For most of us, weekends, most especially Sundays, are spent tidying up and cleaning the house, trying to prepare for another busy week ahead. Imagine having a robot at home that could help you with all these tedious chores. This might not be so far out since according to a report by BBC, a start-up company in Japan is trying to teach a pair of machines exactly just this. It seems to be proving a bit difficult 'coz what seems like a simple job for us humans, is a surprisingly tricky task for a robot - specifically, cleaning a bedroom.
In a basement in Tokyo, researchers from Preferred Networks, a Japanese tech start-up, have been applying a species of artificial intelligence to teach robots how to deal with disordered objects - they are teaching the AI how to deal with disorder and chaos in a child's room.
Deep learning is where algorithms, inspired by the human brain, learn from large amounts of data so they're able to perform complex tasks. Some tasks, like welding car chassis in the exact same way day after day, are easy for robots as it is a repetitive process. If presented with a messy, disordered world, without Deep learning, they become perplexed and are unable to achieve their goal as their regular algorithms fail. They are using the same Artificial Intelligence used in self-driving cars and smart factories to teach them about chaos.
With the algorithms, the machines are able to identify every object, strewn in random places all over the room and they were able to figure out how to pick them up, and then finally, place them in the appropriate bins or boxes.
At this point though, the company said that the robots work slowly and are easily defeated by things they don't know. For example, they failed to recognize a sock, which was larger and more colorful than the socks it had encountered before. Nonetheless, the company's founder and chief executive, Toru Nishikawa, hopes to start selling these tidy-up robots 'within five years'. Investors in the firm include Fanuc, the Japanese company whose robot arms work at tasks in many of the world's most advanced factories. They both plan to develop a futuristic factory of robots armed with AI-based self-learning capability. 'Technology is advancing significantly and it will become even more important to learn not only about software but also hardware,' said Mr. Nishikawa.