[StarTech] TechViews: Emotional Robots

http://www.thedailystar.net/story.php?nid=98268

Ever heard of a robot that is emotional? Robots are supposed to be cranky rude metallic creatures that seem to have machine-like robotic and completely emotionless voices, as started to be depicted by Isaac Asimov in his novels and to the more recent movie sequels of the Transformers. But behold! What if a robot, who looks meek and harmless, having stark similarities to one of the greatest physicists of all times, Albert Einstein looks at you and frowns? Or better still, gives you a sarcastic smile?

This week in Star Tech, we will look into some of the major advances in the world of robotics and its recent trends on research and development.

Take for example the Einstein robot head at University of California — San Diego (USA), which performs asymmetric random facial movements as a part of the expression learning process. The hyper-realistic robot at the university has learned to smile and make facial expressions through a process of self-guided learning. The UC San Diego researchers used machine learning to “empower” their robot to learn to make realistic facial expressions.

“As far as we know, no other research group has used machine learning to teach a robot to make realistic facial expressions,” said Tingfan Wu, the computer science Ph.D. student from the UC San Diego Jacobs School of Engineering who presented this advance on June 6 at the IEEE International Conference on Development and Learning.

The faces of robots are increasingly realistic and the number of artificial muscles that controls them is rising. In light of this trend, UC San Diego researchers from the Machine Perception Laboratory are studying the face and head of their robotic Einstein in order to find ways to automate the process of teaching robots to make lifelike facial expressions.

This Einstein robot head has about 30 facial muscles, each moved by a tiny servo motor connected to the muscle by a string. Today, a highly trained person must manually set up these kinds of realistic robots so that the servos pull in the right combinations to make specific face expressions. In order to begin to automate this process, the UCSD researchers looked to both developmental psychology and machine learning.

Developmental psychologists speculate that infants learn to control their bodies through systematic exploratory movements, including babbling to learn to speak. Initially, these movements appear to be executed in a random manner as infants learn to control their bodies and reach for objects.

“We applied this same idea to the problem of a robot learning to make realistic facial expressions,” said Javier Movellan, the senior author on the paper presented at ICDL 2009 and the director of UCSD’s Machine Perception Laboratory.

Although their preliminary results are promising, the researchers note that some of the learned facial expressions are still awkward. One potential explanation is that their model may be too simple to describe the coupled interactions between facial muscles and skin.

Moving on to machines which understand how we feel or what our mood is, we will look into a scenario at a New York (USA) restaurant where 46 supporters have gathered to watch the Super Bowl, America’s most popular televised sporting event, the advertisements of which are valued at USD 3 million for 30 seconds! Machines are monitoring these sports fans’ every move and every breath they take.

The viewers are wearing vests with sensors that monitor their heart rate, movement, breathing and sweat. A market research company has kitted out the party-goers with these sensors to measure their emotional engagement with adverts during the highly expensive commercial breaks. Advertisers pay a fortune during the Super Bowl, so they want to be as confident as they can be that their ads are hitting home. And they are willing to pay for the knowledge. “It’s a rapidly growing market – our revenues this year are four times what they were last year,” says Carl Marci, CEO and chief scientist for the company running the experiment, Innerscope Research based in Boston, Massachusetts, USA.

Innerscope’s approach is the latest in a wave of ever more sophisticated emotion-sensing technologies. The latest technologies could soon be built into everyday gadgets to smooth our interactions with them. In-car alarms that jolt sleepy drivers awake, satnavs (satellite navigation systems) that sense our frustration in a traffic jam and offer alternative routes, and monitors that diagnose depression from body language are all in the pipeline. Prepare for the era of emotionally aware gadgets!

The most established way to analyse a person’s feelings is through the tone of their voice. For several years, companies have been using “speech analytics” software that automatically monitors conversations between call-centre agents and customers. One supplier is NICE Systems, based in Ra’anana, Israel. It specialises in emotion-sensitive software and call-monitoring systems for companies and security organisations, and claims to have more than 24,000 customers worldwide, including the New York Police Department and Vodafone.

As well as scanning audio files for key words and phrases, such as a competitor’s name, the software measures stress levels, as indicated by voice pitch and talking speed. Computers flag up calls in which customers appear to get angry or stressed out, perhaps because they are making a fraudulent insurance claim, or simply receiving poor service.

Voice works well when the person whose feelings you are trying to gauge is expressing themselves verbally, but that’s not always the case, so several research teams are now figuring out ways of reading a person’s feelings by analysing their posture and facial expressions alone.

Using different techniques, computer programs can correctly recognise six basic emotions – disgust, happiness, sadness, anger, fear and surprise – more than 9 times out of 10, but only if the target face uses an exaggerated expression. Software can accurately judge more subtle, spontaneous facial expressions as “negative” or “positive” three-quarters of the time, but they cannot reliably spot spontaneous displays of the six specific emotions – yet. To accurately interpret complex, realistic emotions, computers will need extra cues, such as upper body posture and head motion.

All in all, we have seen major advancements in machines portraying emotions themselves and being able to comprehend, analyze and act accordingly to human emotions. Robots are fast becoming humans, or so it seems!

Compiled by Mahdin Mahboob

Information Sources: UCSD Website, NewScientist, stltoday.com

[News Room] Seminar on Fiscal Budget 09-10 at BRAC University

http://www.thedailystar.net/campus/2009/07/01/newsroom.htm

A seminar on Fiscal Budget 09-10 was held on the 24th of June at BRAC University. Organised by the Economics Club of the university, the seminar had Dr. Debapriya Bhattacharya, Distinguished Fellow of Centre for Policy Dialogue (CPD) as its chief speaker. Dr. Salehuddin Ahmed, Pro Vice Chancellor of the university presided over the event and delivered a speech on the historical aspects of Bangladesh’s budget.

[StarTech] TechViews: Tools of advanced warfare (Where is the limit?)

http://www.thedailystar.net/story.php?nid=95152

Before writing this article, I was having second thoughts as to how relevant this topic would be in the context of Bangladesh. But I was soon brought out of my dilemma by the fact that relevance has nothing to do with people’s interest in a certain subject. So here goes this week’s Lead News on the Star Tech page, on some of the recent advances of warfare tools the world has seen.

Imagine a scenario where, half a mile outside the enemy-held airport that is on the night’s objective, 100 U.S. Special Forces operatives stow their parachutes, regroup into squads, and prepare their attack. In the past, these soldiers wouldn’t have known where the enemy was or whether they were walking into an ambush –until the shooting started. They would have relied on printed maps with information that was likely to be several hours old when they boarded their C-130 for transport to the objective.

But this unit has advanced technology that gives it a decisive edge. Each soldier is equipped with a helmet-mounted GPS navigation receiver, a small wireless intrasquad voice and data comms system, and a wearable computer linked to an intrasquad LAN. From a flip-down display on his helmet, each soldier can scan the darkness with thermal and night-vision sensors mounted on his M-4 rifle. Each soldier navigates his computer through a track pad mounted beneath his uniform on top of his chest. For navigation and situational awareness, a soldier calls up his position on a map that automatically scrolls as he moves in any direction. The relative positions of his squad members are also displayed, as are surrounding buildings and suspected positions of enemy soldiers, updated in nearreal time via radio.

As each soldier and his squad members come within a few hundred meters of the airport buildings, they fan out. The soldiers approach the immediate objective: a structure believed to be, based on the latest intelligence data, the enemy’s sleeping quarters. One soldier takes up a position just outside the main door and swings his rifle into the doorway, surveying the scene via a camera mounted on his M-4 rifle, avoiding exposure to hostile fire.

Although this scenario may sound improbable, all this technology exists, with much of it deployed in parts by the US Defence. The development of smaller, faster, and cheaper computers, interface improvements, networks, database access, and improved software algorithms has put computing power in the hands of U.S. infantrymen and women.

Computers arrived just in time for World War II, and the military quickly adapted the room-size behemoths for ballistics predictions and code breaking. Throughout the Cold War, the U.S. and its allies poured money into IT to improve their weapons. By the time the Berlin Wall came down, radars and other sensors were using computer power to process more target information; missiles relied on embedded processors for guidance and control; and complex algorithms provided fire solutions that let tanks shoot on the move. In fact, computer-controlled avionics (aeronautical electronics) are the only reason the ungainly F-117 stealth fighter can fly.

By the time the Gulf War erupted in 1991, U.S. aircraft, ships, and tanks bristled with technology that boosted the performance of their sensors, communications, fire-control systems, and munitions. Greater processing power let weapons systems fuse their own sensor data with off-board intelligence feeds for greater situational awareness. As a result, U.S. forces could engage more distant targets and detect and defeat guided missiles with jammers that cycled through thousands of jamming techniques in the few seconds it took the missiles to reach their targets.

War vehicles have also recently seen a lot of change, with emphasis on aerodynamics, durability, strength and adaptability. However, interestingly enough, cost has always remained a lower priority with exorbitant price tags to these mighty machines.

One of the latest additions to the armoured vehicle fleet of the British Army will be a category of vehicle called the tactical support vehicle (TSV). In October 2008, 400 TSVs were ordered as part of the $700m protected patrol vehicles package. The new TSVs will be used to accompany patrols, and also to transport supplies such as ammunition and water.

The three types of vehicle include the Wolfhound a heavy armoured support vehicle to support and supply the new Mastiff with heavy mine protection (force protection), the Husky a medium armoured truck to carry out support in less threatened areas and the Coyote a light armoured support vehicle to support the new Jackal 2.

The Wolfhound TSV (heavy) and the Coyote TSV (light) will be produced as one variant, which is a utility flatbed vehicle that will be used to transport combat supplies. The Husky TSV (medium) will be produced as three variants; utility vehicle, ambulance with enhanced protection and command post vehicle.

The Jackal 2 has been designed to a high specification to protect personnel against roadside explosions and mine attack. The vehicle also has a special air-bag suspension system that allows rapid movement of the vehicle across varying terrain.

The vehicle is expected to be used for reconnaissance, rapid assault, fire support and convoy protection. The vehicle will have a range of 800km and will include a 7.62mm general-purpose machine gun (GPMG) and either a .50-calibre heavy machine gun (HMG) or grenade machine gun (GMG) as the main weapon system. The gun ring weapon in this machine has a 360° sweep of fire, much higher coverage than its predecessors.

Although, the key objective of most modern war machines is to minimize the number of personnel casualties by machines doing most of the work, it also means higher precision and hence higher number of people getting killed from the ‘enemy side’. With growing concerns and calls for ‘world peace’ by global leaders, spending on warfare, ironically enough, seems to be on the rise and shows no sign of decline!

Sources: pcmag.com, army-technology.com

Compiled by Mahdin Mahboob