{"id":44035,"date":"2023-02-21T00:06:36","date_gmt":"2023-02-21T00:06:36","guid":{"rendered":"https:\/\/mailinvest.blog\/index.php\/2023\/02\/21\/carnegie-mellon-engineers-made-an-ai-powered-robot-that-manually-paints-pictures-from-text-audio-and-visual-prompts\/"},"modified":"2023-02-21T00:07:37","modified_gmt":"2023-02-21T00:07:37","slug":"carnegie-mellon-engineers-made-an-ai-powered-robot-that-manually-paints-pictures-from-text-audio-and-visual-prompts","status":"publish","type":"post","link":"https:\/\/mailinvest.blog\/index.php\/2023\/02\/21\/carnegie-mellon-engineers-made-an-ai-powered-robot-that-manually-paints-pictures-from-text-audio-and-visual-prompts\/","title":{"rendered":"Carnegie Mellon engineers made an AI-powered robot that manually paints pictures from text, audio, and visual prompts"},"content":{"rendered":"

<\/a>\n
<\/p>\n

\n

In a nutshell:<\/strong> Researchers at Carnegie Mellon College’s (CMU) Bot Intelligence Group (BIG) have developed a robotic arm that may paint footage based mostly on spoken, written, and visible prompts. The AI is similar to DALL-E, besides it bodily paints the output in actual time as an alternative of manufacturing a near-instant digital picture. <\/p>\n

The BIG<\/a> group named the robotic FRIDA as a nod to Mexican artist Frida Kahlo and as an acronym for Framework and Robotics Initiative for Creating Arts. At the moment, the robotic requires<\/a> no less than some contextual enter and about an hour to arrange its model of brush strokes.<\/p>\n

Customers also can add a picture to “encourage” FRIDA and affect the output by offering plain language descriptors. As an illustration, given a bust shot of Elon Musk and the spoken immediate “child sobbing,” the AI created the portrait under (prime left). The researchers have experimented with different enter varieties, corresponding to letting the AI take heed to a tune like Abba’s Dancing Queen.<\/p>\n

\n

A few of our new work on the FRIDA undertaking: Robotic Synesthesia, portray from sound and emotion inputs.https:\/\/t.co\/LrqyGigg5J<\/a> pic.twitter.com\/ouswMrMdyh<\/a><\/p>\n

— FRIDA Robotic Painter (@FridaRobot) February 12, 2023<\/a><\/p><\/blockquote>\n

Carnegie Mellon Ph.D. pupil and lead engineer Peter Schaldenbrand shortly identified that FRIDA can’t carry out like a real artist. In different phrases, the robotic shouldn’t be expressing creativity.<\/p>\n

“FRIDA is a robotic portray system, however FRIDA shouldn’t be an artist,” Schaldenbrand mentioned. “FRIDA shouldn’t be producing the concepts to speak. FRIDA is a system that an artist might collaborate with. The artist can specify high-level targets for FRIDA, after which FRIDA can execute them.”<\/p>\n

The robotic’s algorithms will not be not like these utilized in OpenAI’s ChatGPT and DALL-E 2. It’s a generative adversarial community (GAN) set as much as paint footage and consider its efficiency to enhance its output. Theoretically, with every portray, FRIDA ought to higher interpret the immediate and its product, however since artwork is subjective, who’s to say what’s “higher.”<\/p>\n