{"id":559173,"date":"2021-03-22T12:01:40","date_gmt":"2021-03-22T16:01:40","guid":{"rendered":"https:\/\/www.therobotreport.com\/?p=559173"},"modified":"2021-03-22T12:01:40","modified_gmt":"2021-03-22T16:01:40","slug":"deep-learning-sensor-placement-soft-robots","status":"publish","type":"post","link":"https:\/\/www.therobotreport.com\/deep-learning-sensor-placement-soft-robots\/","title":{"rendered":"Deep learning optimizes sensor placement for soft robots"},"content":{"rendered":"
\"deep

MIT built a deep learning neural network to aid the design of soft robots, such as these iterations of a robotic elephant. | Photo Credit: MIT<\/strong><\/p><\/div>\n

There are some tasks traditional robots<\/a> – the rigid and metallic kind – simply aren\u2019t cut out for. Soft-bodied robots, on the other hand, may be able to interact with people more safely or slip into tight spaces with ease. But for robots to reliably complete their programmed duties, they need to know the whereabouts of all their body parts. That\u2019s a tall task for a soft robot that can deform in a virtually infinite number of ways.<\/p>\n

MIT researchers developed an algorithm to help engineers design soft robots<\/a> that collect more useful information about their surroundings. The deep learning algorithm suggests an optimized placement of sensors within the robot\u2019s body, allowing it to better interact with its environment and complete assigned tasks. The advance is a step toward the automation of robot design.<\/p>\n

\u201cThe system not only learns a given task, but also how to best design the robot to solve that task,\u201d said Alexander Amini. \u201cSensor placement is a very difficult problem to solve. So, having this solution is extremely exciting.\u201d<\/p>\n

The research will be presented at the IEEE International Conference on Soft Robotics and will be published in the journal IEEE Robotics and Automation Letters<\/em>. Co-lead authors are Amini and Andrew Spielberg, both PhD students in MIT Computer Science and Artificial Intelligence Laboratory (CSAIL). Other co-authors include MIT PhD student Lillian Chin, and professors Wojciech Matusik and Daniela Rus.<\/p>\n

Related:<\/strong> Designing a quadruped controlled & powered by pneumatics<\/a><\/p>\n

Creating soft robots that complete real-world tasks has been a long-running challenge in robotics. Their rigid counterparts have a built-in advantage: a limited range of motion. Rigid robots\u2019 finite array of joints and limbs usually makes for manageable calculations by the algorithms that control mapping and motion planning. Soft robots are not so tractable.<\/p>\n

Soft robots are flexible and pliant \u2014 they generally feel more like a bouncy ball than a bowling ball. \u201cThe main problem with soft robots is that they are infinitely dimensional,\u201d said Spielberg. \u201cAny point on a soft-bodied robot can, in theory, deform in any way possible.\u201d That makes it tough to design a soft robot that can map the location of its body parts. Past efforts have used an external camera to chart the robot\u2019s position and feed that information back into the robot\u2019s control program. But the researchers wanted to create a soft robot untethered from external aid.<\/p>\n

\n