Dexterous manipulation is an important function for working robots. Manipulator tasks such as grasping, assembly and disassembly can generally be divided into several motion primitives. We call such motion primitives "skills" and explain how most manipulator tasks can be composed of sequences of these skills. We will address the issues involved with various types of robots such as maintenance robots and service robots. We have considered hierarchizing the manipulation tasks of these robots since their tasks have become more complex than ever before. Additionally, as errors are seen likely to increase in complex tasks, it is important to implement effective error recovery technology. This paper presents our proposal for a new type of error recovery that uses the concepts of task stratification and error classification which can be expressed specifically using flow charts.

No abstract

This paper analyzes the indeterminate grasp force in power grasps with a rigid body model. A power grasp overconstrains an object with multiple contact points using the surfaces of finger links and palm. It is known that the overconstrained grasp results in the static indeterminacy of the grasp force. This paper shows that it also results in an infeasible combination of the sliding directions at the contact points. A static friction force acts only in the opposite direction of the trend of sliding. This characteristic of friction restricts the grasp force in power grasps although it is indeterminate. First, we show an example to illustrate the restriction on the grasp force. Then, we formulate it formally. This analysis leads to a special case where the grasp force is unique.

No abstract

This paper proposes a novel method for randomized bin-picking based on learning. When a two-fingered gripper tries to pick an object from the pile, a finger often contacts a neighboring object. Even if a finger contacts a neighboring object, the target object will be successfully picked depending on the configuration of neighboring objects. In our proposed method, we use the visual information on neighboring objects to train the discriminator. Corresponding to a grasping posture of an object, the discriminator predicts whether or not the pick will be successful even if a finger contacts a neighboring object. We examine two learning algorithms, the linear support vector machine (SVM) and the random forest (RF) approaches. By using both methods, we demonstrate that the picking success rate is significantly higher than with conventional methods without learning.

No abstract

No abstract

No abstract