This paper describes an active camera system for high-speed object tracking. Under ordinary illumination, such as fluorescent lights, our system is capable of tracking an object in a typical indoor environment that contains a cluttered background. In order to accomplish this task, we developed a high-sensitivity high-frame-rate visual sensor system and a real-time object tracking algorithm that makes use of our previously proposed motion estimation technique, which is capable of robustly estimating optical flow in a high-frame-rate image sequence. The experimental results for our active camera system show the effectiveness and robustness of our visual sensor system and tracking algorithm.

The Mechanical Engineering Laboratory (MEL) is developing technologies for multi-robot collaboration in remote environments with the Toshiba Mechanical Systems Laboratory (TMSL). Human operators' delayed visual perception due to the communication delay over the network seriously affects the collaboration performance in the multi-operator-multi-robot tele-manipulation. We have built an experimental tele-manipulation test bed connecting the MEL and the TMSL to study the time-delayed remote tele-collaboration between two places. In the test bed, one operator controls her master robot nearby two slave robots in the work site and another from a distance. A local online graphics simulator without time delay is developed to cope with the communication delay and several multi-robot coordinated control strategies are devised to avoid the collision. To verify the validity of this simulator assisted approach, we demonstrated a maintenance work on a plant mock-up in the TMSL by two different slave robots and two distant operators in the MEL and TMSL respectively through an ISDN.

In the case of conventional industrial robot systems, operators have to write robot-language programs for each type of workpiece. This is an onerous task, especially when each workpiece has a different shape. We propose a teaching-less robot system for the finishing of two-dimensional workpieces of various shapes and thicknesses using force control and computer vision. The robot system does not require shape information for the workpiece to be included in the CAD data or to be input by the operator. Each workpiece shape is acquired by segmenting edges into straight lines and circular arcs from the image data of the workpiece. The robot-language program for each workpiece is generated automatically from the workpiece shape data and finishing condition data. The effectiveness of the proposed method is verified by experiments using a newly developed robot system. In the system, the robot picks up a workpiece whose shape is not previously known on the workpiece stand by itself and carries out the finishing tasks using the automatically generated robot-language program. This method provides a compact and inexpensive finishing robot system which reduces the programming and workpiece-setting burden on the operators.

We developed a robot system which can play one-on-one volleyball games with a human player. It can not only hit a flying ball back to the player correctly but also have various autonomous functionalities to interact with humans necessary for playing games, i.e., it can pick up a ball of a requested color by recognizing voice instructions, can locate the players by recognizing their faces, and can shake hands. This robot performed the entire game sequence over 100 times at a company-sponsored exhibition, where the ball rally continued over 25 times with an arbitrary player. In this paper, we mainly describe the real-time visual feedback system of the robot which is essential for playing ball games.

Proposes a method of stable force controller design for robotic manipulators based on frequency response identification. The force controller described falls into the hybrid controller category. Force control loops are added to a popular position controller, enabling position control loops and force control loops to be designed independently. The proposed method does not require a detailed model of manipulator and environment dynamics. It is, therefore, robust enough for unmodeled dynamics, and easily analyzes stability in the high frequency region using the phase and gain margin method. The frequency response is identified by an accurate method called multi-decimation (MD), using motor input and contact-force output data. The MD method was previously developed by the author. The force control parameters (i.e. PID feedback parameters) are calculated by a stable design method called partial-model-matching (PMM), using the identified frequency response. The effectiveness of the proposed design method is demonstrated, through some experimental results, including a tracing task along a stiff environment, carried out using a planar two-link manipulator with harmonic drive gears.>