This paper discuss an improvement of that robot acquires a knowledge of environment by interacting with objects without designer’s knowledge. The knowledge is acquired by moving its arm slightly around an object and calculating affordances probabilistically through the behavior of feature points in images of environment. Specifically, the robot distinguish whether its arm is occluded by an obje...

In this paper we propose an optimal arm motion generation satisfying multiple criteria via evolved neural controllers. Three different criteria are chosen to be optimized simultaneously, similar to human arm motion in performing daily activities. These criteria are minimum execution time, minimum distance and minimum acceleration. Selected neural controllers from the Pareto solutions are implem...

The diffusion of e-commerce has produced larger and volumes varying items to be handled in warehouses, with the effect that need for picking automation is increasing. Conventionally, been achieved through a custom plant designed large-scale production having well-established characteristics are expected change slowly only small degree over time. However, today challenge realize solution flexibl...

This paper proposes a method to improve the robustness of a robot arm control program. The control program is generated in simulation by genetic programming. The robustness is measured in the real world. To improve the robustness, the control program is evolved with multiple robot arm configurations. The result shows that the robustness of a control program is improved by 10% compared to a cont...