Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Using monocular slam + ego video to create usable reinforcement learning environments for embodied ai

Chris Paxton

37,567 subscribers

12,943 Aufrufe • vor 1 Monat •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environments TL;DR: We present WildGS-SLAM, a robust monocular RGB SLAM system. - Utilizes uncertainty-aware tracking and mapping to handle dynamic scenes. - Leverages DINOv2-based uncertainty maps for dynamic object removal. - Improves tracking and mapping. - Enables high-quality view synthesis.

WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environments TL;DR: We present WildGS-SLAM, a robust monocular RGB SLAM system. - Utilizes uncertainty-aware tracking and mapping to handle dynamic scenes. - Leverages DINOv2-based uncertainty maps for dynamic object removal. - Improves tracking and mapping. - Enables high-quality view synthesis.

MrNeRF

17,438 Aufrufe • vor 1 Jahr

Just released five robotics simulation environments we have been using to train reinforcement learning from vision and touch! Very easy to install. Powered by Google DeepMind MuJoCo, Gymnasium, and robosuite. GitHub link:

Just released five robotics simulation environments we have been using to train reinforcement learning from vision and touch! Very easy to install. Powered by Google DeepMind MuJoCo, Gymnasium, and robosuite. GitHub link:

Carlo Sferrazza

24,389 Aufrufe • vor 2 Jahren

Using large-scale GPU parallelized reinforcement learning in Isaac Sim, we are able to obtain a robust whole-body controller for Taku optimized for precise loco-manipulation.

Using large-scale GPU parallelized reinforcement learning in Isaac Sim, we are able to obtain a robust whole-body controller for Taku optimized for precise loco-manipulation.

Dyna Robotics

85,440 Aufrufe • vor 1 Monat

AI video generated using 2 softwares: 1. Midjourney : To create avatar 2. D-ID : To create talking video For video editing: 1. Veed : For captioning 2. VN : Video editing software It was so much fun creating this one😍

Rishika Gupta

70,601 Aufrufe • vor 3 Jahren

1. Machine Learning Specialization Break into AI with this 3-course program by Andrew Ng. What you’ll learn: → Build machine learning models → Train neural networks → Deep reinforcement learning → Unsupervised learning techniques 🔗

1. Machine Learning Specialization Break into AI with this 3-course program by Andrew Ng. What you’ll learn: → Build machine learning models → Train neural networks → Deep reinforcement learning → Unsupervised learning techniques 🔗

Amit

55,462 Aufrufe • vor 10 Monaten

Uhhhh, what a creepy video for Mario Lopez to create using AI and then post… Especially since the subject is his niece!

Uhhhh, what a creepy video for Mario Lopez to create using AI and then post… Especially since the subject is his niece!

Yashar Ali 🐘

3,498,074 Aufrufe • vor 3 Monaten

I'm learning to make my own environments. 🛠️🌲

I'm learning to make my own environments. 🛠️🌲

Scaredy_Hare

26,839 Aufrufe • vor 2 Monaten

StereoWorld Geometry-Aware Monocular-to-Stereo Video Generation

StereoWorld Geometry-Aware Monocular-to-Stereo Video Generation

AK

11,372 Aufrufe • vor 10 Monaten

My kid is learning how to program. He is not using AI.

My kid is learning how to program. He is not using AI.

Santiago

32,511 Aufrufe • vor 1 Jahr

.28 seconds reaction time. With the click of a button you’ll be able to automatically create a video that measures FSD’s reaction time using CamCutApp. Probably my favorite feature One area where I’d like to see FSD improve: recognizing high-occlusion environments. Densely parked cars next to hidden driveways create situations where a vehicle can suddenly appear with little warning for either driver. Tesla AI

.28 seconds reaction time. With the click of a button you’ll be able to automatically create a video that measures FSD’s reaction time using CamCutApp. Probably my favorite feature One area where I’d like to see FSD improve: recognizing high-occlusion environments. Densely parked cars next to hidden driveways create situations where a vehicle can suddenly appear with little warning for either driver. Tesla AI

Edge Case

45,030 Aufrufe • vor 4 Monaten

What if we could teach an AI to master the strategic game of 2048 through pure reinforcement learning? I did exactly that with "Agent 2048" - fine-tuning Qwen 7B model using GRPO to develop spatial reasoning and merge strategies with zero prior gameplay SFTdata! Thanks to Hugging Face and Unsloth AI for their easy to use implementation kalomaze and will brown you might like this :)

What if we could teach an AI to master the strategic game of 2048 through pure reinforcement learning? I did exactly that with "Agent 2048" - fine-tuning Qwen 7B model using GRPO to develop spatial reasoning and merge strategies with zero prior gameplay SFTdata! Thanks to Hugging Face and Unsloth AI for their easy to use implementation kalomaze and will brown you might like this :)

Hrishbh Dalal

31,863 Aufrufe • vor 1 Jahr

Learn how to create film-quality 3D environments with Intro to Worldbuilding and Environments, a new workshop from DoubleJump Academy. The workshop covers various techniques for layout, procedural modeling for environments, lighting, and more: #sponsored #ad

Learn how to create film-quality 3D environments with Intro to Worldbuilding and Environments, a new workshop from DoubleJump Academy. The workshop covers various techniques for layout, procedural modeling for environments, lighting, and more: #sponsored #ad

80 LEVEL

18,910 Aufrufe • vor 9 Monaten

The CapCut Video Studio Challenge is LIVE 🤩 Create a video using CapCut’s newly launched AI workspace, Video Studio, and enter to win $9.5K in prizes. What are you waiting for?

The CapCut Video Studio Challenge is LIVE 🤩 Create a video using CapCut’s newly launched AI workspace, Video Studio, and enter to win $9.5K in prizes. What are you waiting for?

Contra

10,880 Aufrufe • vor 7 Monaten

Fin-R1 is out on Hugging Face A Large Language Model for Financial Reasoning through Reinforcement Learning

Fin-R1 is out on Hugging Face A Large Language Model for Financial Reasoning through Reinforcement Learning

AK

89,153 Aufrufe • vor 1 Jahr

Almost forgot my streak 😂 Anyways here's Day 5 of learning AI Video 🎥 Created a UGC-style ad for Glovo using ChatGPT + Google Flow. Would you stop scrolling to watch this ad? #AIVideo #Glovo #GoogleFlow #AI #LearningInPublic

Almost forgot my streak 😂 Anyways here's Day 5 of learning AI Video 🎥 Created a UGC-style ad for Glovo using ChatGPT + Google Flow. Would you stop scrolling to watch this ad? #AIVideo #Glovo #GoogleFlow #AI #LearningInPublic

Ajé | the Gohighlevel Guy

10,817 Aufrufe • vor 1 Monat

one day PhDs will animate every object around us with reinforcement learning to keep their thesis going

one day PhDs will animate every object around us with reinforcement learning to keep their thesis going

Jim Fan

464,159 Aufrufe • vor 2 Jahren

NVIDIA's Jim Fan has verified from reliable sources that the video by EngineAI is a real robot demo and not CGI. The controller is a neural net trained in the NVIDIA Isaac simulator using reinforcement learning. There’s also another video from a different angle.

NVIDIA's Jim Fan has verified from reliable sources that the video by EngineAI is a real robot demo and not CGI. The controller is a neural net trained in the NVIDIA Isaac simulator using reinforcement learning. There’s also another video from a different angle.

The Humanoid Hub

148,535 Aufrufe • vor 1 Jahr

We are excited to announce our strategic partnership with Fraction AI for their IIO launch. Fraction AI is the first decentralized training platform for AI agents with millions of sessions, 150,000+ agents deployed, and over $1M in rewards distributed. On our platform, thousands of AI agents compete in specialized domains and continuously improve through Reinforcement Learning. Stay tuned for upcoming surprise announcements.

We are excited to announce our strategic partnership with Fraction AI for their IIO launch. Fraction AI is the first decentralized training platform for AI agents with millions of sessions, 150,000+ agents deployed, and over $1M in rewards distributed. On our platform, thousands of AI agents compete in specialized domains and continuously improve through Reinforcement Learning. Stay tuned for upcoming surprise announcements.

peep icosystem

19,969 Aufrufe • vor 1 Jahr

$Meet Scout 1.0, our first AI model built for investigating production incidents. Scout matches frontier-model investigation quality at a fraction of the cost, which makes it practical to investigate more issues, earlier. We trained Scout on realistic simulations built from real-world incidents and production telemetry, using reinforcement learning to reward accurate root causes backed by evidence. Learn more and sign up for the preview:$

Meet Scout 1.0, our first AI model built for investigating production incidents. Scout matches frontier-model investigation quality at a fraction of the cost, which makes it practical to investigate more issues, earlier. We trained Scout on realistic simulations built from real-world incidents and production telemetry, using reinforcement learning to reward accurate root causes backed by evidence. Learn more and sign up for the preview:

Datadog, Inc.

52,402 Aufrufe • vor 19 Tagen