Robotic development

From The Conversation Quote:

The uptake of robotics technology is increasing at a startling rate.

Most of these robots will perform repetitive tasks that require little or no intelligence, but a huge range of useful jobs need robots that can adapt and learn on their own. That’s why we’re using Darwinian evolution as the basis of our robot design process.

Robots are often used in what we might call a “structured” environment – somewhere that conditions are predictable and controllable, with no hidden surprises.

But robots struggle when we take them outside. Australia is a prime location for deploying robots outdoors, whether performing long term biodiversity studies in rain forests or providing vital information to first responders following a natural disaster. Robots would be incredibly helpful in these “unstructured” environments, which are unpredictable and uncontrollable.

Instead of a population of birds or plants, what if we used Darwin’s principles to evolve a population of robots that automatically improve their performance in an environment?

We can do this either by creating a computer simulation of the robots – which saves time and money – or by creating them in real life.

Let’s say we want our robots to count wombats in a certain region. We define an equation called a fitness function. Fitness is a score that tells us how well the robot is performing – for instance, how many wombats it counts per hour. The robots attempt the task, which gives us a fitness score for each robot. Some robots will be fitter than others, and the fittest robots are more likely to be picked as “parents”.

Our parents create children. Crossover combines genes from both parents into a new “child” genome. Mutation slightly changes some of these genes as they pass from parent to child. We can make the children and get a fitness score for each, as before. Because the genomes of the children are similar to the genomes of fit parents, they are likely to be good at the task.

We perform this loop many times, incrementally optimising the population of robots to be suited to their task and environment. End quote.

I would like to say that, while this is an exciting time to be developing robots, the science behind this is not entirely Darwinian. Darwin just assumed that all animals were built a certain way, and did not really consider mutations. However, it was adaptive mutations that stayed in the gene pool, which allowed the developmental changes in animals over time.

Have you seen this video of a robot doing a backflip? What is truly amazing is that the robot was not specifically programmed to do that. It would be more accurate to say that it was programmed to self-mutate, as part of the evolution of its ‘neural’ network.

I did hear a story (sorry, I can’t find a reference) of a robot with a neural network designed to minimise the power requirements of a large computer system. It did its job really well. It shut the whole system down.

So thinking about that… what would happen if we came up with a neural network designed to minimise the human environmental footprint? How do you think it would achieve that?


Do you want:

  • Ad-free access?
  • Access to our very popular daily crossword?
  • Access to daily sudoku?
  • Access to Incite Politics magazine articles?
  • Access to podcasts?
  • Access to political polls?

Our subscribers’ financial support is the reason why we have been able to offer our latest service; Audio blogs. 

Click Here  to support us and watch the number of services grow.

Accountant. Boring. Loves tax. Needs to get out more. Loves the environment, but hates the Greens. Has been called a dinosaur. Wears it with pride.

To read my previous articles click on my name in blue.

Listen to this post:
Voiced by Amazon Polly
64%