The Future of Robotics

Life Like Robots

People have a fascination for anything that looks or acts human. Groups of visitors at the zoo will endlessly gaze at the chimpanzees, while the aardvark rarely receives a second glance. Children become mesmerized as they watch the animated characters performing at the local pizzeria, but when the animatronics go silent, the children will quickly lose interest. Robotic engineers are designing the next generation of robots to look, feel and act more human, to make it easier for us to warm up to a cold machine.

Robot Girl from World Expo 2005

Realistic looking hair and skin with embedded sensors will allow robots to react naturally in their environment. For example, a robot that senses your touch on the shoulder and turns to greet you.

Subtle actions by robots that typically go unnoticed between people, help bring them to life and can also relay non verbal communication.

Artificial eyes that move and blink. Slight chest movements that simulate breathing. Man made muscles to change facial expressions. These are all must have attributes for the socially acceptable robots of the future.



Robots to the Rescue


Carnegie Mellon University Millibots

Imagine yourself lost deep in the forest on a cold autumn night and nightfall is rapidly approaching. Too windy for search aircraft and too dark for ground teams, this could be a life threatening situation. Fortunately for you, it is ten years into the future and hundreds of tiny intelligent robots will be combing the woods for you throughout the night.

These all terrain robots (ATRs), will truly function as a team by sharing their locations, discoveries, search patterns and more. Large ATRs could carry many smaller robots and provide them with localized control and power.

These smaller more specialized robots will have cameras, sonar, heat sensors, motion detectors and can be sent out by the large ATRs as needed. Smaller robots might work together to perform tasks such as moving a large obstacle.

Getting robots to act as a team and to adapt to changing environments is no easy task. The Millibot project is a research effort being conducted at Carnegie Mellon University. The goal of this project is to construct a robotic team on the five to ten centimeter scale that provide extended surveillance and reconnaissance.

The Replicator –
No Simple Matter

It is easy to visualize how robots working together, can perform many tasks that a single robot cannot. Now picture billions of these robots, each robot about the size of a human cell, coalescing like self forming clay into any form. Continually scan a 3d image of yourself and your “virtual presence” can be anywhere.

But we are not there yet. The hard part is not necessarily the hardware (or bioware). Controllable devices are expected to be nano in size in the next 10 to 20 years. The biggest obstacle is the software that is needed to manage all of the robots and the decision making required to complete tasks in a changing environment.


Robotic Pets

DOMO

Human environments present special challenges for robots. They are complex, dynamic, uncontrolled, and difficult to perceive reliably.

Domo is a unique robot created at the MIT Computer Science and Artificial Intelligence Laboratory that has force sensing actuators throughout its body from the neck down. These actuators allow for safe human interaction with the robot by telling Domo, for example, how much force to apply when shaking your hand or how to hold a banana without bruising it. Many of today’s robots can be dangerous around people and are poorly suited for use in human environments. Domo’s hardware allows investigation of fundamental research issues surrounding manipulation.

BallBot

Carnegie Mellon Researchers Develop New Type of Mobile Robot That Balances and Moves on a Ball Instead of Legs or Wheels

“Ballbot”, developed by Robotics Research Professor Ralph Hollis, is a self-contained, battery-operated, omnidirectional robot that balances dynamically on a single urethane-coated metal sphere. It weighs 95 pounds and is the approximate height and width of a person. Because of its long, thin shape and ability to maneuver in tight spaces, it has the potential to function better than current robots can in environments with people.

ASIMO

ASIMO is “The world’s most advanced humanoid robot”, created by Honda Motor Company. Standing at 130 centimeters (4 feet 3 inches) and weighing 54 kilograms (119 lbs.), the robot resembles a small astronaut wearing a backpack and can walk on two feet in a manner resembling human locomotion at up to 6 km/h (3.7 mph).

ASIMO can run, walk, climb stairs and grasp objects. ASIMO can also understand and respond to simple voice commands. Using cameras for eyes, ASIMO has the ability to recognize the objects and people it has seen. ASIMO can also avoid moving obstacles as it moves through its environment.

Officially, ASIMO is an acronym for “Advanced Step in Innovative MObility”. Honda’s official statements indicate that the robot’s name is not an homage to science fiction writer and inventor of the Three Laws of Robotics, Isaac Asimov. In Japanese, the name is pronounced ashimo and, not coincidentally, means “legs also”.

The SuperBot

Another research project that focuses on reconfigurable robots is the SuperBot. A modular, multifunctional robot being developed by a team at the University of Southern California’s Polymorphic Robotics Laboratory. The SuperBot is being developed for use in space missions.

Modular Design

SuperBot will be made of many autonomous, intelligent, and self-reconfigurable modules. The modules are extreme examples of design for reuse. The system will interact with humans to detect unexpected module failures and repair malfunctions by reconfiguration.

The SuperBot can reconfigure into an “extended arm” for extravehicular maintenance; then reconfigure into multiple “flying eye/hands” for in-vehicle crew assistance. At the destination, the robot can optimally pack itself in a landing capsule to reduce the landing volume.

On the surface, it may morph into a “rover” to explore a flat environment, a “climber” to go down and up a crater, or a mobile “platform” to perform applications such as drilling, building, or sample collection. It may also perform exterior inspection of a habitat, or tend to the growing of plants inside a greenhouse.

Mirror, Mirror

When deciding whether a primate is self-aware, evolutionary
psychologists employ a controversial experiment called the mirror test. When confronted with a mirror, a rhesus monkey will treat its reflection as another monkey, displaying signs of aggression. Chimpanzees, on the other hand, will quickly begin to use the mirror to preen themselves and pick at their teeth. They realize that their mirror reflection is associated with their own physical self and begin to exhibit self-directed behavior. While the chimpanzees learn quickly, the other species of monkey never become aware of this correspondence. Thus, the chimpanzees are considered self-aware, but the other monkeys are not.

The mirror test not only plays a crucial role in the study of animal behavior, it also reveals insight into the development of self-awareness in humans. When confronted with an image of its body that is temporally contingent with its movement, such as a mirror reflection, a human infant exhibits signs of self-exploratory behavior from 3 months of age onwards. As early as at four months of age, babies display some measure of social self-awareness, showing more interest in experimenters imitating them than in their own reflections.

Most would agree that it is premature to label a robot that can identify its reflection in a mirror self-aware. We would probably expect self-aware robotic agents to possess introspection and reflection abilities leading to a far more complex sense of self than that afforded by simple visual self-identification. However, even if passing the mirror test is not a sufficient condition for self-awareness, it is still useful for a humanoid robot to be able to identify itself under a wide variety of circumstances. More about Nico, an infant-like humanoid robot currently in development at Yale.

The Talking Robot

The WT-6 talking robot is the creation of Atsuo Takanishi and his Ph.D. student Kotaro Fukui at Waseda University in Tokyo. Takanishi and his group used mechanical actuators and a variety of materials to re-create the entire human vocal system. The vocal cavity, tongue, vocal chords, lips, teeth, soft palate and lungs were modeled from soft plastics and polymers. According to listeners, the result is “clear, natural speech” – in Japanese, of course. Read more about this robot

WiiBot: How to build a sword-wielding, tennis-playing, WiiMote-controlled, friendly robot

Check out this project by two weekend warriors.

The idea was to take one industrial robot, add a laptop talking to a WiiMote, strap on a tennis racket, have it follow the swings that the user makes, and do it all in a few hours on a Saturday so we could get back to our busy schedules. Of course we had to put on a sword too”…

A Helping Hand

The Shadow Hand is designed to mimic the human hand. It provides 24 movements, allowing a direct mapping from a human to the robot.

The Shadow Hand has sensing and position control, allowing for precise control.

The Shadow Hand contains a bank of Air Muscles which make it move. The muscles are compliant, which allows the hand to be used around soft or fragile objects.

The Shadow Hand can be fitted with touch sensing on the fingertips, offering sensitivity sufficient to detect a single small coin. See the video


टिप्पणी छोड्नुहोस्