{"id":117272,"date":"2024-07-10T15:44:06","date_gmt":"2024-07-10T13:44:06","guid":{"rendered":"https:\/\/prohoster.info\/blog\/novosti-interneta\/roboekskavator-obuchili-priczelno-shvyryat-kamni"},"modified":"2024-07-10T15:44:06","modified_gmt":"2024-07-10T13:44:06","slug":"roboekskavator-obuchili-priczelno-shvyryat-kamni","status":"publish","type":"post","link":"https:\/\/prohoster.info\/en\/blog\/news\/roboekskavator-obuchili-priczelno-shvyryat-kamni","title":{"rendered":"The robotic excavator has been trained to precisely throw stones.","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"

Experienced excavator operators are familiar with a trick that allows them to throw the bucket's contents beyond the reach of the arm. The neural network-equipped robotic excavator proved to be a diligent learner, capable of mastering<\/a><\/noindex> the precise throwing of stones further than the reach of the arm. Next up is throwing bulk materials and improving accuracy for working with the bucket at different heights.<\/p>\n

<\/center> \t\t\t\t
<\/center> \"The <\/p>\n

Researchers from Switzerland (ETH Z\u00fcrich) reported on the training process of the neural network of a robotic excavator for precise manipulation of the bucket's contents. The reinforcement learning-based neural network was trained to throw balls and stones to a designated point that was beyond the reach of the arm (up to 9.5 meters with a 7.5-meter reach). Such operations will help robotics tackle a wider range of tasks with lower energy costs for movements and will also make its work safer.<\/p>\n

The excavator performed grabs and throws with a bucket that had two degrees of freedom and was not rigidly fixed to the arm. Throws were made both in a straight line, when only the arm was in operation, and with the rotation of the cabin. In the latter case, accuracy was slightly reduced, but in any case, the projectile deviated from the aiming point by no more than 30\u201340 cm. <\/p>\n

<\/center>
\r\n \"Play\r\n
<\/div>\r\n <\/div><\/center> <\/p>\n

Researchers trained the neural network on a modified 12-wheeled Menzi Muck M545 excavator. Previously, they had trained the excavator to perform a number of non-trivial operations, such as teaching it to build a stable wall from unprepared stone blocks. The excavator assessed the balance of the stones itself and constructed a sturdy stone enclosure. For precise autonomous operations on the terrain, the excavator builds a model of the surrounding space using sensors installed on it, in which it performs the assigned tasks.<\/p>\n

Source:<\/strong><\/p>\n