As a child, I watched "Star Wars", saw robots C3Po and R2D2 and dreamed of his own robot. This desire grew even stronger when I saw "Jetsons" family robot housekeeper Rosie, who worked flawlessly doing the housework. I've always felt that a personal robot could come in handy as your own chef, trainer, and companion. It seems that the future has come into our lives, because now more and more advanced models of robots for the home appear on the market and are even cheaper than the iPhone or MacBook. Let's take a look at 12 personal robots for the home: some of them are more human, others less, but they can all make your life better.
Pepper fromSoftBank Robotics
Pepper is one of the line of robots most similar to humans. This robot is said to be capable of recognizing human emotions. Pepper detects your emotions and reacts to them with the appropriate mood. Today the Pepper robot is used for a variety of commercial purposes in Japan, but it can also be a great friend at home.
Jibo
Jibo is a cute little robot that reminds me of the Wall-E robot from the Pixar movie of the same name. He does not move independently, but this family robot learns from everyone who communicates with him - and remembers everything that you share with him. Jibo will speak to you the next time you enter the room, and don't be surprised if he makes a joke.
Kuri fromMayfield Robotics
Kuri is a fun friend and a good helper with some serious tech content. The robot is mobile, equipped with WiFi, Bluetooth, 1080p camera and face recognition. He also has the ability to telepresence, which allows you to talk through the robot with other people at home. He can move around the house, avoiding obstacles and pets, and additionally play the role of a home monitoring system, since he hears and sees everything that happens in the house. Kuri emits beeping sounds similar to R2D2 from Star Wars... Kuri can take photos and save content daily in the app on your phone - where you can view, edit and send this content to friends.
Zenbo fromAsus
Zenbo is a smart mobile robot that can communicate, help and entertain you when you need it. While you are at home, Zenbo learns and adapts to you, and when needed, shares his emotions. Zenbo can help with reminders, control home devices, act as a security system when you are away, and even entertain children with fairy tales.
Lynx fromUbtech
Lynx is a humanoid robot that provides mobility to the Alexa voice assistant. Lynx can order the products it needs directly from Amazon using simple voice commands. Lynx is equipped with face recognition and personalized greetings. It can play music and keep you safe by broadcasting what is happening in the house.
Budgee from 5Elements Robotics
Looking for another pair of hands to help you carry around the house or yard? Then you need Budgee. Budgee is a friendly, hardworking robot that helps you carry things.
Hub Robot fromLg
LG's Hub Robot is a smart home assistant powered by Alexa voice service. It can help make your home smarter by simply placing the robot in the most active place in your home. The robot reacts to your movements with nods and simple answers. It can take care of everything from creating the mood and playing music to turning the air conditioner on and off. The interactive flat panel displays messages, videos, and photos. Using facial recognition, Hub Robot can recognize family members. This robot is currently not on sale yet, but we hope it will be available soon as it was first shown at the Consumer Electronics Show in January 2017.
Olly Robot fromEmotech
Olly Robot is a mix of smart home hub and personal robot. This round tabletop device is designed to make your day better. Olly is a London-based robot startup that learns how you would like to communicate, then answers your questions and controls the connected devices.
Robo temi
Temi is a personal robot for the home: it is smarter than a telepresence robot, so it can take on the role of a personal assistant on wheels. Temi was designed to be a video chat and music machine to keep you entertained and connected. Temi runs on the Android operating system, so it's compatible with many of your favorite apps.
Aido fromIngen Dynamic
Aido is a family home robot that can move around the house and help and improve your life. Aido can do everything: from playing with your kids to helping around the house, doing everything planned. Aido can keep connected and safe in the home thanks to its mobile and visual capabilities.
Personal Robot fromRobot Base
This creatively named robot does a lot. As we said earlier, Personal Robot is equipped with all the basic functions such as: face recognition, photo capability, alarm clock, accurate language recognition and offline navigation. In addition, it can create a map of your home using navigation and mapping algorithms. Personal Robot can also interact with other home devices, such as the Nest smart thermostat and others, so it can help automate your home.
Personal robotQ. Bo open source
Looking for a 2-in-1: both a personal robot and an experiment robot? Meet Q.Bo, an open source robot that allows you to add the required functionality and thus create the most personalized robot. Q.Bo is equipped with basic functions and technical capabilities, but they can be expanded. This robot is perfect for children, parents and educators - after all, you can invent and customize the personal robot you want from it.
BONUS
Erica is a Japanese robot based on Android
This robot is not yet being produced for a mass audience, I just thought it might be worth listing to show the direction the robots are heading. Erica reminds me of the bad Westworld robot. It is possible that soon robots will be more human-like, like Erica, and even be able to work among us, or maybe they are already among us - then ominous music follows.
We are still at the beginning of the era of artificial intelligence and personal robots for the home. I am confident that this group of robots, which currently looks like a new HTML web page during the Internet revolution, will be supplanted by more advanced tools. However, it's fascinating to see how things are moving towards the future - towards what we've seen on the big screens and what we've been looking forward to over the past few decades.
Assistant robots.
1. Robot artist-hooligan.
A robot invented to help painters. This robot, created by Japanese designers, can do only one thing - paint walls. To paint the walls, the robot uses a twin hose, which is hinged and connected to the tank. There are several tanks and several shades of paint can be poured into them and the robot will take turns applying them to the surface to be painted. The robot moves using a chassis and an electric motor.
2. Robot fish.
A robot fish named Danio was created to monitor the composition of water and purify it, as well as to study the behavior of fish in their natural environment. Danio is developed at the British Institute of Physics. The design of the fish robot should be such that, being constantly in the aquatic environment, the work of the internal elements in no case is disturbed.
The robot fish has the appearance of a Danio fish, which is why it acquired this name. The robot is so similar to the species of Danio's fish that when placed in the company of fellows, they, in turn, could not understand that she was a robot and tried to nail her to the flock. The robot is completely autonomous and can spend a long time in water.
3. SCV is a robot rescue.
A robot created by Japanese designers. Due to the fact that the Japanese islands are prone to devastating earthquakes and tsunamis, it is very difficult for rescuers to look for people under the rubble, and the designers of robots have created a rescue robot to help them. The robot is equipped with video cameras and the ability to transmit images to a remote monitor.
In addition to the cameras, the robot is equipped with two wheels and a guide track. The robot's unusualness lies in the fact that its entire body is hidden in a solid leather casing, and the cameras are hidden under powerful glass. Thanks to this, the robot is not afraid of dust, dirt, or water, which can damage its insides. At the moment there is a small prototype of this robot, but it is known that in the future it is planned to make a massive machine out of SCV (Slug Crawler Vehicle) that will help in finding people.
4. AutoMee Robot Screen Cleaner. Little cleaner.
AutoMee Robot Screen Cleaner is a small robot that can keep your tablet clean. A small $ 40 toy designed to wipe the screen of your tablet.
Thanks to this little assistant, there will be no more dust and fingerprints on the screen of your tablet.
5. Vacuum robot cleaner.
And here's another little robot to help you keep your desk clean. Everyone has already heard about the vacuum robot vacuum cleaner, but we present you with its little brother. If you often eat buns, cookies or other foods that crumble easily at your desk, then this small, vacuum robot cleaner is just for you. It moves silently across the table and draws in all the crumbs.
6. Robot for cleaning windows.
Having rummaged through the Internet, I realized that there are a great many such robots. Slightly fewer than robotic vacuum cleaners. Such a robot will easily wash your dusty windows.
The vacuum keeps the robot on the glass and does not fall down. The robot itself chooses the route along which it will be easier for him to bring your windows to shine. This pleasure will cost you about $ 600.
7. Robots are gardeners.
Gardening robots from Harvest Automation. These robots are designed to help gardeners grow potted plants. In general, robots gardeners do nothing except drag the pots with plants from place to place, but for large greenhouses, where millions of pots are a great help. Considering that plants in pots need to be watered, fed, pruned, it turns out that you can move them happens very often.
Robot gardener
The gardener robot moves the pots at a given distance and places them at a distance from each other such as is currently set in his program. The parameters can be changed. For the robot to work, the gardener only needs a magnetic tape attached to the floor by which he orients himself in space.
8. Robot strawberry picker.
Another robot designed to facilitate the work of gardeners. The strawberry picker robot, like most modern robots, is developed by a Japanese company. The two-meter robot is designed to work in special greenhouses. In Japan, strawberries are grown differently from ours. Japanese strawberries grow in special greenhouses, and to save space inside the greenhouses, there are multi-tiered racks, and strawberries grow on these racks.
The strawberry picking robot rolls along the racks and, with the help of three cameras, estimates the ripeness of the berry, with which it also determines the distance to the berry. After calculating the ripeness of the fruit and the distance to it, the robot cuts the berries into a tray using a mechanized gripper. As conceived by the developers, the picking robot can pick strawberries at night, and the farmer, having come to work in the morning, should only check if any berry is hidden from the robot behind a leaf.
9. Robot lantern.
Probably in the near future such robots-lanterns will roam the streets of all the megalopolises of the world, but so far they have appeared only in Japan. The device is called Toro-bot and it looks like some kind of alien creature.
Infrared sensors built into the robot allow the robots to navigate in space and detect the approach of a person. In addition, robots also have beacons that help them recognize each other. Each robot can be configured individually and give it its own line of behavior.
10. Robot carrier.
A budgee porter who has to follow his owner everywhere and carry his purchases. The robot has two wheels, a basket with a capacity of 22 kg. The robot does not have a navigation system, it just tirelessly watches its owner and follows on the heels everywhere. For this, the robot has a special ultrasonic transmitter.
There is also a special program for smartphones to configure the robot, where you can specify at what distance the budgee should roll. After you have made purchases with budgee, you can pack it and put it in the trunk, for example.
Written by
Barbara
Creativity, work on a modern idea of \u200b\u200bworld outlook and constant search for answers
“Robot Scientist” attended a robotics lesson and overheard what the students of the “Robot and Me” club were dreaming about.
At the age of 7, little robotics know 3 kinds of levers (do you remember?) And they assemble ready-made robots in a lesson. Boys make sure that batteries are disposed of exclusively in a special box, and not in a common trash can. They, as adults, refer to the teacher only by name, but by “you”.
They also know that when they grow up, they will build robots to help humanity. Young engineers dream of conquering space, defeating enemies and troublemakers. Well, win the robot competition. "Robot Scientist" attended a robotics lesson and wrote down the answers to the question about what kind of robots the guys dream of creating.
Dima Tatarinov, 8 years old
“I don't know yet what kind of robot I want to make. But he will definitely help humanity. For example, make calculations for scientists and fly to distant planets. When he arrives on a new planet, he will place the Russian flag there. "
Misha Fedorov, 10 years old
“I want to create a radio-controlled robot. The remote control will have a screen that will show where the robot is driving and what actions it does. This robot will issue parking tickets. The robot itself will have a printer that prints penalty checks. He will be fast, because he needs to manage to distribute fines before the offender leaves. ”
Artem Soloviev, 8 years old
“It will be a tank that drives without a driver. Nobody will control it at all, I will create such a system so that the tank itself knows what to do. He will transmit the picture to the headquarters and if anything, it will be possible to take control on the remote control. It can also be hit by a projectile and disrupt the self-control sensor. He can shoot himself, he will have a barrel for large shells, for bombs and two machine guns. Then you can make the same plane. In general, I want to become a military man and create something to make our army stronger. "
Maxim Khotuntsev, 10 years old
“Well, I would not say that it will be a robot. I would like to create a costume. He'll have acid stuff on his sleeves, and flying stuff on his legs (like Tony Stark). There will be two masks on the helmet, the inner one will be terrible, with glowing eyes. It will be possible to spray a toxin from it, from which it will seem to enemies that something strange is happening around. He will have a sword and a flamethrower, just in case. And scorpion venom. The suit will be armored but lightweight. He will be called "Black Adam", there is such a pirate.
And he will also have a thing that will slow down time. If it flies back and forth at high speed, then most likely a time portal will form at this place and, probably, I will be able to see the future. Probably."
Timofey Kuznetsov, 10 years old
“My robot will help explore black holes. People are afraid to fly there, no one knows what is there. And the robot could be sent to study some black hole. He, as a person, will think for himself, he will have artificial intelligence. I would like to develop artificial intelligence for it myself. ”
Seryozha Oruzheinikov, 9 years old
“My dream is to build a robot that can constantly protect me from bad boys. Or it won't be a robot, but a robotic suit. He will be able to do everything, even turn into a car and run on batteries. From this it will be called - "Defender".
Sasha Fedorov, 8 years old
“I want to invent a robot soccer player for our competition. He himself will be about 50 cm and will be able to kick the ball up to 1 meter high. Maybe I will be able to assemble a few more of these, a whole team. These robots will play soccer until they run out. I think I can make such robots in 10 or 12 years. "
Arseny Rodkin, 7 years old
“My robot will help scientists to bring the future to life as soon as possible. He will create new technologies himself.
And also at school I drew a pen that writes itself, a flying backpack and a notebook that writes itself for the teacher! "
Styopa Eshukov, 11 years old
“What kind of robot do I want to invent? It depends on what topic. For our competitions (competitions on the basis of the "Robot and I" club - ed.) In football - one, for the battle of robots - another. For battle, I want to build a large robot that will ride on tracks. But not on plastic ones, because the plastic will slip. He will have thorns from different sides: he will drive up, stick them into the enemy and knock out his parts. There will also be a mechanism on top that will lift other models, something like a crane.
In football competitions, control is more important, because the victory does not depend much on the model itself.
And for racing I want to build a fast and well-controlled model. I will put the gearbox at speed, on the rear wheels, the front wheels will be low. It will still need to be finalized. "
A person spends a significant part of his time on doing such monotonous and monotonous household chores, such as cleaning the room or working in the garden. Some people get real pleasure from this kind of activity, but for most, putting the living space in proper order is a routine, boring and not very pleasant task. Since the 50s and 60s of the last century, when the concept of a “robotic assistant” was just beginning to emerge, society has already dreamed of shifting part of its daily duties to a soulless mechanized device that is not subject to fatigue, stress and is ready to do the dirtiest work. We are talking about robotic servants and automated assistants, prototypes of which appeared more than half a century ago.
The first mobile robot that analyzes commands and actions
In 1966, engineers at the Center for Artificial Intelligence at Stanford University set about creating a robot capable of self-orientation and movement indoors without creating an emergency. The project involved the development of a structure on a wheeled chassis with the possibility of self-learning, as well as a holistic analysis of the tasks assigned to the machine.
The device, dubbed Shakey, was equipped with a set of sensors and a television camera to determine the current location and dimensions of objects surrounding the robot. In 1972, the Shakey project came to an end, embodying the advanced achievements of the engineers of the time into a single design. The mobile device demonstrated its capabilities in a special test pavilion of several rooms connected by corridors. The robot carried out the commands of scientists, pushing various objects, closing and opening doors, interacting with switches and various objects.
The prospect of the algorithm incorporated in Shakey pushed scientists to further work in this direction and to create a number of more advanced automated mechanisms, as well as to implement the ability of such a device to identify and respond to voice commands.
.png)
Wireless and standalone lawn mowing
In 1969, MowBot Inc. introduced the world to a robotic lawnmower that operates on a built-in battery without the need to connect to a home network. The battery charge was sufficient for cutting grass on an area of \u200b\u200b650 m 2. And although the $ 795 device was very far from modern programmable "smart" devices that can be controlled even from a smartphone, the idea of \u200b\u200bgetting rid of wires turned out to be very interesting and received a logical development.
Full-size robot Arok: walks with a dog and takes out the garbage
What "house of the future" can do without robotic servants? A similar thought came to the inventor Ben Skora, who presented his vision of futuristic, taking into account the 70s of the last century, dwellings with remote-controlled lamps and other technical innovations. Not without "smart" service personnel, which was replaced by a two-meter robot Arok with a frankly creepy face.
The mechanized giant's tasks included taking out the trash, serving drinks, and even walking your four-legged pet. Of course, the presence of an operator to manipulate the device was imperative. So the staff in the "house of the future" provided for an additional vacancy to control the robot assistant.
Japan's popular game robot Omnibot: background
3DNews readers are familiar with a device called the Omnibot. But much less is known about its progenitor, which became one of the most compact robots of its time - the Omnibot 2000. An unusual device was released in 1984, and it represented, as it is today, a super-technological and advanced autonomous model on the market for the most unusual toys of that time.
Omnibot 2000 had the ability to remotely control, however, the developers provided for a completely independent movement of their brainchild along a pre-established route. All the data necessary for the programmed movement was recorded on a cassette, and the robot could be used as a waiter for delivering food and drinks at a large party.
SynPet Newton: a domesticated version of the "star" R2D2
If you liked the cute and quirky robot R2D2 from George Lucas's Star Wars saga, then you will be interested to know that from the late 1980s to the early 1990s its commercial analogue - SynPet Newton. Of course, this robot with a height of about 86 cm cannot be called an exact copy of the legendary R2D2, but the similarity in design, as they say, is "evident".
SynPet Newton was able to move freely around the apartment, boasted voice control and helped to cope with household chores. A 16-bit microprocessor chip was responsible for its performance, as well as a wide range of sensors for fully autonomous movement in accordance with the selected mode. At the same time, SynPet Newton could communicate with residents using a special voice synthesizer, as well as provide communication between its owner and the outside world using a built-in wireless phone and modem.
True, only the wealthiest Americans could afford SynPet Newton, because the price of a "smart car" was a fabulous $ 8,000.
The crown of evolution of humanoid robots from Honda engineers
Perhaps the most famous humanoid robot today is a Honda device called ASIMO. It took the engineers of the Japanese company about ten years to eventually bring the prototype parameters to the current limit in the form of a combination of high travel speed, extraordinary dexterity and advanced human interaction.
ASIMO is capable of welcoming guests with a handshake and serving drinks no worse than a real waiter would.
iRobot Roomba: Responsible for the cleanliness of your home
Robot vacuum cleaners did not manage to become a common gadget in the homes of ordinary users due to their high cost. However, some models nevertheless had commercial success and took root in the apartments of their owners, as did one of the first home mechanized cleaners - the iRobot Roomba. The main task of the device, which appeared on the market 12 years ago, is high-quality, and most importantly, completely autonomous cleaning of the most difficult types of flooring.
Humanoid robot Reem: both a loader and an information center
Have you often had a chance to move around a railway station or airport with bulky and heavy luggage, and at the same time try to find out the information necessary to board a flight? It seems that this problem in Spain, where PAL Robotics is based, prompted a team of four engineers to develop the Reem-A porter robot.
Previously, the developers already had experience in designing humanoid machines that take on the role of maintenance personnel. This made it possible in 2012 to present a commercial Reem model with a telecontrol function, which is not only capable of transporting goods, but also acts as an information and information kiosk.
Subsequently, the device was upgraded to the REEM-C version - both legs were returned to it, as it was envisaged in modifications with the index "A" and "B".
Your personal robotic bartender for $ 2700
If we discard the procedures that require movement in space, lifting of loads and complex mechanical manipulations, then what would a small stationary robotic device be useful for? Of course for making a variety of cocktails. The Monsieur robot has become an example of a skillful automated bartender who will not only prepare your favorite drink, but also joyfully greet its owner upon returning home. To do this, the designers provided a function for determining your stay in the apartment using an application for a mobile device that provides synchronization with Monsieur and machine controlvia Bluetooth and Wi-Fi.
The system is able not only to fulfill orders for cocktails remotely from a smartphone or tablet, but also to offer you double portions of drinks in case you are late at work and you have a very busy day.
The main feature of the 23 kg drawer with touch display is the number of cocktails it can prepare for guests at your party. The device includes 12 thematic variations - "non-alcoholic party", "sports bar", "Irish pub" and others, each of which contains about 25 recipes for various drinks.
The implementation of the robotic bartender project was made possible thanks to the Kickstarter crowdfunding platform, on which the startup Monsieur collected donations totaling $ 140,000.
JIBO startup: if you are lonely and have no one to talk to
The JIBO robot, which was liked by visitors to the Indiegogo site, which brought the creators of the device over $ 2 million, will become a personal compassionate interlocutor, polite, submissive and encouraging listener, regardless of your current emotional state.
The so-called social behavior model characteristic of JIBO, combined with advanced hardware and software components, will allow the device to find an individual approach when communicating with each family member. The device is able to independently identify the interlocutor, as well as to catch his mood in order to choose the most appropriate behavior algorithm in the current situation.
JIBO, having wireless Internet access, will find recipes for various dishes for the upcoming dinner by voice request, inform about a new letter by e-mail, help with purchases, and also joke appropriately, entertain with a funny story and brighten up a gloomy evening with a good musical composition.
Almost anyone can get an unusual robotic friend, because the price of JIBO is only $ 500.
Robots on guard
An excellent way to use robotic devices has become their security functions. Indeed, thermal imagers, motion sensors, a laser rangefinder, all kinds of cameras and "smart" systems, in theory, are capable of detecting an intruder much earlier, suspect something was wrong and report a threat or already entered a protected area than even an experienced person would.
And if the brainchild of specialists from Knightscope is intended for passive observation and sending an alarm signal to the control room, then, for example, the PatrolBot Mark II security robot is ready to independently counteract the intruder. For this, a 100 dB horn and a water pistol are installed on its wheeled platform, with the help of which the operator can stain the reputation and clothes of the offender in the literal sense of the word.
It's much easier to be human than to create a human. Take, for example, playing ball as a child with a friend. If we decompose this activity into separate biological functions, the game will cease to be simple. You need sensors, transmitters and effectors. You need to calculate how hard to hit the ball so that it closes the distance between you and your companion. You need to consider sun glare, wind speed, and anything else that might distract. You need to determine how the ball rotates and how you need to receive it. And there is still room for outside scenarios: what if the ball flies overhead? Fly over the fence? Will knock out a neighbor's window?
These questions highlight some of the most pressing issues in robotics, and also lay the foundation for our countdown. Here is a list of the ten most difficult things to teach robots. We must beat this top ten if we ever want to fulfill the promises made by Bradbury, Dick, Asimov, Clark and other science fiction writers who have seen imaginary worlds where machines behave like humans.
Lead the way
Moving from point A to point B seemed simple to us since childhood. We humans do this every day, every hour. For a robot, however, navigation - especially through a unified environment that is constantly changing, or through an environment that it has never seen before - is the hardest thing. First, the robot must be able to perceive the environment and also understand all the input data.
Robotics solve the first problem by equipping their machines with an array of sensors, scanners, cameras, and other high-tech tools that help robots assess their surroundings. Laser scanners are becoming more and more popular, although they cannot be used in aquatic environments due to the severe distortion of light in water. Sonar technology appears to be a viable alternative for underwater robots, but is far less accurate on the ground. In addition, a computer vision system, consisting of a set of integrated stereoscopic cameras, helps the robot "see" its landscape.
Collecting environmental data is only half the battle. A much more difficult task will be to process this data and use it to make decisions. Many developers control their robots using a predefined map or making one on the fly. In robotics, this is known as SLAM, a method of simultaneous navigation and mapping. Mapping here means how a robot transforms the information received by the sensors into a specific form. Navigation means how the robot positions itself relative to the map. In practice, these two processes have to proceed simultaneously, in the form of "chicken and egg", which is feasible only with the use of powerful computers and advanced algorithms that calculate position based on probabilities.
Demonstrate agility
Robots have been assembling packages and parts in factories and warehouses for many years. But in such situations they, as a rule, do not meet with people and almost always work with objects of the same shape in a relatively free environment. The life of such a robot in a factory is boring and ordinary. If a robot wants to work at home or in a hospital, for this it will need to have an advanced sense of touch, the ability to detect people nearby and impeccable taste in terms of choice of actions.
These skills are extremely difficult to teach a robot. Scientists usually do not teach robots to touch at all, programming them to fail if they come into contact with another object. However, over the past five years or so, there have been significant advances in combining malleable robots and artificial leather. Compliance refers to the level of flexibility of a robot. Flexible machines are more malleable, rigid ones less.
In 2013, researchers at Georgia Tech created a robotic arm with spring-loaded joints that allow the arm to bend and interact with objects like a human hand. Then they covered it all with "skin" that could sense pressure or touch. Some types of robot skin contain hexagonal microcircuits, each of which is equipped with an infrared sensor that detects any approach closer than a centimeter. Others are equipped with electronic “fingerprints” - a ribbed and rough surface that improves grip and facilitates signal processing.
Combine these high-tech manipulators with an advanced vision system and you have a robot that can give a gentle massage or sort through a folder with documents, choosing the one you want from a huge collection.
Keep the conversation going
Alan Turing, one of the founders of computer science, made a bold prediction in 1950: one day, machines will be able to speak so freely that you cannot tell them apart from humans. Alas, so far robots (and even Siri) have fallen short of Turing's expectations. This is because speech recognition is vastly different from natural language processing - what our brains do to extract meaning from words and sentences in conversation.
Scientists originally thought it would be as easy to replicate as to plug the rules of grammar into the memory of a machine. But the attempt to program grammar examples for each individual language simply failed. It turned out to be very difficult even to determine the meanings of individual words (after all, there is such a phenomenon as homonyms - a key for a door and a treble clef, for example). People learned to define the meanings of these words in context, relying on their mental abilities, developed over many years of evolution, but it was simply impossible to break them down again into strict rules that can be put on the code.
As a result, many robots today process the language based on statistics. Scientists feed them huge texts known as corpuses and then allow computers to break long texts into chunks to figure out which words often go together and in what order. This allows the robot to "learn" the language based on statistical analysis.
Learn new
Imagine that someone who has never played golf decides to learn how to swing a golf club. He can read a book about it and then try, or watch a famous golfer practice and then try on his own. In any case, it will be easy and quick to master the basics.
Robotics face certain challenges when trying to build an autonomous machine that can learn new skills. One approach, as with golf, is to break down the activity into precise steps and then program them into the robot's brain. This suggests that every aspect of the activity needs to be separated, described and coded, which is not always easy to do. There are certain aspects of golf club swinging that are difficult to describe in words. For example, the interaction of the wrist and elbow. These subtle details are easier to show than describe.
In recent years, scientists have had some success in teaching robots to mimic a human operator. They call it imitation learning, or demonstration learning (LfD technique). How do they do it? Arming machines with arrays of wide-angle and zoom cameras. This equipment allows the robot to "see" the teacher performing certain active processes. The learning algorithms process this data to create a mathematical function map that integrates visual input and desired actions. Of course, LfD robots have to be able to ignore certain aspects of their teacher's behavior - like itching or runny nose - and deal with similar problems that arise from the difference in robot and human anatomy.
Deceive
The curious art of deception was developed even in animals in order to bypass competitors and not be eaten by predators. In practice, deception as an art of survival can be a very, very effective mechanism for self-preservation.
For robots, learning to fool humans or other robots can be incredibly difficult (and possibly good for you and me). Deception requires imagination - the ability to form ideas or images of external objects unrelated to feelings - and machines usually do not. They are great at directly processing data from sensors, cameras and scanners, but they cannot form concepts that transcend sensory data.
On the other hand, the robots of the future may be better at dealing with deception. Scientists at Georgia Tech were able to transfer some of the skills of deceiving squirrels to robots in the lab. They first studied cunning rodents that protect their food caches by luring competitors into old and unused storage facilities. Then they coded this behavior into simple rules and loaded it into the brains of their robots. Machines were able to use these algorithms to determine when cheating might be beneficial in a given situation. Consequently, they could deceive their companion by luring him to another place in which there is nothing of value.
Anticipate human actions
In the Jetsons, Rosie the robot maid was able to hold conversation, cook, clean and help George, Jane, Judy, and Elroy. To understand Rosie's build quality, just remember one of the initial episodes: Mr. Spaceley, George's boss, comes to the Jetson house for dinner. After the meal, he takes out a cigar and places it in his mouth, while Rosie lunges forward with a lighter. This simple action represents complex human behavior - the ability to anticipate what will happen next based on what has just happened.
Like deception, anticipating human actions requires the robot to imagine a future state. He should be able to say, "If I see a person doing A, then, as I can guess from past experience, he will most likely do B." In robotics, this point was extremely difficult, but people are making some progress. A team at Cornell University developed an autonomous robot that could respond based on how the companion interacted with objects in the environment. To do this, he uses a pair of 3D cameras to capture an image of the surroundings. The algorithm then identifies the key objects in the room and makes them stand out from the rest. Then, using a huge amount of information obtained as a result of previous trainings, the robot develops a set of specific expectations of movements from the person and the objects that it touches. The robot draws conclusions about what will happen next and acts accordingly.
Sometimes Cornell robots are wrong, but they are moving forward quite confidently, including as camera technology improves.
Coordinate activities with other robots
Building a single large-scale machine - even an android, if you will - requires a significant investment of time, energy and money. Another approach involves deploying an army of simpler robots that can act together to achieve complex missions.
A number of problems arise. A robot working in a team must be able to position itself well in relation to its peers and be able to communicate effectively - with other machines and a human operator. To solve these problems, scientists turned to the world of insects, which use complex swarming behaviors to find food and solve problems that benefit the entire colony. For example, by studying ants, scientists realized that individuals use pheromones to communicate with each other.
Robots can use this same "pheromone logic", only rely on light, not chemicals, to communicate. It works like this: a group of tiny robots are dispersed in a confined space. They first explore this area randomly until one comes across a light trail left by another bot. He knows to follow the trail, and he goes, leaving his own trail. As the tracks merge into one, more and more robots follow each other in single file.
Self-copy
The Lord told Adam and Eve: "Be fruitful and multiply, and replenish the earth." A robot that received such a command would feel embarrassed or disappointed. Why? Because he is unable to reproduce. It is one thing to build a robot, but it is quite another to create a robot that can make copies of itself or regenerate lost or damaged components.
Remarkably, robots may not take humans as an example of a reproductive model. You may have noticed that we are not divided into two identical parts. The simplest, however, do this all the time. Relatives of jellyfish - hydras - practice a form of asexual reproduction known as budding: a small ball detaches from the parent's body and then breaks off to become a new, genetically identical individual.
Scientists are working on robots that can perform the same simple cloning procedure. Many of these robots are built from repeating elements, usually cubes, which are made in the image and likeness of a single cube, and also contain a self-replication program. Cubes have magnets on the surface, so they can attach and detach from other cubes nearby. Each cube is divided diagonally in two, so each half can exist independently. The whole robot contains several cubes, assembled into a certain figure.
Act from principle
When we interact with people every day, we make hundreds of decisions. In each of them, we weigh our every choice, determining what is good and what is bad, honest and dishonest. If robots wanted to be like us, they would need to understand ethics.
But, as with language, it is extremely difficult to code ethical behavior, mainly because there is no single set of generally accepted ethical principles. Different countries have different rules of conduct and different systems of law. Even in individual cultures, regional differences can affect how people evaluate and measure their own actions and those of others. An attempt to write a global ethics suitable for all robots turns out to be almost impossible.
This is why scientists decided to create robots while limiting the scope of the ethical problem. For example, if a machine is to operate in a specific environment - in the kitchen, say, or in a patient's room - it will have far fewer rules of conduct and fewer laws to make ethically sound decisions. To achieve this goal, robotics engineers introduce ethical choices into the machine's learning algorithm. This choice is based on three flexible criteria: what good will the action lead to, what harm it will do, and the measure of justice. Using this type of artificial intelligence, your future home robot will be able to determine exactly who should wash the dishes in the family and who will get the TV remote control at night.
Feel emotions
“This is my secret, it is very simple: only the heart is sharp-sighted. You cannot see the most important thing with your eyes. "
If this remark of the Fox from "The Little Prince" by Antoine de Saint-Exupery is correct, then robots will not see the most beautiful and best in this world. After all, they are great at probing the world around them, but they cannot turn sensory data into specific emotions. They cannot see the smile of a loved one and feel joy, or they cannot fix the angry grimace of a stranger and tremble with fear.
This, more than anything else on this list, is what separates man from machine. How to teach a robot to fall in love? How to program frustration, disgust, surprise, or pity? Should I even try?
Some people think it's worth it. They believe that the robots of the future will combine cognitive and emotional systems, which means they will work better, learn faster and interact more effectively with people. Believe it or not, prototypes of such robots already exist, and they can express a limited range of human emotions. Nao, a robot developed by European scientists, has the emotional qualities of a one-year-old. He can express happiness, anger, fear and pride by accompanying emotions with gestures. And this is just the beginning.
Dec 24, 2017 Gennady
Source: nauka.boltai.com
