A WORLD FULL OF ROBOTS (machine learning)

Not all robots are the same. The ones we are most familiar with are robots used in manufacturing. However, there are many other robots used in different industries which are helping us humans in our daily lives. Before we go further, let’s define what a robot is. According to the Carnegie Mellon CS Department website, a robot is a ‘Force through intelligence’ or ‘Where A.I. meets the real world’.

Daniel Faggella, Founder & CEO at Emerj writes in his May 2019 article that some researchers might even argue against a set definition for robot, or debate where a definition can be relative or dependent upon the context of a situation. There is also a debate if for example autonomous vehicles, drones, and other similar machines are robots. Daniel Faggella further outlines that like many innovative technological fields, robotics has and is being influence, and in some directions steered by machine learning technologies.

The term ‘machine learning’ is what creates fear in us as we imagine humanoid robots taking over the world. To your surprise, only a portion of recent developments in robotics can be credited to the uses of machine learning. Daniel Faggella points out that most robots are not, and will likely not, be humanoids 10 years from now as robots are designed for a range of behaviours in a plethora of environments, their bodies and physical abilities will reflect a best fit for those characteristics.

An exception will likely be robots that provide medical or other care or companionship for humans, and perhaps service robots that are meant to establish a more personal and ‘humanised’ relationship. Personally, I do not believe that any robot will ever be able to provide a superior humanised relationship than a human itself. On the other hand, sci-fi movies already giving us an insight how humanoid robots work next to humans in defeating evil.

Daniel Faggella provided us an overview of machine learning application in robotics where machine learning has had a significant impact on robotic technologies in the present and future uses. Lets have a look at Daniel Faggella’s 5 technologies:

Machine vision or Robot vision, which involves more than just computer algorithms, engineers and robotics also must account for camera hardware that allow robots to process physical date. Robot vision is very closely linked to machine vision, which can be given credit for the emergence of robot guidance and automatic inspection systems. Extrasensory technologies like radar, lidar, and ultrasound, are also driving the development of 360-degree vision-based systems for autonomous vehicles and drones.

Imitation Learning, which is closely related to observational learning. Then there is also imitation learning which is an integral part of field robotics used in construction, agriculture, search and rescue, military, and others.

Then there is self-supervised learning which enables robots to generate their own training examples in order to improve their performance. Those robots can detect and rejects objects, identify vegetables and obstacles in rough terrain, and in 3D scene analysis and modelling vehicles dynamics.

Assistive and medical technologies are assistive robots that can sense, process sensory information, and perform actions that benefits people with disabilities and seniors, but also help the general population for example with driver assistance tools. In the medical world, advances in machine learning methodologies applied to robotics are fast advancing, even through not in reality available in many medical facilities.

Multi-agent learning, which key components are coordination and negotiation are mainly used in the gaming world as they can adapt to a shifting landscape of other robots/agents and find equilibrium strategies. Daniel Faggella provides the following research example: Robots collaborated to build a better and more inclusive learning model than could be done with one robot (smaller chunks of information processed and then combined), based on the concept of exploring a building and its room layouts and autonomously building a knowledge base.

Each robot built its own catalog, and combined with other robots’ data sets, the distributed algorithm outperformed the standard algorithm in creating this knowledge base. While not a perfect system, this type of machine learning approach allows robots to compare catalogs or data sets, reinforce mutual observations and correct omissions or over-generalizations, and will undoubtedly play a near-future role in several robotic applications, including multiple autonomous land and airborne vehicles.

In summary, the world is full of robots utilising machine learning to provide us with the assistance we require. For more information on this subject please contact Founder & CEO Daniel Faggella at Emerj,

I hope you enjoyed this article and if you’d like to learn more about this topic, just give us a call.

Synergy Consulting Australia provides a large range of business consulting services which includes 4IR, Legal, Accounting, Marketing, Project Management, Migration services and many more tailored business solutions. This also includes full market research and feasibility report before investing.

Synergy Consulting Australia is led by Ilona Solinska. Ilona has over 19 years of international business consulting experience.  She is a successful Business Growth Strategist, Educator, Keynote speaker, and Writer. Ilona has coached hundreds of businesses in the area of Marketing, Finance, Legal, Compliance, Operation, Change & Project Management and is a highly sought-after presenter on a wide variety of business topics.