Researchers use ChatGPT to build a tomato picking robot, demonstrating the infinite possibilities of artificial intelligence

News on June 8, recently, some researchers used the help of ChatGPT to build a tomato picking robot.

OpenAI’s ChatGPT is a language model that can process and understand large amounts of text data and use this information to answer questions. In a new case study, researchers from Delft University of Technology in the Netherlands and the Swiss Federal Institute of Technology turned to ChatGPT-3 for help in designing and building a robot.

This sounds a bit strange because ChatGPT-3 is a language model, not a mechanical model. "Although ChatGPT-3 is a language model, its code generation is also text-based, providing important insights and intuition for physical design and showing great potential to inspire human creativity," said study co-author Josie Hughes said.

First, the researchers asked the AI ​​model, "What are the challenges facing humanity in the future?" ChatGPT-3 came up with three: food supply, population aging, and climate change. The researchers chose food supply as a robot design direction and then asked ChatGPT-3 what characteristics a tomato harvesting robot should have. ChatGPT-3 proposes a motor-driven gripper for plucking ripe tomatoes from the vine.

Once this rough design is determined, researchers can make decisions about design details, including what materials to use and what control code to write. Currently, language models cannot generate complete computer-aided design (CAD) models, evaluate codes, or automatically manufacture robots, so this step requires researchers to play the role of "technicians" to assist in these aspects and optimize the code written by the language model. Complete the CAD and build the robot.

The questions posed by the researchers are presented above, while the options provided by the language model are shown below. Human decision trees, shaded green, gradually focus the problem in a direction consistent with their goals.

With technical advice provided by ChatGPT-3, the researchers built their robotic gripper and tested it in the real world, using it to pick tomatoes, with successful results.

b. Technical suggestions, including shape instructions, coding, component and material selection, mechanical design, etc., for generating language models. b. Guided by these inputs, a clamp was built and tested on real-world tasks, such as tomato picking, as shown on the right.

The researchers say their case study demonstrates the potential for collaboration between humans and language models to transform the design process, but they also realize this collaboration may come in varying degrees.

An extreme approach, they say, is for AI to act as the "inventor," providing all input into the robot's design, while humans just blindly apply it. Another approach is to use AI’s extensive knowledge to supplement human expertise. The third way is to retain humans as inventors and use artificial intelligence to troubleshoot, debug and handle tedious or time-consuming processes to optimize the design process.

Researchers have raised some of the ethical and common sense risks that may arise from AI working with humans, citing issues such as bias, plagiarism and intellectual property as areas of concern.

“In our study, ChatGPT-3 identified tomatoes as the most worthy crop to design a harvesting robot for,” Hughes said. “However, this may be a bias against crops with greater literature coverage, Rather than crops that are truly in need. When decisions are made beyond an engineer's knowledge, this can lead to serious ethical, engineering, or factual errors."

Despite these problems, researchers believe that if managed properly, artificial intelligence There is great potential for collaboration with humans.

This case study was published in the journal "Natural Machine Intelligence". You can click here to view details.

The above is the detailed content of Researchers use ChatGPT to build a tomato picking robot, demonstrating the infinite possibilities of artificial intelligence. For more information, please follow other related articles on the PHP Chinese website!