Replicating human motions with the android 

Context in source publication

Context 1

... soft. After that modification, a plaster full-body mold was made from the modified clay model, and then a silicon full-body model was made from that plaster mold. This silicon model is maintained as a master model. Using this master model, silicon skin for the entire body is made. The thickness of the silicon skin is 5 mm in our current version. The mechanical parts, motors and sensors are covered with polyurethane and the produced silicon skin. As shown in the figure, the details are so finely represented that they cannot be distinguished from those of human beings in photographs. Our current technology for replicating the human figure as an android has reached a fine degree of reality. It is, however, still not perfect. One issue is the detail of the wetness of the eyes. The eye is the body part to which human observers become most sensitive. When confronted with a human face, a person first looks at the eyes. Although the android has eye-related mechanisms, such as blinking or making saccade movements, and the eyeballs are near-perfect copies of those of a human, we still become aware of the differences from a real human. Actually, making the wet surface of the eye and replicating the outer corners using silicone are difficult tasks, so further improvements are needed for this part. Other issues are the flexibility and robustness of the skin material. The silicone used in the current manufacturing process is sufficient for representing the texture of the skin; however, it loses flexibility after one or two years, and its elasticity is insufficient for adapting to large joint movements. Very human-like movement is another important factor in developing androids. Even if androids look indistinguishable from humans as static figures, without appropriate movements, they can be easily identified as artificial. To achieve highly human-like movement, we found that a child android was too small for embedding the number of actuators required, which led to the development of an adult android. The right half of figure 3 shows our latest adult android. This android, named Repliee Q2, contains 42 pneumatic (air) actuators in the upper torso. The positions of the actuators were determined by analyzing real human movements using a precise 3D motion tracker. With these actuators, both unconscious movements, such as breathing in the chest, and conscious large movements, such as head or arm movements, can be generated. Furthermore, the android is able to generate the facial expressions that are important for interacting with humans. Figure 4 shows some of the facial expressions generated by the android. In order to generate a smooth, human-like expression, 13 out of 42 actuators are embedded in the head. We decided to use pneumatic actuators for the androids, instead of the DC motors used in most robots. The use of a pneumatic actuator provides several benefits. First, it is very silent, much closer to human-produced sound. DC servomotors require reduction gears, which generate nonhuman-like, very robot-like noise. Second, the reaction of the android to external force becomes very natural with the pneumatic damper. If we use DC servomotors with reduction gears, sophisticated compliance control is required to obtain the same effect. This is also important for ensuring safety in interactions with the android. On the other hand, the weakness of the pneumatic actuators is that they require a large and powerful air compressor. Due to this requirement, the current android cannot walk. For wide applications, we need to develop new electric actuators that have similar specs to the pneumatic actuators. The next issue is how to control the 42 air servo actuators used to achieve very humanlike movements. The simplest approach is to directly send angular information to each joint. However, as the number of actuators in the android is relatively large, this takes a long time. Another difficulty is that the skin movement does not simply correspond to the joint movement. For example, the android has more than five actuators around the shoulder for generating human-like shoulder movements, with the skin moving and stretching according to the actuator motions. Already, we have developed methods such as using Perlin noise 10 to generate smooth movements or using a neural network to obtain mapping between the skin surface and actuator movements. There still remain some issues, such as the limited speed of android movement due to the nature of the pneumatic damper. To achieve quicker and more human-like behavior, speed and torque controls are required in our future study. After obtaining an efficient method for controlling the android, the next step is the implementation of human-like motions. A straightforward approach to this challenge is to imitate real human motions in synchronization with the android’s master. By attaching 3D motion tracker markers on both the android and the master, the android can automatically follow human motions (figure 5). This work is still in progress, but interesting issues have arisen with respect to this kind of imitation. Imitation by the android means representation of complicated human shapes and motions in the parameter space of the actuators. Although the android has a relatively large number of actuators compared to other robots, the number is still far smaller compared with a human. Thus, the effect of data-size reduction is significant. By carefully examining this parameter space and mapping, we may find important properties of human body movements. More concretely, we expect to develop a hierarchical representation of human body movements that consist of two or more layers, such as small unconscious movements and large conscious movements. With this hierarchical representation, we can expect to achieve more flexibility in android behavior control. Androids require human-like perceptual abilities in addition to human-like appearance and movements. This problem has been tackled in the fields of computer vision and pattern recognition under rather controlled environments. However, the problem becomes extremely difficult when applied to robots in real-world situations, since vision and audition become unstable and noisy. Ubiquitous/distributed sensor systems solve this problem. The idea is to recognize the environment and human activities by using many distributed cameras, microphones, infrared motion sensors, floor sensors and ID tag readers in the environment (figure 6). We have developed distributed vision systems 11 and distributed audition systems 12 in our previous work. To solve the present problem, theses developments must be integrated and extended. The omnidirectional cameras observe humans from multiple viewing points and robustly recognize their behaviors 13 . The microphones catch the human voice by forming virtual sound beams. The floor sensors, which cover the entire space, reliably detect the footprints of humans. The only sensors that should be installed on the robot are skins sensors. Soft and sensitive skin sensors are important particularly for interactive robots. However, there has not been much work in this area in previous robotics. We are now focusing on its importance in developing original sensors. Our sensors are made by combining silicone skin and Piezo films (figure 7). This sensor detects pressure by bending the Piezo films. Furthermore, it can detect very near human presence from static electricity by increasing the sensitivity. That is, it can perceive a signal that a human being is there. These technologies for very human-like appearance, behavior and perception enable us to develop feasible androids. These androids have undergone various cognitive tests, but this work is still limited. The bottleneck is long-term conversation in interaction. Unfortunately, current artificial intelligence (AI) technology for developing human-like brains has only a limited ability, and thus we cannot expect human-like conversation with robots. When we meet humanoid robots, we usually expect to have human-like conversation with them. However, the technology is very far behind this expectation. Progress in AI takes time, and this is actually our final goal in robotics. In order to arrive at this final goal, we need to use the technologies available today and, moreover, truly understand what a human is. Our solution to this problem is to integrate android and teleoperation technologies. We have developed Geminoid, a new category of robot, to overcome the bottleneck issue. We coined “geminoid” from the Latin “geminus,” meaning “twin” or “double,” and added “oides,” which indicates “similarity” or being a twin. As the name suggests, a geminoid is a robot that will work as a duplicate of an existing person. It appears and behaves as a person and is connected to the person by a computer network. Geminoids extend the applicable field of android science. Androids are designed for studying human nature in general. With geminoids, we can study such personal aspects as presence or personality traits, tracing their origins and implementation into robots. Figure 8 shows the robotic part of HI-1, the first geminoid prototype. Geminoids have the following capabilities: The appearance of a geminoid is based on an existing person and does not depend on the imagination of designers. Its movements can be made or evaluated simply by referring to the original person. The existence of a real person analogous to the robot enables easy comparison studies. Moreover, if a researcher is used as the original, we can expect that individual to offer meaningful insights into the experiments, which are especially important at the very first stage of a new field of study when beginning from established research methodologies. Since geminoids are equipped with teleoperation functionality, they are not only driven by an autonomous program. By introducing manual control, the limitations in current AI technologies can be ...