MIT debuts a large language model-inspired method for teaching robots new skills

Date:

Share post:


MIT this week showcased a new model for training robots. Rather than the standard set of focused data used to teach robots new tasks, the method goes big, mimicking the massive troves of information used to train large language models (LLMs).

The researchers note that imitation learning — in which the agent learns by following an individual performing a task — can fail when small challenges are introduced. These could be things like lighting, a different setting, or new obstacles. In those scenarios, the robots simply don’t have enough data to draw upon in order to adapt.

The team looked to models like GPT-4 for a kind of brute force data approach to problem solving.

“In the language domain, the data are all just sentences,” says Lirui Wang, the new paper’s lead author. “In robotics, given all the heterogeneity in the data, if you want to pretrain in a similar manner, we need a different architecture.”

The team introduced a new architecture called Heterogeneous Pretrained Transformers (HPT), which pulls together information from different sensors and different environments. A transformer was then used to pull together the data into training models. The larger the transformer, the better the output.

Users then input the robot design, configuration, and the job they want done.

“Our dream is to have a universal robot brain that you could download and use for your robot without any training at all,” CMU associate professor David Held said of the research. “While we are just in the early stages, we are going to keep pushing hard and hope scaling leads to a breakthrough in robotic policies, like it did with large language models.”

The research was founded, in part, by Toyota Research Institute. Last year at TechCrunch Disrupt, TRI debuted a method for training robots overnight. More recently, it struck a watershed partnership that will unite its robot learning research with Boston Dynamics hardware.  



Source link

Lisa Holden
Lisa Holden
Lisa Holden is a news writer for LinkDaddy News. She writes health, sport, tech, and more. Some of her favorite topics include the latest trends in fitness and wellness, the best ways to use technology to improve your life, and the latest developments in medical research.

Recent posts

Related articles

Quantum Machines and Nvidia use machine learning to get closer to an error-corrected quantum computer

About a year and a half ago, quantum control startup Quantum Machines and Nvidia announced a deep...

Can you build a startup without sacrificing your mental health? Bonobos founder Andy Dunn thinks so

Bonobos founder Andy Dunn is back in the builder’s seat, working on an in-person social media platform...

CoffeeSpace is a Hinge-like app that wants to help you find your co-founder

CoffeeSpace is on a mission to help people find partners for their startup ideas online. The startup,...

CareYaya is enabling affordable home care by connecting healthcare students with elders

CareYaya, a platform that matches people who need caregivers with healthcare students, is working to disrupt the...

How national interest startups should be thinking about government contracts

National interest technology can show up in a lot of ways, like in data analysis and cybersecurity,...

Microsoft and a16z set aside differences, join hands in plea against AI regulation

Two of the biggest forces in two deeply intertwined tech ecosystems — large incumbents and startups —...

SpaceX wants to test refueling Starships in space early next year

SpaceX will attempt to transfer propellant from one orbiting Starship to another as early as next March,...

Perplexity launches an elections tracker

Perplexity, the AI-powered search engine, might hallucinate from time to time. But the company wants to show...