Excited to share our latest work, Vision-Language Frontier Maps – a SOTA approach for semantic navigation in robotics. VLFM enables robots to navigate and find objects in novel environments using vision-language foundation models, zero-shot! Accepted to #ICRA2024! 🧵

Does AI need a “body” to become truly intelligent? Meta researchers think so. We may be on the brink of finally seeing human-level intelligence in an AI — thanks to robots. AIs that can generate videos, quickly translate languages, or write new computer code could be world

Our #ICRA2024 paper was selected as a finalist for the Best Paper Award in Cognitive Robotics! I'll be giving a presentation on this paper at the conference for a shot at the award. See you there!

like this line of work so much Object-oriented navigation Habitat simulator And control the dog Solid contribution, function in real world at a scale

Today we’re releasing OpenEQA — the Open-Vocabulary Embodied Question Answering Benchmark. It measures an AI agent’s understanding of physical environments by probing it with open vocabulary questions like “Where did I leave my badge?” More details ➡️ go.fb.me/7vq6hm

I have been working on vision+language models (VLMs) for a decade. And every few years, this community re-discovers the same lesson -- that on difficult tasks, VLMs regress to being nearly blind! Visual content provides minor improvement to a VLM over an LLM, even when these

Launching OpenEQA, our new benchmark for AI's understanding of physical environments. Despite AGI optimism, our tests with top VLMs reveal a significant gap to human-level comprehension. Let's bridge this gap in AI's world understanding.

Washingtonians delved into the world of artificial intelligence (AI) at the Washington AI Network’s inaugural weekend TGAIFriday Lunch for White House correspondents. trib.al/FwHF9Um

FAIR researchers (AI at Meta) presented SegmentAnything and our robotics work at the White House correspondents’ weekend. Llama3 + Sim2Real skills (trained with AI Habitat) = a robot assistant

Proud of the team for the very robust and engaging robot demo.

On Tuesday at #ICLR2024, we will be presenting Habitat 3.0, our human/robot simulator, featuring a VR demo that allows you to interact firsthand with both the scenes and the robot.

.Georgia Tech Computing Award winning paper presentation from the GT 🐝🐝s

Naoki Yokoyama Naoki Yokoyama presenting his best paper award finalist talk at #ICRA2024! Vision-Language Frontier Maps for Zero-Shot Semantic Navigation: show how to combine VL foundation models with a mapping+search stack. Georgia Tech School of Interactive Computing Robotics@GT Machine Learning at Georgia Tech Boston Dynamics

Dhruv Batra Naoki Yokoyama Georgia Tech School of Interactive Computing Machine Learning at Georgia Tech Boston Dynamics .Dhruv Batra We were thrilled to catch the talk live 🤖🔥

A good day for Georgia Tech School of Interactive Computing Robotics@GT. Congratulations Sehoon Ha Naoki Yokoyama Dhruv Shah and Shuo Cheng !

From Best Paper finalist to WINNER 🏆 IEEE ICRA for Naoki Yokoyama and team. Congratulations, Naoki Yokoyama Sehoon Ha Dhruv Batra Georgia Tech Computing

From Best Paper Award finalist to winner! Congratulations Naoki Yokoyama on a well-deserved recognition! Georgia Tech Computing Robotics@GT #icra2024

Robotics@GT FTW!

This is no small feat. At the robotics field's #1 research venue, our researchers are #1, earning the Best Paper Award in Cognitive Robotics, among the eligible 1,700+ papers at #ICRA2024. Partnered with Boston Dynamics. 🤖🏆🎉 Award details: ieee-ras.org/awards-recogni…

A best paper winner at the most prestigious robotics conference in the world! A major accomplishment for our researchers. #WeCanDoThat