Humanoid refers to any being whose body structure resembles that of a human: head, torso, legs, arms, hands. It is a robot that is based on the general structure of a human, such as a robot that walks on two legs and has an upper torso, or a robot that has two arms, two legs and a head. A humanoid robot does not necessarily look convincingly like a real person, for example the ASIMO humanoid robot has a helmet instead of a face.
However an android (male) or gynoid (female) is a humanoid robot designed to look as much like a real person as possible, although these words are frequently perceived to be synonymous with humanoid.
While there are many humanoid robots in fictional stories, some real humanoid robots have been developed since the 1990s, and some real human-looking android robots have been developed since 2002.
The main differences between humanoids and other kinds of robots are: Bipedal human-like locomotion, Stable gait, Changing model during one/two feet support walking, Two legs + two arms + torso + head, Hyper DOF system (>20), Complex kinematics and dynamics, On-board power and computer autonomy, Complex real-time control architecture
Current use of humanoids
Famous humanoid robots like the Honda ASIMO or the Toyota Partner Robots do not accomplish any useful work. They are, however, presented to the media and demonstrate their capabilities like walking, running, climbing stairs, playing musical instruments or conducting orchestras on stage and during exhibitions.
ASIMO is one of the most advanced humanoids; it has the ability to recognize moving objects, postures, gestures, its surrounding environment, sounds and faces, which enables it to interact with humans. The robot can detect the movements of multiple objects by using visual information captured by two camera “eyes” in its head and also determine distance and direction. This feature allows ASIMO to follow or face a person when approached. The robot interprets voice commands and human gestures, enabling it to recognize when a handshake is offered or when a person waves or points, and then respond accordingly.
ASIMO’s ability to distinguish between voices and other sounds allows it to identify its companions. ASIMO is able to respond to its name and recognizes sounds associated with a falling object or collision. This allows the robot to face a person when spoken to or look towards a sound. ASIMO responds to questions by nodding or providing a verbal answer and can recognize approximately 10 different faces and address them by name
Another area where money is not much of an issue is missions to space. Since human life support in space is costly and space missions are dangerous, there is a need to complement or replace humans in space by human-like robots. The two prominent projects in this area are the NASA Robonaut and DLR’s Justin.
While in industrial mass production robot arms are used which are not anthropomorphic at all, the Japanese company Yaskawa sees a market for human-like dual-arm robots in manufacturing. It recently announced the Motoman-SDA10 robot which consists of two 7DOF arms on a torso that has an additional rotational joint.
An obvious domain for the use of humanoid robots is the household. Some humanoid projects explicitly address this domain. They include the Armar series of robots developed in Karlsruhe, Twendy-One developed at Waseda University, and the personal robot PR1 developed in Stanford.
A currently more viable application for humanoid robots is robot competitions. RoboCup and FIRA, for example, feature competitions for humanoid soccer robots.
After four decades of research on humanoid robots impressive results have been obtained, but the real-world capabilities of humanoids are still limited. This should not discourage further research. In fact, research on cognitive robots, including humanoids, is gaining momentum. More and more research groups worldwide are targeting this application. A good part of the difficulties humanoid robots face comes from perception. Here, more advanced methods are developed every year to cope with the ambiguities of sensory signals. The continuous improvements of computer vision and speech recognition systems will make it easier to use humanoid robots in un-modeled environments.
Advances are also to be expected from the mechanical side. Multiple research groups develop muscle like actuators with controllable stillness. Such compliant actuation will significantly contribute to the safe operation of robots in the close vicinity of humans. Compliance also leads to control schemes that support the dynamics of the body instead of imposing inefficient trajectories on it. Insights from biophysics and neuroscience also give ideas for robust control strategies, which degrade gracefully in case of disturbances or component failure.
In general, research on humanoid robots strengthens the respect for the biological model, the human. Much remains to be learned from it in areas like perception, mechanics, and control. I am convinced that it will be possible to understand many of nature’s inventions which account for its astonishing performance and in turn apply this on the humanoids.
The two major issues could hinder the widespread application of humanoid robots: costs and system complexity. It would however be very interesting to see how much part of human life humanoids will play and just how much human they can become.