RT-2: Vision-Language-Action Models (2023) (robotics-transformer2.github.io)

Screenshot of robotics-transformer2.github.io: RT-2: Vision-Language-Action Models (2023)

First screen, captured 1 year ago.

Looks similar

Screenshot of blog.google: RT-2 AI model translates vision and language into robotic actions

RT-2 AI model translates vision and language into robotic actions (blog.google)

142 points by BhattMayurJ 3 years ago | 56 comments

Screenshot of bostondynamics.com: Boston Dynamics and DeepMind form new AI partnership

Boston Dynamics and DeepMind form new AI partnership (bostondynamics.com)

61 points by mfiguiere 9 months ago | 31 comments

Screenshot of robopen.github.io: RoboAgent: A universal agent with 12 Skills

RoboAgent: A universal agent with 12 Skills (robopen.github.io)

124 points by reqo 3 years ago | 17 comments

Screenshot of vlmsareblind.github.io: Vision language models are blind

Vision language models are blind (vlmsareblind.github.io)

425 points by taesiri 2 years ago | 172 comments

Project page for the research paper "Vision language models are blind" from Auburn University and University of Alberta, with links to the arXiv paper, code, and dataset.

vision-language-models multimodal-ai benchmarks computer-vision

Screenshot of dinov2.metademolab.com: DINOv2: State-of-the-art computer vision models with self-supervised learning

DINOv2: State-of-the-art computer vision models with self-supervised learning (dinov2.metademolab.com)

139 points by mvoodarla 3 years ago | 13 comments

Screenshot of ok-robot.github.io: Show HN: OK-Robot: open, modular home robot framework for pick-and-drop anywhere

Show HN: OK-Robot: open, modular home robot framework for pick-and-drop anywhere (ok-robot.github.io)

494 points by MahiShafiullah 2 years ago | 103 comments

Project page for OK-Robot, an open, modular framework for zero-shot, language-conditioned pick-and-drop tasks by robots in arbitrary homes.

robotics home-robots zero-shot-learning manipulation

Looks similar

RT-2 AI model translates vision and language into robotic actions(blog.google)

Boston Dynamics and DeepMind form new AI partnership(bostondynamics.com)

RoboAgent: A universal agent with 12 Skills(robopen.github.io)

Vision language models are blind(vlmsareblind.github.io)

DINOv2: State-of-the-art computer vision models with self-supervised learning(dinov2.metademolab.com)

Show HN: OK-Robot: open, modular home robot framework for pick-and-drop anywhere(ok-robot.github.io)