kind of self-exploration of its bodily affordances in a more or less playful way with a tendency to development due to increasing cognitive abilities. We present below a number of examples demonstrating that this principle, called also the principle of homeokinesis, can be translated into a reliable, extremely robust algorithm which governs the parameter dynamics of the neural networks for both the self-model and the controller. Videos are from simulated environments as well as from real world experiments.