In motor control, mapping high-level goals to low-level motor commands often leads to ambiguities, as there are usually many ways a task can be achieved. The key to resolving such ambiguities, for both humans and robots, lies in prediction. In this dissertation, a novel approach for acquiring and applying predictive robot action models is presented. Action models are first learned from observed experience, and enable robots to predict the performance and outcome of their actions. These models are then used to tailor actions to the context they are being executed in, for instance to optimize action sequences, tailor actions to novel goals, or coordinate actions of several robots. The main principle behind this approach is that in robot controller design, knowledge that robots learn themselves from observed experience complements well the abstract knowledge that humans specify.
«
In motor control, mapping high-level goals to low-level motor commands often leads to ambiguities, as there are usually many ways a task can be achieved. The key to resolving such ambiguities, for both humans and robots, lies in prediction. In this dissertation, a novel approach for acquiring and applying predictive robot action models is presented. Action models are first learned from observed experience, and enable robots to predict the performance and outcome of their actions. These models ar...
»