This paper describes a stereo-based person detection and tracking method for a mobile robot that can follow a specific person in dynamic environments. Many previous works on person detection use laser range finders which can provide very accurate range measurements. Stereo-based systems have also been popular, but most of them have not been used for controlling a real robot. We propose a detection method using depth templates of person shape applied to a dense depth image. We also develop an SVM-based verifier for eliminating false positive. For person tracking by a mobile platform, we formulate the tracking problem using the Extended Kalman filter. The robot continuously estimates the position and the velocity of persons in the robot local coordinates, which are then used for appropriately controlling the robot motion. Although our approach is relatively simple, our robot can robustly follow a specific person while recognizing the target and other persons with occasional occlusions.
In order to analyze and recognize various types of facial expressions, discriminating slight movements of facial muscles is essential. However, it is difficult because of complex structures of facial muscles. In many traditional methods of facial expression analyses, discriminative movements of facial muscles are manually defined in advance and facial expressions are discriminated by analyzing only the predefined movements. This approach is problematic because finding and defining appropriate movements is quite troublesome and time-consuming. To solve this problem, we propose an effective method to automatically find useful movements. We accurately estimate the movements of facial muscles and represent them as time-series data called multistream. Since multistream generally contains several redundant streams, we remove useless streams by evaluating the usefulness of each stream based on AMSS (Angular Metrics for Shape Similarity) which efficiently measures the similarity between streams. We verify the effectiveness of the proposed method through several facial expression recognition experiments.
In this paper, we report the importance of the reactive behaviors of humanoid robots against human actions for smooth communication. We hypothesize that the reactive behaviors of robots play an important role in achieving human-like communication between humans and robots since the latter need to be recognized by the former as communication partners. To evaluate this hypothesis, we conducted psychological experiments in which we presented subjects with four types of reactive behaviors resulting from pushing a wheeled inverted-pendulum-type humanoid robot. From the experiment, we found that subject's impressions to the robot regarding extroversion and neuroticism changed by the robot's reactive behaviors. We also discuss the reasons for such changes in impressions by comparing the robot's and human reactive behavior.
This paper presents a ceiling mobile robot platform which enables multiple robots to move smoothly and execute their own tasks in a living space. An advantage of this platform is potential to actualize sharing space between humans and robots and secure humans' safety, although the robots can access to humans when they need. For realizing the ceiling mobile robot platform, two key techniques are utilized. The first one is permanent magnet inductive traction method for the robots attaching under a ceiling plate, and the second is multi-robots simultaneous position measurement method using matrix of 2 dimensional codes. By experiments, feasibility and characteristics of permanent magnet inductive traction method are confirmed. And also practicality of position estimation method using matrix of 2 dimensional codes is examined.
To achieve flight, an insect generates aerodynamic force by flapping its wings. However, this aerodynamic force acting on the wings has not been directly measured during free-flight. In this study, we fabricated an ornithopter modeled on a hawk moth, and attached a MEMS differential pressure sensor on its wing. Then, we measured differential pressure between upper and lower surfaces of the wing during free-flight. Reynolds number of the wing and wing load of the ornithopter were designed to be 4.2 × 103[–], and 7.5[N/m2], which were close to those of a hawk moth. The mass, wing length and flapping frequency were 6.8[g], 110[mm] and 13[Hz], respectively. The maximum differential pressures at the center of the wing were 39[Pa] and 18[Pa] during downstroke and upstroke, which were 5 and 2 times larger than the wing load. The differential pressure contributed vertical pressure of 38[Pa] during downstroke and horizontal pressure of 15[Pa] during upstroke. The time average of vertical differential pressure was 7.0[Pa], which was as large as the wing load of the ornithopter.
Landing control is one of the important issues for biped walking robot, because robots are expected to walk on not only flat known surfaces but also unknown and uneven terrain for working at various fields. This paper presents a new controller design for a robotic foot to land on unknown terrain. The robotic foot considered in this study equips springs to reduce the impact force at the foot landing. There are two objectives in the landing control; achieving the desired terrain reaction force and positioning the foot on unknown terrain. To achieve these two objectives simultaneously by adjusting the foot position, we propose a PI force controller with a desired foot position, which guarantees the robust stability of control system with respect to terrain variance, and exact positioning of the foot to unknown terrain. The effectiveness of the proposed controller is demonstrated by simulation and experimental results.
This paper proposes a new method of measuring position of daily life commodities placed on a floor. Our method uses a laser range finder (LRF) together with a mirror. The LRF scans the laser beam just above the floor and measure the distance to the object. Some beams are reflected by the mirror and measure the distance from different origin. Even if the two measurements fail, the method calculates the position of the object by utilizing information that no measurement is available. Thus, the method achieves two major advantages: 1) robust against occlusion and 2) applicable to variety of daily life commodities.