Introduction   Historical Perspectives   Early Endeavors   What Is A Humanoid Robot?   Research Issues Past Problems with "Thinking robots" Building Intelligence from the Bottom-Up Learning by Doing: Automated Development through Real-World Interaction   Current Research Projects Legged Locomotion Arm Control and Dexterous Manipulation Robot-Human Interaction Service & Entertainment Robots Learning and Adaptive Behavior Perception Anthropopathic Robots   What Does The Future Hold?   Ethical Considerations   References   Glossary   Publications

What Is a Humanoid Robot?

Humanoid Robotics includes a rich diversity of projects where perception, processing and action are embodied in a recognizably anthropomorphic form in order to emulate some subset of the physical, cognitive and social dimensions of the human body and experience. Humanoid Robotics is not an attempt to recreate humans. The goal is not, nor should it ever be, to make machines that can be mistaken for or used interchangeably with real human beings. Rather, the goal is to create a new kind of tool, fundamentally different from any we have yet seen because it is designed to work with humans as well as for them. Humanoids will interact socially with people in typical, everyday environments. We already have robots to do tedious, repetitive labor for specialized environments and tasks. Instead, humanoids will be designed to act safely alongside humans, extending our capabilities in a wide variety of tasks and environments.

At present, Humanoid Robotics is not a well-defined field, but rather an underlying impulse driving collaborative efforts that crosscut many disciplines. Mechanical, electrical and computer engineers, roboticists, computer scientists, artificial intelligence researchers, psychologists, physicists, biologists, cognitive scientists, neurobiologists, philosophers, linguists and artists all contribute and lay claim to the diverse humanoid projects around the world. Inevitably, some projects choose to emphasize the form and mechanical function of the humanoid body. Others may focus on the software to animate these bodies. There are projects that use humanoid robots to model the cognitive or physical aspects of humans. Other projects are more concerned with developing useful applications for commercial use in service or entertainment industries. At times, there are deep ideological and methodological differences. For example, some researchers are most interested in using the human form as a platform for machine learning and online adaptation, while others claim that machine intelligence is not necessary. How can we characterize such a broad range of efforts?

An early version of Cog, developed under Rodney Brooks at the MIT AI Laboratory.

Defining a humanoid robot is a lot like defining what it means to be human. Most likely, you'll know one when you see it, and yet have trouble putting the characteristics on paper. The physical constitution of the body is clearly crucial. Not surprisingly, some have chosen to define a humanoid robot as any robot with two arms, two legs and a human-like head. Unfortunately, such a definition says nothing about the ability of this robot to receive information, process it and respond. Moreover, many Humanoid Robotics projects spend the majority of their efforts on a portion of the body such as the head, the legs or the arms.

Rather than distinguish humanoids by their physical construction, we choose to identify several complementary research areas that, thus far, have stood out as distinct emphases. Eventually, a fully-fledged humanoid robot will incorporate work from each of the areas below.

Robonaut works with creator, Robert Ambrose, Ph.D., to make a weld.

Perception:
This area includes computer vision as well as a great variety of other sensing modalities including taste, smell, sonar, IR, haptic feedback, tactile sensors, and range of motion sensors. It also includes implementation of unconscious physiological mechanisms such as the vestibulo-ocular reflex, which allows humans to track visual areas of interest while moving. Lastly, this area includes the attentional, sensor fusion and perceptual categorization mechanisms which roboticists implement to filter stimulation and coordinate sensing.

Human-robot interaction:
This area includes the study of human factors related to the tasking and control of humanoid robots. How will we communicate efficiently, accurately, and conveniently with humanoids? Another concern is that many humanoids are, at least for now, large and heavy. How can we insure the safety of humans who interact with them? Much work in this area is focused on coding or training mechanisms that allow robots to pick up visual cues such as gestures and facial expressions that guide interaction. Lastly, this area considers the ways in which humanoids can be profitably and safely integrated into everyday life.

Learning and adaptive behavior:
For robots to be useful in everyday environments, they must be able to adapt existing capabilities to cope with environmental changes. Eventually, humanoids will learn new tasks on the fly by sequencing existing behaviors. A spectrum of machine learning techniques will be used including supervised methods where a human trainer interacts with the humanoid, and unsupervised learning where a built-in critic is used to direct autonomous learning. Learning will not only allow robust, domain-general behavior, but will also facilitate tasking by hiding the complexity of task decomposition from the user. Humanoids should be told what to do rather than how to do it.

Legged locomotion:
For humanoids to exploit the way in which we have structured our environment, they will need to have legs. They must be able to walk up stairs and steep inclines and over rough, uneven terrain. The problem is that walking is not simply a forwards-backwards mechanical movement of the legs, but a full-body balancing act that must occur faster than real-time. The best approaches look closely at the dynamics of the human body for insight.

Arm control and dexterous manipulation:
Around the world, researchers are working on dexterous tasks including catching balls, juggling, chopping vegetables, performing telesurgery, and pouring coffee. From a mechanical point of view, robot arms have come a long way, even in the last year or so. Once large and heavy with noisy, awkward hydraulics, some humanoids now have sleek, compliant limbs with high strength to weight ratios. While mechanical innovation will and should continue, the real hard problem is how to move from brittle, hard-coded dexterity toward adaptive control where graceful degradation can be realized. The humanoid body functions as a whole and consequently, small errors in even one joint can drastically degrade the performance of the whole body.