PaLM-SayCan: Google’s new model to make robots more helpful with complex requests
Google has created a new large-scale learning model that improves the robots’ overall performance and ability to perform more complex and abstract tasks, as well as handle complex human requests. Called PaLM-SayCan, the Google-Everyday Robots research uses PaLM — or Pathways Language Model — in a robot learning model.
About PaLM-SayCan
This collaborative study, dubbed PaLM-SayCan, employs PaLM — or Pathways Language Model — in a robot learning model running on an Everyday Robots helper robot. This is the first time a large-scale language model has been used to plan for a real robot. It not only allows people to communicate with helper robots through text or speech, but it also improves the robot’s overall performance and ability to execute more complex and abstract tasks by utilising the world knowledge encoded in the language model.
Using language to improve robots
PaLM-SayCan teaches the robot how we communicate, allowing for more natural interaction. Language reflects the human mind’s ability to assemble tasks, contextualise them, and even reason through problems. Language models also contain massive amounts of information about the world, which turns out to be quite useful to the robot. PaLM can assist the robotic system in processing more complex, open-ended prompts and responding to them in reasonable and sensible ways.
“This effort is the first implementation that uses a large-scale language model to plan for a real robot. It not only makes it possible for people to communicate with helper robots via text or speech but also improves the robot`s overall performance,” the tech giant said in a blog post.
Today, most robots exist in industrial settings and are painstakingly programmed for specific tasks. As a result, they are unable to adapt to the unpredictability of the real world. “That`s why Google Research and Everyday Robots are working together to combine the best of language models with robot learning,” said Vincent Vanhoucke, Head of Robotics at Google Research.
Liked this post? Don’t forget to check out our other short stories in our Quick Read section