For the tomato harvest: Swiss researchers develop robots with ChatGPT

class=”sc-29f61514-0 jbwksb”>

In the first phase, scientists from the Swiss Federal Institute of Technology (EPFL) in Lausanne used ChatGPT to discuss humanity’s future challenges. In this discussion, the researchers and the computer program jointly identified robotic harvesting as a solution to the global food supply problem. ChatGPT also concluded that the tomato is the crop for which a harvester is most valuable.

Designed and coded by ChatGPT

Then the researchers asked ChatGPT, “What characteristics should a harvesting robot have?” asked more specific questions such as This is how the design and features of the robot emerged. The second stage was the realization of the robot. ChatGPT provided programming code and design ideas for it.

Optimization by researchers

As the study says, the researchers took on the technician role. They optimized ChatGPT’s proposed code, finalized the design pattern, and produced the robot.

What’s new is that so-called LLM (Large Language Models) like ChatGPT supports not only the development of the code, but also the design. According to the researchers, this could enrich and simplify the design process of robots.

However, the question of how these tools can be used to meet the challenges of the 21st century without limiting the creativity, innovation and scientific effort required for robotics remains unanswered.

Scientists are enthusiastic about it. “Looking forward, we strongly believe that LLMs will open up many exciting opportunities and, if managed properly, will be a force for good,” the researchers wrote in the study.

https://doi.org/10.1038/s42256-023-00669-7

(SDA)

Source : Blick