CAJ | 학술논문

针对机器人模仿学习控制策略获取的问题，基于高斯过程的方法，建立示教机器人示教行为的样本数据的高斯过程回归模型并加以训练，以求解示教机器人的感知和行为之间的映射关系，并将此映射关系作为模仿机器人的控制策略来实现对示教行为的模仿。以Braitenberg车为仿真对象，研究趋光模仿学习行为。仿真实验表明：基于高斯过程的机器人模仿学习算法具有有效性，模仿机器人在不同任务环境下具有很好的适应性。
침대궤기인모방학습공제책략획취적문제，기우고사과정적방법，건립시교궤기인시교행위적양본수거적고사과정회귀모형병가이훈련，이구해시교궤기인적감지화행위지간적영사관계，병장차영사관계작위모방궤기인적공제책략래실현대시교행위적모방。이Braitenberg차위방진대상，연구추광모방학습행위。방진실험표명：기우고사과정적궤기인모방학습산법구유유효성，모방궤기인재불동임무배경하구유흔호적괄응성。
To acquire the control strategy in robot imitation learning, a Gaussian processes ( GP ) regression model based on GP is used to construct the mapping relationship between actions of teaching robot and perception by the sample data of the teaching behavior. Then, the mapping relationship is used as control the strategy to imitate the teaching action. The Braitenberg vehicles are used as simulation subject to study phototaxis imitation learning action. Simulation results show that robot imitation learning based on Gaussian processes is effective. Furthermore, the simulation results in various task environments indicate that the method is adaptive.