{"id":609,"date":"2018-12-19T09:52:59","date_gmt":"2018-12-19T09:52:59","guid":{"rendered":"http:\/\/horizon.peachpuff-wolverine-566518.hostingersite.com\/?p=609"},"modified":"2018-12-19T09:52:59","modified_gmt":"2018-12-19T09:52:59","slug":"robots-are-being-programmed-to-adapt-in-real-time","status":"publish","type":"post","link":"https:\/\/scienceblog.com\/horizon\/609\/robots-are-being-programmed-to-adapt-in-real-time\/","title":{"rendered":"Robots are being programmed to adapt in real time"},"content":{"rendered":"

By Gareth Willmer<\/em><\/p>\n

A robust, adaptable robot that responds to its environment on the fly and overcomes obstacles such as a broken leg without human intervention could be used to rescue people from an earthquake zone or clean up sites that are too hazardous for humans.<\/strong><\/h3>\n
\n
\n
\n

It\u2019s part of a field of work that is building machines that can provide real-time help using only limited data as input. Standard machine-learning algorithms often need to process thousands of possibilities before deciding on a solution, which may be impractical in pressurised scenarios where fast adaptation is critical.<\/p>\n

After Japan\u2019s Fukushima nuclear disaster in 2011, for example, robots were sent into the power plant to clear up radioactive debris in conditions far too dangerous for humans. The problem, says robotics researcher Professor Jean-Baptiste Mouret is that the robots kept breaking down or came across hazards that stopped them in their tracks.<\/p>\n

As part of the\u00a0ResiBots\u00a0<\/a>initiative, he is designing a lower-cost robot that can last long periods without needing constant human maintenance for breakages and are better at overcoming unexpected obstacles.<\/p>\n

The ResiBots team is using what it refers to as micro-data learning algorithms, which can help robots adapt in front of one\u2019s eyes in a similar way to how animals react to problems. An animal will, for example, often find a way to continue moving if they get injured, even if they don\u2019t know exactly what the problem is.<\/p>\n

In contrast, most current robots self-diagnose a problem before working out a way to overcome it, says Prof. Mouret, principal investigator at ResiBots and a senior researcher at the Inria research centre in France.<\/p>\n

\u2018We\u2019re trying to shortcut this by finding a way for them to react without necessarily having developed an understanding of what\u2019s wrong,\u2019 he said.<\/p>\n

Rather than self-diagnosing, the aim for these robots is to learn in a proactive way by trial and error what alternative actions they can take. This could help them overcome difficulties and stop them from shutting down in situations such as disaster scenarios like Fukushima, said Prof. Mouret.<\/p>\n

This may not be full artificial intelligence, but Prof. Mouret points out that having knowledge of everything is not essential for getting a robot to work.<\/p>\n

\u2018We\u2019re not trying to solve everything,\u2019 he said. \u2018I\u2019m more interested in how they can adapt \u2013\u00a0and, in fact, adapting to what\u2019s happening is some of what makes animals intelligent.\u2019<\/p>\n

Simulated childhood<\/strong><\/p>\n

In one of the most promising approaches developed in the ResiBots project, the robots have a simulated childhood, in which they learn different ways to move their body using an algorithm that searches ahead of time to collect examples of useful behaviours.<\/p>\n

This means that when seeking a way to move, the robots need to choose from one of about 13,000 behaviours rather than an estimated 1047<\/sup>\u00a0options that standard algorithms could select from. And the aim is for them to try only a handful of these before finding one that works.<\/p>\n

Most of ResiBot\u2019s tests are currently being carried out on a six-legged robot that seeks to find new ways to move after having one or more legs removed. In the latest trials, Prof. Mouret said the robots learned to walk in one to two minutes after one of their legs was taken off, meaning they generally need to test fewer than 10 behaviours before finding one that works.<\/p>\n