TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

GPT for Robotics: Perception-Action Causal Transformer

2 pointsby madratmanover 2 years ago

1 comment

madratmanover 2 years ago
Generative self-supervised model for robotics data. Highlights: - Transformer model for autoregressive prediction of states and actions over time to implicitly encode dynamics and behaviors for a particular robot - The representation learned can be fine-tuned to distinct tasks (navigation, mapping, localization) with minimal data - The base transformer model serves as a generative robotics model, similarly to GPT-3, and can be prompted to result in different robot behaviors<p>Paper: <a href="https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;2209.11133;" rel="nofollow">https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;2209.11133;</a> Video: <a href="https:&#x2F;&#x2F;youtu.be&#x2F;mNQvQu_atuw;" rel="nofollow">https:&#x2F;&#x2F;youtu.be&#x2F;mNQvQu_atuw;</a> Code and data: <a href="https:&#x2F;&#x2F;github.com&#x2F;microsoft&#x2F;PACT" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;microsoft&#x2F;PACT</a>