Technology Used In Asimo Robot

Abstract Artificial intelligence and their applications are now pervasive throughout the world. AI & their applications play vital role in day to day life of human being. This paper discusses the one application of AI that is ASIMO Robot. ASIMO is latest curiosity topic in AI nowadays. It stands for “Advanced Step in Innovative MObility”, and is the most advanced humanoid robot in the world. ASIMO is the first humanoid robot in the world that can walk independently and climb stairs. ASIMO uses AI techniques that are Recognition of moving objects, Posture/gesture recognition, Environment recognition, Sound recognition & Face recognition. We will concentrate on these techniques

1.         Introduction: Over the past couple decades much work, and progress, has been made in the pursuit of creating artificial minds and lifelike humanoid movement. Researchers from many different nations have experimented with recreating realistic human characteristics - with some success. Honda's humanoid robot ASIMO (Advanced Step in Innovative MObility), leads the way in mobility, In starting first three models (E1 through E3) focused on what engineers felt was the most difficult task; walking on two legs. Then three models (E4 through E6) focused on balancing those legs. Those first six prototypes took a combined six years to perfect. These were followed by "humanoid prototype models" in 1993, 1996 and 1997 and were numbered P1, P2 and P3 respectively. P1 was over 6 feet tall and weighed almost 400 pounds. By the P3 model, the size and weight of the ASIMO prototypes were a mere five foot two inches tall and weighed just under 300 pounds. At this point the P model prototypes had the ability to walk, climb and descend stairs as well as complete a handful of other engineer-controlled movements. The first true ASIMO debuted in 2000 and was improved upon; ASIMO "for hire" was produced in 2001, "intelligent" ASIMO in 2002, "next-gen" ASIMO in 2004 and "New" ASIMO in 2005

We are focusing on new Generation Asimo which is 120 cm high robot has already mastered the complicated balancing act required when walking, running and jumping and it can safely navigate around random objects. It is also capable of recognizing people and faces and greets people accordingly, he can also move where indicated and recognize his name. ASIMO is able to recognize color, depth, movement, speed, and light. ASIMO is capable of checking path congestion while walking in busy street, it constantly scanning and checking whether the path is clear or not. Further, utilizing networks such as the Internet, ASIMO can provide information while executing tasks such as reception duties. Additionally, ASIMO can use its programming to recognize when a collision is imminent and can avoid it smoothly.

  

ASIMO was meant to be a helper to human beings in a household environment, particularly people who are bed-ridden or in wheelchairs. ASIMO's size is deliberately set at four feet tall to "look" its owner in the face. ASIMO’s were able to detect small shifts in each other's movements and correct themselves accordingly, proving that ASIMO could "think" its way out of a situation.

ASIMO can be controlled by four methods:

 

·        PC :- Using wireless technology and a laptop or desktop computer, you can control ASIMO as well as see what ASIMO sees via its camera eyes. ASIMO can also use its PC connection to access the Internet and retrieve information for you, such as weather reports and news.

 

·        Wireless controller (sort of like a  joystick) :-  The wireless joystick controller operates ASIMO's movements the same way you would operate a remote-control car. You can make ASIMO go forward, backward, sideways, diagonally, turn in place, walk around a corner or run in circles. Making ASIMO move by remote control may not seem that advanced, but ASIMO does have the ability to self-adjust its steps. If you have it walk forward, and it encounters a slope or some sort of obstacle, ASIMO automatically adjusts its steps to accommodate the terrain.

 

 

·        Voice commands :- ASIMO can understand and execute simple, preprogrammed verbal commands. The number of commands that can be programmed into its memory is practically unlimited. You can also have your voice registered in its programming, making it easier for ASIMO to recognize you. In addition to the voice commands for controlling ASIMO's movements, there are also spoken commands to which ASIMO can respond verbally. This is the feature that has made it possible for ASIMO to work as a receptionist, greeting visitors and answering questions.

 

·        Gesture :- Like most other technologies in the robotics field, ASIMO is powered by servo motors. Which helps the asimo to maintain gesture of the body. These are small but powerful motors with a rotating shaft that moves limbs or surfaces to a specific angle as directed by a controller. Once the motor has turned to the appropriate angle, it shuts off until it is instructed to turn again. For example, a servo may control the angle of a robot's arm joint, keeping it at the right angle until it needs to move, and then controlling that move. Servos use a position-sensing device (also called a digital decoder) to ensure that the shaft of the motor is in the right position. They usually use power proportional to the mechanical load they are carrying. A lightly loaded servo, for example, doesn't use much energy.
ASIMO has 34 servo motors in its body that move its torso, arms, hands, legs, feet, ankles and other moving parts. ASIMO manages a series of servo motors to control each kind of movement.

 

 

2.         Recognition of Moving Objects & Environment: Using the visual information captured by the camera mounted in its head, ASIMO can detect the movements of multiple objects, assessing distance and direction. Specifically, ASIMO can:

·        follow the movements of people with its camera

·        follow a person

·        greet a person when he or she approaches

·        ASIMO is able to assess its immediate environment, recognizing the position of

obstacles and avoiding them to prevent collisions in robotics, vision is a captured image that is interpreted based on programmed templates. In a manufacturing environment, where robotic arms build cars or robots inspect the microscopic connections on Another way ASIMO can sense the environment is through the use of IC Communication cards. IC cards use semiconductor chips, you're dealing with a controlled environment. The lighting is always the same, the angle is always the same, and there is a limited number of things to look at and understand. In the real (and unstructured) world, however, the number of things to look at and understand increases greatly. A humanoid robot that must navigate through homes, buildings, or outdoors while performing jobs must be able to make sense of the many objects it "sees." Shadows, odd angles and movement must be understandable. For example, to walk on its own into an unknown area, a robot would have to detect and recognize objects in real time, selecting features such as color, shape and edges to compare to a database of objects or environments it knows about. There can be thousands of objects in the robot's "memory." ASIMO's vision system consists of two basic video cameras for eyes, located in its head. ASIMO uses stereoscopic vision and a proprietary vision algorithm that lets it see, recognize, and avoid running into objects even if their orientation and lighting are not the same as those in its memory database.

 

These cameras can detect multiple objects, determine distance, perceive motion, recognize programmed faces and even interpret hand motions. For example, when you hold your hand up to ASIMO in a "stop" position, ASIMO stops. The facial recognition feature allows ASIMO to greet "familiar" people. ASIMO can recognize objects in motion by interpreting the images captured by the cameras in its head. It can assess a moving object’s distance and direction, which allows ASIMO to follow a person, stop its own progress to allow a moving object to cross its path, or greet you as you approach. The cameras also relay what ASIMO sees to ASIMO's controller. That way, if you're controlling ASIMO from a PC, you can see what ASIMO sees. In addition to the cameras in its head, ASIMO has several sensors that help it maneuver through environments and interact with objects and people. Floor surface sensors allow ASIMO to detect objects and changes in the floor. Ultrasonic sensors help orient ASIMO by detecting surrounding objects. The sensors help ASIMO resolve discrepancies between the internal map of the area preprogrammed in its memory and the actual environment.

 

ASIMO even has a sense of touch, in a way. The force sensors in ASIMO's wrists allow ASIMO to judge how much force to use when picking up a tray, handing you a file or shaking your hand. ASIMO can integrate information gathered by its cameras and force sensors to move in sync with a person while holding hands. When pushing a cart, ASIMO's force sensors help the robot to adjust the amount of force needed to push the cart (for example, ASIMO can push a cart with more force if the sensors detect an incline). infrared signals to receive and transmit information. If you hold an IC card with your information encoded on it, ASIMO can detect your presence even if you aren’t within the line of sight of its cameras. These cards enhance ASIMO’s ability to interact with others. For example, if you were to visit Honda’s office and receive an IC card as a visitor pass, ASIMO could greet you and direct you to the right room after electronically reading the information encoded on your card.

 

3.         Recognition of postures and gestures: Based on visual information, ASIMO can interpret the positioning and movement of a hand, recognizing postures and gestures. Thus ASIMO can react not only to voice commands, but also to the natural movements of human beings. For example, ASIMO can:

 

·        recognize an indicated location and move to that location (posture recognition)

·        shake a person's hand when a handshake is offered (posture recognition)

·        respond to a wave by waving back (gesture recognition)

 

For posture ASIMO has soft projections on its feet that play a similar role to the one our toes play when we walk. This soft material also absorbs impact on the joints, just as our soft tissues do when we walk. ASIMO has hip, knee, and foot joints. Robots have joints that researchers refer to as "degrees of freedom." A single degree of freedom allows movement either right and left or up and down. ASIMO has 34 degrees of freedom spread over different points of its body in order to allow it to move freely. There are three degrees of freedom in ASIMO's neck, seven on each arm and six on each leg. The number of degrees of freedom necessary for ASIMO's legs was decided by measuring human joint movement while walking on flat ground, climbing stairs and running. ASIMO also has a speed sensor and a gyroscope sensor mounted on its body. They perform the tasks of:

 

·        Sensing the position of ASIMO's body and the speed at which it is moving

·        Relaying adjustments for balance to the central computer

 

These sensors work similarly to our inner ears in the way they maintain balance and orientation. ASIMO also has floor surface sensors in its feet and six ultrasonic sensors in its midsection. These sensors enhance ASIMO's ability to interact with its environment by detecting objects around ASIMO and comparing gathered information with maps of the area stored in ASIMO's memory. To accomplish the job our muscles and skin do in sensing muscle power, pressure and joint angles, ASIMO has both joint-angle sensors and a six-axis force sensor.  The most significant part of ASIMO's walk is the turning capabilities. Rather than having to stop and shuffle, stop and shuffle, and stop and shuffle into a new direction, ASIMO leans and smoothly turns just like a human. ASIMO can also self-adjust its steps in case it stumbles, is because businesses need to be efficient to keep up with the industry competition. Therefore, having robots helps business owners to be competitive, because robots can do pushed, or otherwise encounters something that alters normal walking. In order to accomplish this, ASIMO's engineers had to find a way to work with the inertial forces created when walking. For example, the earth's gravity creates a force, as does the speed at which you walk. Those two forces are called the "total inertial force." There is also the force created when your foot connects with the ground, called the "ground reaction force." These forces have to balance out, and posture has to work to make it happen. This is called the "zero moment point" (ZMP).

To control ASIMO's posture, engineers worked on three areas of control:

·        Floor reaction control means that the soles of the feet absorb floor unevenness while still maintaining a firm stance.

·        Target ZMP control means that when ASIMO can't stand firmly and its body begins to fall forward, it maintains position by moving its upper body in the direction opposite the impending fall. At the same time, it speeds up its walking to quickly counterbalance the fall.

·        Foot-planting location control kicks in when the target ZMP control has been activated. It adjusts the length of the step to regain the right relationship between the position and speed of the body and the length of the step.

 

4.         Sound Recognition:Asimo has the ability to understand three voices at once, thanks to an array of eight microphones that can recognize each voice individually. The recognition software, HARK, can process the commands with 70-80 percent accuracy and the microphones are placed all over Asimo’s head and body for spatial recognition purposes. The current application for this technology is using Asimo as a judge for verbal Paper-Rock-Scissors, where everyone calls out their answer at once, and Asimo decides who said what, and who wins.

 

5.         Face recognition: ASIMO relies on facial mapping, recording the topographical features of a person's face and electronically storing the data in its internal memory. When ASIMO sees a face, it compares what it sees with the data in its memory to try to identify a match. If a match is found, ASIMO will respond with a unique greeting for that person even when ASIMO or the human being is moving. For example, ASIMO can recognize the faces of people which have been pre-registered, addressing them by name, communicating messages to them, and guiding them.

 

6.         Conclusion: Today we find most robots working for people in industries, factories, warehouses, and laboratories. Robots are useful in many ways. For instance, it boosts economy jobs better and faster than humans can, e.g. robot can built, assemble a car. Yet robots cannot perform every job; today robots roles include assisting research and industry. Finally, as the technology improves, there will be new ways to use robots which will bring new hopes and new potentials.

7.         References:

1.      http://www.ehow.com/about_4673049_cansimo-do.html    

2.      http://world.honda.com/ASIMO/technolog y/intelligence.html

3.      http://en.wikibooks.org/wiki/The_Computer_Revolution/Artificial_Intelligence/ASIMO

4.      http://www.tridentgarages.co.uk/home_showroom_honda_thefuture_hondaasimo

5.      http://science.howstuffworks.com/asimo5.htm

6.      http://www.gizmodo.com.au/2008/06/_asimo_understands_multiple_people_yelling_at_once_ has_future_on_wall_street_-2/#more-292922

7.      Elaine Rich and Kevin Knight: Artificial Intelligence published by Tata McGraw Hill.

8.      Dan W. Patterson: Introduction to Artificial Intelligence and Expert Systems- Prentice India.

9.      Nils J.Nilson: Principles of Artificial Intelligence–Narosa Publishing House.

10.  Clocksin & S.Melish: Programming in PROLOG-Narosa Publishing House.

11.  M.Sasikumar, S.Ramani etc.  Rule based Expert System Narosa Publishing House