Credit: © CREATE Lab/EPFL
Key points:
- Researchers used Chat-GPT to design robotic tomato pickers.
- The resulting study and lessons learned provides a framework for future human and AI collaborations.
- The team concluded that large language models have great potential to be a force for good, if well managed.
Neural networks known as large language models (LLMs) like Chat-GPT continue to make headlines for their potential to change the way we live. Now, EPFL researchers are applying the technology to a new area: robotic design.
In a study published in Nature Machine Intelligence, researchers used Chat-GPT to design a working robotic tomato-harvester. The study provides a framework for humans and LLMs to design such devices collaboratively.
In the first stage of the study, researchers conversed with the LLM on future challenges to humanity, identifying robotic crop harvesting as a solution to the challenge of global food supply. They then drew upon the LLM’s access to global data from academic publications, technical manuals, books, and media to get an answer to which features are most important for a robot harvester.
Once a basic robotic format was identified, researchers began to ask deeper questions about the design, including asking the LLM to make technical suggestions such as materials and computer code for controlling the device.
Based on their experience, the researchers describe opportunities and risks of applying artificial intelligence tools to robotics, which they argue “could change the way we design robots, while enriching and simplifying the process.” For example, “collaborative exploration” uses AI to augment researchers’ expertise by contributing wide-ranging knowledge beyond their own fields. AI can also act as a funnel, helping to refine the design process and providing technical input, with humans retaining creative control.
As there are logical and ethical risks associated with each collaboration mode, the researchers caution that the role of LLMs must be carefully evaluated going forward. For example, the use of LLMs raises questions of bias, plagiarism, and intellectual property, as it’s unclear if an LLM-generated design can be considered novel.
Still, the team concluded that based on their experience, LLMs have great potential to be a force for good, if well managed.