has learned to open doors using a new method that reduces the time and effort required to train it, but that efficiency may come at the cost of adaptability.
Robots are often controlled by a deep learning model that has been trained over thousands of trial-and-error attempts to complete the task. Instead, Hiroshi Ito at Waseda University, Tokyo, and his colleagues split the model into modules, with one controlling the robot as it approached the door, another taking over to open the door and one handling passing through the entrance. For each task, the robot had one module for doors that pull open and one for doors that push open.
The robot received 6 hours of training for each of the six modules and was shown how to perform the task by humans 108 times. This is less training overall than a single model would need because each module was trained on a smaller, simpler task. Ito says that a comparable problem by Google researchers took two months of training, using 14 robots in parallel.
After training, the robot accomplished its task 96 per cent of the time. In one test it went back and forth through the door for 30 minutes straight, completing 15 round trips.The robot runs all of its modules continuously. Each one suggests what it should do next, and an “operation selector” chooses the most appropriate action for the situation and switches from one module to another as appropriate.
“I believe that this would have improved the data efficiency of the method. What I’m still very sceptical about is the generalisability,” he says. “There is no such thing as a free lunch in machine learning.”
Nice 👌
Can ppl be trained into not hoarding money?
Cool. It can almost do what a toddler does.
Will it knock first?
maybe for once humans can learn from robots. stop stressing over big tasks and split it into smaller attainable ones. now you'll feel happy for every small task you complete :)
that’s rather useless. it ought to check there’s no-one behind it before letting the door slam, and hold the door open until they pass if they are close by.
Technology Technology Latest News, Technology Technology Headlines
Similar News:You can also read news stories similar to this one that we have collected from other news sources.
Source: sciam - 🏆 300. / 63 Read more »
Source: ForbesTech - 🏆 318. / 59 Read more »
Source: physorg_com - 🏆 388. / 55 Read more »
Source: ForbesTech - 🏆 318. / 59 Read more »
Source: DigitalTrends - 🏆 95. / 65 Read more »
Source: cleantechnica - 🏆 565. / 51 Read more »