Plastic bags are challenging objects for robot manipulation due to transparency and deformability. This paper proposes a learning approach for a robot to insert its hand into a container- or bag-shaped object based on visual and tactile sensing. The basic idea is to utilize probing action that allows to acquire rich information about the object even with a simple tactile sensor. The structure of the object is estimated by unsupervised learning with contact and reachability information. The result is transferred to visual recognition as self-supervised learning. Based on the unsupervised learning result, the robot can verify whether the hand truly reached the interior of the bag by additional probing actions. The proposed method was evaluated experimentally by a robot hand with a simple tactile sensor.

Path integral policy improvement (PI2) is known to be an efficient reinforcement learning algorithm, particularly, if the target system is a high-dimensional dynamical system. However, PI2, and its existing extensions, have adjustable parameters, on which the efficiency depends significantly. This article proposes an extension of PI2that adjusts all of the critical parameters automatically. Motion acquisition tasks for three different types of simulated legged robots were performed to test the efficacy of the proposed algorithm. The results show that the proposed method cannot only eliminate the burden on the user to set the parameters appropriately but also improve the optimization performance significantly. For one of the acquired motions, a real robot experiment was conducted to show the validity of the motion.

To date, many gait generation strategies have been designed for robots with leg configurations that model those of natural creatures. However, their leg configurations are limited to the 2 × N type, such as hexapod or myriapod; hence, simultaneously, the potential ability of legged robots is implicitly limited. We consider single-legged modular robots that can be arranged to form a cluster with arbitrary 2-D leg configurations. By choosing configurations appropriately, these robots have the potential to perform several types of tasks, as is the case for reconfigurable modular robots. However, to use appropriate configurations for a given task, a unified gait generation system for various configurations of a cluster is required. In this article, we propose an autonomous distributed control system for each single-legged modular robot to collectively achieve static walking of the cluster with various leg configurations on planar ground. Moreover, our system is an autonomous distributed system with scalability and fault tolerance, in which each module determines the moving pattern of its foot through local communication without global information, such as the entire leg configuration of the cluster. We verified that several types of clusters achieved static walking using our system not only in dynamic simulations, but also in real robot experiments.

This paper describes the generation of digital elevation models (DEMs) with stereo technologies. We developed this method, and applied it to high-resolution TerraSAR-X data. The generated DEM was evaluated quantitatively using airborne DEM. It showed that the vertical accuracy was dependant on the land cover, and almost satisfied the objective specification in flat area.