The purpose of this study is to develop a method for an air hockey robot to hit back the puck to a target position using reinforcement learning. The learning of hitting back motion, which is executed on a simulator that reproduces an air hockey robot and a field hockey table, is conducted step by step in three phases: bringing the mallet into contact with the puck, hitting the puck back to the wall on the opponent's side, and aiming at the opponent's goal. Two types of movement are acquired based on two different strategies: aiming directly at the goal and aiming the goal with reflection on the side walls. First, experiments on the simulator were conducted to evaluate the model obtained by the proposed method, and then the actual air hockey robot system was operated using the model to confirm the feasibility of hitting the puck back to the goal.

A stop function that takes into considerations the principle of human behavior is defined as a ``Anshin Stop Switch'' and proposed as a cooperative safety technology for humans and machines. To confirm its effectiveness, we conducted a questionnaire survey among employees working in a robot restaurant in operation to confirm its hazard avoidance effect and its influence on future behavior. The results were organized as ``Safety Behavior Design Diagram'' based on ``Applied Behavior Analysis'' and its basic effectiveness was confirmed.

Assessment of patient joint stiffness during robotic upper extremity rehabilitation has the potential to expand the range of its adaptations. In this study, we investigated the feasibility of measuring shoulder joint impedance during arm weight compensation using an exoskeleton robot joint driven by an hybrid actuator. It is shown that, in principle, impedance measurement during assisting is possible by weight compensation by pneumatic force and perturbation application by electromagnetic force.

Harvesting Chinese chives is hard work that requires bending over at the waist, which can cause back pain, so the development of labor-saving machinery is expected. Therefore, various harvesting robots have been developed in recent years and have achieved a certain level of labor-saving effect, but more efficient harvesting machines are still desired. The IoP project in Kochi Prefecture has developed a Chinese chives harvester that can harvest 1.6[m] hilling width Chinese chives in batches, aiming to realize light labor and high-speed harvesting. This report outlines the system and describes the results of field tests.

This paper addresses the extraction of the in-region sound sources. To solve this problem, we propose an LCMV-based Scan-and-Sum Beamformer (LCMV-SS-BF) that can extract sources within a specified wide and continuous region by integrating an LCMV Beamformer (LCMV-BF) for continuous region separation and a Scan-and-Sum Beamformer (SS-BF) for wide-area source separation. Numerical simulations using convolutional source datasets showed the effectiveness of source extraction by LCMV-SS-BF.

The wire-driven orthogonal 3-axis joint mechanism was proposed utilizing a minimum 4 drive wires. ``Wire Support'' assembly guides two pairs of wires wound oppositely around the arm shaft in four directions, enabling the drive to tilt and twist rotations. This mechanism offers advantages such as no sliding, low friction, simple kinematics, and the potential for a compact design. A prototype was developed to conduct experimental evaluations confirming its repeatability and stiffness.

In the construction industry, remote control of construction machines is highly demanded to improve productivity. A major problem of teleoperation is that the operator cannot accurately understand the surround environment, resulting in the risk of tipping over or collision. For example, three-dimensional (3D) information such as the height of obstacles, the depth of the excavated hole, and the slope angle, cannot be obtained when traveling. In this study, we propose a system to visualize such 3D information of a construction site for operators to avoid hazards during remote-controlled traveling by utilizing 3D terrain data of the site.

We describe a demonstration experiment conducted to examine the usage scenarios and evaluate the functionality of the autonomous mobile robot ``AI Suitcase,'' which supports the mobility of people with visual impairments in unfamiliar environment. 11 participants with visually impairements walked around the exhibition space together with the robot, which provided voice guidance at various points. We conducted interviews regarding their needs for the exhibition spaces (ex. art galleries and museums) and the operability of the robot, and identified both advantages and areas for improvement. Additionally, based on speed data during navigation and the participants' understanding of the exhibit content, we confirmed the high compatibility between the exhibition spaces and the navigation robot.