Object Grasping with the NAO

摘要

With autonomous robots becoming more and more common, the interest in ap- plications of mobile robotics increases. Many applications of robotics include the grasping and manipulation of objects. As many robotic manipulators have several degrees of freedom, controlling these manipulators is not a trivial task. The ac- tuator needs to be guided along a proper trajectory towards the object to grasp, avoiding collisions with other objects and the surface supporting the object. In this project, the problem of learning a proper trajectory towards an object to grasp, lo- cated in front of a humanoid robot, the Aldebaran NAO, is solved by using machine learning. Three algorithms were evaluated. Learning from demonstration using a neural network trained on a training set of recorded demonstrations was not capable of learning this task. Using Nearest Neighbor on the same training set yielded much better results in simulation but had more problems picking up objects on the real robot. A form of Reinforcement Learning (RL) tailored to continuous state and action spaces, the Continuous Actor Critic Learning Automaton (CACLA), proved to be an effective way to learn to solve the problem by exploring the action space to obtain a good trajectory in a reasonable amount of time. This algorithm also proved to be robust against the additional complexity of operating on the real robot after being trained in simulation, bridging the reality gap.