10 problems of robotics for the next 10 years

Date:

2018-02-13 13:00:04

Views:

46

Rating:

1Like 0Dislike

Share:

10 problems of robotics for the next 10 years

Robotics has made tremendous strides in recent years, but cars is still a lot of obstacles in front to tightly come into our lives. The journal Science Robotics identified ten Grand challenges that need to be addressed to make this a reality. The editors of the journal conducted an online poll on unsolved problems in robotics and interviewed a group of industry experts.

the

New materials and Assembly drawings

The Robotics start to move away from the traditional motors, gears and sensors, experimenting with elements such as artificial muscles, soft robotics and new methods of assemblies that combine multiple functions in one material. But most of the list of these achievements not yet passed the stage of demonstration, and the merger is too early to tell.

Multifunctional materials combine sensitivity, movement, energy harvesting or storage and allow you to design more effective robots. But the combination of these features in one machine will require new approaches combining micro - and macro-scale Assembly technique. Another promising area of steel materials, which can change over time, adapting or recovering, but this area requires much more research.

the

Viewdocsonline and biohybrid robots

Nature had already solved many of the problems that puzzled robotics, so many of them turned to biology in search of inspiration, or even include living systems in their robot. However, the reproduction of the mechanical performance of muscle and the ability of biological systems to independently feed herself faced with "narrow" places in development.

The Area of artificial muscles have seen significant progress, but their strength, efficiency, energy density and power require improvement. The introduction of living cells into robots to overcome the difficulties associated with the use of small robots and to use biological features such as self healing and built-in perception, but the introduction of such components is a complex task. Although the growing "roboscope" helps us to explore the secrets of nature, it is necessary to conduct more work on how animals made the transition from a pure flight and navigation multimodal platforms.

the

Power and energy

Energy Storage — a major stumbling block for mobile robotics. The growing demand for drones, electric cars and renewable energy is pushing progress in the field of batteries, but the fundamental problems remain largely unchanged for many years.

From this it follows that in parallel with the development of batteries is the need to minimize energy consumption of the robots and outfitting them with new sources of energy. To give robots the ability to use the energy of their environment and transfer energy to them wirelessly — these two promising approach is being actively studied.

the

a swarm of robots

A swarm of simple robots which are available in various configurations to solve a variety of problems, can be a cheap and flexible alternative to the large, specialized robots. Small, inexpensive and powerful items of equipment that enable simple robots to sense their environment and communicate, combined with AI that can simulate this kind of behavior already exist in natural swarms.

You Need to spend more work on effective forms of governance at different scales — small swarms can be controlled centrally, but larger should be more centralized. They must also be durable and adaptable to changing real-world conditions and is resistant to intentional or accidental damage. You also need to work more on swarms of heterogeneous robots with additional capabilities.

the

Navigation and exploration

The Key usage of robots is the study of places can't get people, for example, in deep sea, space or disaster area. This means that they need to be skillful in the exploration and navigation without maps, often in a chaotic and hostile environment.

The Main problems include the creation of systems that can adapt, learn and recover from faults in navigation, and the ability to create and recognize new discoveries. This will require a high level of autonomy, which will allow the robots to monitor and reconfigure themselves to create the picture of the world from multiple data sources of different reliability and accuracy.

the

AI for robots

Deep learning has given the machines the ability to recognize patterns and schemas on a new level, but it needs to be linked with a simulated reasoning for the creation of adaptable robots that can learn on the fly.

The Key to this will be to create AI that is aware of its own limitations and is able to learn learning new things. It is also important to create systems that can learn quickly based on limited data, and not on millions of examples used in deep learning. Further advances in our understanding of human intelligence will also be necessary to address these problems.

the

brain-computer interfaces

Brain-computer interfaces will transparently manage the developed robotic prostheses and will provide faster and more natural way to pass instructions to the robots or just help them understand the mental state of the person.

Most modern approaches to the measurement of brain activity are expensive and clumsy, so we need to design compact, ergonomic and wireless device. They should include extensive training, calibration and adaptation for the reason that we are unable to accurately read the brain activity. In addition, it remains to be seen whether they work better than simple techniques like eye-tracking or reading muscle signals.

the

Social interactions

If the robots want to enter the human environment, they will need to learn how to communicate with people. It's hard because we don't have many clearly defined patterns of conduct of men and we tend to underestimate the complexity of what seems to us natural.

Social robots will have to be able to perceive the smallest social signals such as facial expression or intonation, to understand the cultural and social context in which they operate, and to model the mental state of the people with whom you interact and adapt their relationship in the short term engineering and long term relationships.

the

Medical robots

Medicine — one of the areas in which robots can have a significant impact in the near future. Devices that complement the capabilities of the surgeon, already used on a daily basis, but to give them complete autonomy we can not because of high interest rates and risks.

Autonomous assistants in the face of robots will need to learn to recognize human anatomy in a variety of contexts and to use situational awareness and your voice to understanding what is required of them. Surgery Autonomous robots can perform a normal operation, freeing the surgeon for a more subtle and important work.

The Microbots working in the human body, too, promise much, but are in an embryonic stage of its development.

the

Ethics and security robots

As overcome current problems and the integration of robots into our lives, we face new ethical challenges. Most importantly, we can become overly dependent on robots.

It can cause people get rid of certain skills and abilities and not be able to take the reins in the event of failure of the robotic system. We can ultimately delegate tasks, which for ethical reasons is unpleasant for people, and blame it on a standalone system.

...

Tags:

Comments (0)

This article has no comment, be the first!

Add comment

Related News

#video of the day | SpotMini Robot company Boston Dynamics has learned new tricks

#video of the day | SpotMini Robot company Boston Dynamics has learned new tricks

to Observe how rapidly evolutionary robots production company Boston Dynamics — a very exciting experience.

China has developed an exoskeleton for the military

China has developed an exoskeleton for the military

Chinese State Corporation Norinco produces not only military equipment and ammunition.

The US military will teach the AI new skills

The US military will teach the AI new skills "movies on rewind»

Experts of the AI lab of the US army and developers of the University of Texas artificial intelligence Deep TAMER, who will be able to quickly learn new skills by watching videos in an accelerated mode.