Microsoft Tests ChatGPT's Ability to Control Robots
dimanche 26 février 2023, 13:34 , par Slashdot
'We extended the capabilities of ChatGPT to robotics,' brags a blog post from Microsoft's Autonomous Systems and Robotics research group, 'and controlled multiple platforms such as robot arms, drones, and home assistant robots intuitively with language.'
They're exploring how to use ChatGPT to 'make natural human-robot interactions possible... to see if ChatGPT can think beyond text, and reason about the physical world to help with robotics tasks.'
We want to help people interact with robots more easily, without needing to learn complex programming languages or details about robotic systems. The key challenge here is teaching ChatGPT how to solve problems considering the laws of physics, the context of the operating environment, and how the robot's physical actions can change the state of the world.
It turns out that ChatGPT can do a lot by itself, but it still needs some help. Our technical paper describes a series of design principles that can be used to guide language models towards solving robotics tasks. These include, and are not limited to, special prompting structures, high-level APIs, and human feedback via text.... In our work we show multiple examples of ChatGPT solving robotics puzzles, along with complex robot deployments in the manipulation, aerial, and navigation domains....
We gave ChatGPT access to functions that control a real drone, and it proved to be an extremely intuitive language-based interface between the non-technical user and the robot. ChatGPT asked clarification questions when the user's instructions were ambiguous, and wrote complex code structures for the drone such as a zig-zag pattern to visually inspect shelves. It even figured out how to take a selfie! We also used ChatGPT in a simulated industrial inspection scenario with the Microsoft AirSim simulator. The model was able to effectively parse the user's high-level intent and geometrical cues to control the drone accurately....
We are excited to release these technologies with the aim of bringing robotics to the reach of a wider audience. We believe that language-based robotics control will be fundamental to bring robotics out of science labs, and into the hands of everyday users.
That said, we do emphasize that the outputs from ChatGPT are not meant to be deployed directly on robots without careful analysis. We encourage users to harness the power of simulations in order to evaluate these algorithms before potential real life deployments, and to always take the necessary safety precautions. Our work represents only a small fraction of what is possible within the intersection of large language models operating in the robotics space, and we hope to inspire much of the work to come.tics to the reach of a wider audience. We believe that language-based robotics control will be fundamental to bring robotics out of science labs, and into the hands of everyday users.
ZDNet points out that Google Research and Alphabet's Everyday Robots 'have also worked on similar robotics challenges using a large language models called PaLM, or Pathways Language Model, which helped a robot to process open-ended prompts and respond in reasonable ways.'
Read more of this story at Slashdot.
56 sources (32 en français)
jeu. 28 sept. - 06:42 CEST