{"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\/ro\/blog\/news\/roboekskavator-obuchili-priczelno-shvyryat-kamni","title":{"rendered":"Excavatorul robot a fost \u00eenv\u0103\u021bat s\u0103 arunce \u021binte precise cu pietre","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"

Excavator operators are familiar with a trick that allows them to send the bucket's contents beyond the reach of the boom. A robo-excavator equipped with a neural network has proven to be a diligent student who also managed to master<\/a><\/noindex> targeted stone throwing beyond the boom's reach. Next up is throwing bulk materials and improving precision for bucket work at different heights.<\/p>\n

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

Cercet\u0103torii de la ETH Z\u00fcrich din Elve\u021bia au anun\u021bat despre procesul de instruire al re\u021belei neuronale a excavatorului robotic pentru manipularea precis\u0103 a con\u021binutului cupei. Re\u021beaua neuronal\u0103, bazat\u0103 pe \u00eenv\u0103\u021barea prin recompens\u0103, a fost antrenat\u0103 s\u0103 arunce mingi \u0219i pietre \u00eentr-un punct indicat, care se afla dincolo de raza de ac\u021biune a bra\u021bului (p\u00e2n\u0103 la 9,5 m, \u00een condi\u021biile unei raze de ac\u021biune de 7,5 m). Opera\u021biuni de acest tip vor ajuta robotica s\u0103 gestioneze o gam\u0103 mai larg\u0103 de sarcini, cu un consum mai mic de energie pentru deplasare, \u0219i vor face, de asemenea, munca sa mai sigur\u0103.<\/p>\n

Excavatorul realiza prinderi \u0219i arunc\u0103ri cu cupa av\u00e2nd dou\u0103 grade de libertate, care nu era rigid fixat\u0103 pe bra\u021b. Arunc\u0103rile se realizau at\u00e2t pe linie dreapt\u0103, c\u00e2nd lucra doar bra\u021bul, c\u00e2t \u0219i cu rotirea cabine. \u00cen cel de-al doilea caz, precizia era pu\u021bin mai sc\u0103zut\u0103, dar \u00een orice caz, proiectilul devia de la punctul de \u021bint\u0103 cu nu mai mult de 30\u201340 cm. <\/p>\n

<\/center>
\r\n \"Reda\u021bi\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 on a number of non-trivial operations, such as teaching it to build a stable wall from unprepared stone blocks. The excavator independently assessed the balance of the stones and constructed a sturdy stone barrier. For precise autonomous work in the field, the excavator uses sensors installed on it to build a model of the surrounding space in which it performs assigned tasks.<\/p>\n

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