Key Technologies Defining Robotics – The Future of Robotics

21-01-2021 | By Mark Patrick

What will the series cover?

In this series of six blogs, we take a look at the key technologies defining the way robots are being designed and used today, and how that may evolve in the future. It will cover developments at the hardware and software level, and how innovations such as AI are already shaping the future of robotics.

Blog 1: Key Technologies Defining Robotics – From Static Arms to AMRs

Blog 2: Key Technologies Defining Robotics – Mobility and Dexterity

Blog 3: Key Technologies Defining Robotics – Positioning and Navigation 

Blog 4: Key Technologies Defining Robotics – Robot Operating Systems

Blog 5: Key Technologies Defining Robotics – CoBots and AI

Blog 6: The Future of Robotics

The Future of Robotics 

People are beginning to fully appreciate the useful impact robots are having on our lives. Analysts and expert observers are also optimistic about robots, and we can all expect them to become even more integrated into our world. 

One sought-after vision is the house robot taking on chores for homeowners. We are now seeing the start of this trend, with robot vacuum cleaners and lawnmowers that work tirelessly in the background. We should also consider the way established white goods are becoming more intelligent as part of this trend. 

Dishwashers that choose the most suitable program, or refrigerators that remind us when we’re running low on milk are examples. Is it too much to expect these devices to ‘grow’ arms and position the dirty dishes more optimally, or to hand us the milk when we’re making a cup of tea? If we let our imagination roam a little, it becomes easy to expect these things to happen. Though the question remains whether any of us really want that level of assistance.

Robots in Automation – The Next Level

In the near term, the application of robotics in the industrial sector will result in further increases in automation. That shouldn’t be too surprising, given that letters from ‘Universal Automation’ formed the name of the first-ever industrial robot - Unimate (see blog 1 in this series for more on that topic). 

Even back in the 1950s, visionaries could probably predict that one day, things like forklift trucks would be capable of operating entirely autonomously. It is perhaps worth noting that the forklift truck had already been around for about 40 years when robots first saw service. 

The Autonomous Mobile Robot, or AMR, is about to mark the start of a new generation of industrial robots, so what else can we expect? 

Convergence could be the key here. Right now, AI is used in digital assistants to provide us with home automation by controlling light switches and sockets. They are getting better at understanding what we’re asking for, although their responses are still quite limited. 

Similarly, AMRs are now able to move autonomously, but they are probably still only going to be using AI to navigate unfamiliar surroundings initially. What we need to see is AMRs using AI to do jobs for which they have yet to train. When that happens, we can expect to see a significant impact on productivity. 

Robots Will Infer How to do New Tasks

The kind of tasks an AI-enabled AMR will be able to take on will still be quite limited, at least initially. We can’t expect a robot to do very complex tasks without any training, but we could expect them to infer how to do simple tasks based on what they have learnt to do before. 

In an industrial environment, this could be something as seemingly mundane as stacking square items instead of cylinders. To a human operator, moving from round to square would present little challenge, but for a robot, it is an entirely new task that it must learn. 

However, an AI-enabled robot could apply its existing knowledge in a new way. It would be less challenging for this robot to work out a new way of doing something it is already familiar with. This ability to keep learning new skills will define the next level of robot automation. 

Are we ready for the humanoid robot?

There are numerous challenges to overcome if we want to arrive at the ‘classic’ robot that looks, moves and thinks like a human. Each of those three activities needs mastering. We are well on the way to completing the first two, but the third is still probably some years away. 

For example, consider current the research that is going into making robotic pets. They look and mostly move like the real thing, but we can’t say they think like a dog or a cat. If we can’t convincingly mimic something as comparatively simple as a dog or cat using today’s AI, it is apparent that making a robot that thinks like a human is probably not within our grasp just yet.

But the humanoid robot has many advantages. It would be much simpler to integrate robots into a world designed for humans if they look and move just like humans. The expectation here might be that the robot is faster, stronger and smarter than a human. Realistically, even a robot that is slower, weaker and less intelligent than the average person would still be hugely useful. After all, we don’t rely on super-strength to open doors, or super-intelligence to cross the road. 

When AMRs and CoBots reach this level of sophistication, we can start to enjoy the benefits of robotics on a broader scale.  

Mouser’s online resources offer a wealth of deeper learning on the topic of robotics. 

Read More

Key Technologies Defining Robotics – From Static Arms to AMRs

Key Technologies Defining Robotics – Mobility and Dexterity

Key Technologies Defining Robotics – Positioning and Navigation

Key Technologies Defining Robotics – Robot Operating Systems

Key Technologies Defining Robotics – CoBots and AI

Key Technologies Defining Robotics – The Future of Robotics


Mouser Electronics

Authorised Distributor

www.mouser.com

Follow us on Twitter

Mark-Patrick.jpg

By Mark Patrick

Mark joined Mouser Electronics in July 2014 having previously held senior marketing roles at RS Components. Prior to RS, Mark worked at Texas Instruments in applications support and technical sales roles. He holds a first class Honours Degree in Electronic Engineering from Coventry University.