@imankitgoyal Profile picture

Ankit Goyal

@imankitgoyal

Research Scientist @Nvidia | Developing Foundation Models for Robotics | Ph.D. @PrincetonCS | Previously: @UMich, @IITKanpur

Similar User
Haochen Shi photo

@HaochenShi74

Chris Paxton photo

@chris_j_paxton

Jacky Liang photo

@jackyliang42

Dhruv Shah photo

@shahdhruv_

Fei Xia photo

@xf1280

Shuran Song photo

@SongShuran

Oier Mees photo

@oier_mees

Lerrel Pinto photo

@LerrelPinto

Ajay Mandlekar photo

@AjayMandlekar

Vikash Kumar photo

@Vikashplus

Murtaza Dalal photo

@mihdalal

Kaichun Mo photo

@KaichunMo

Harry Zhang photo

@HarryZhangOG

Jiafei Duan photo

@DJiafei

Jason Ma photo

@JasonMa2020

Pinned

Robots can perform several tasks via behavior cloning. But what about tasks that require high precision? We are excited to introduce RVT-2! Using just a single RGBD camera and as few as ten demonstrations, RVT-2 achieves millimeter-level precision for tasks like inserting a…


A very well deserved recognition to the pioneers of neural networks! The Nobel prize is timely and marks the acknowledgment of the transformative power of AI.

BREAKING NEWS The Royal Swedish Academy of Sciences has decided to award the 2024 #NobelPrize in Physics to John J. Hopfield and Geoffrey E. Hinton “for foundational discoveries and inventions that enable machine learning with artificial neural networks.”

Tweet Image 1


Thanks for the invitation! I am looking forward to presenting @MontrealRobots

Join us tomorrow for this week's robot learning seminar, in which @imankitgoyal from @nvidia will present his talk titled "View Transformers for 3D Manipulation in Robotics". See you there at 11:30AM ET! YouTube.com/@MontrealRobot#Manipulation #multiViewLearning #transformers

Tweet Image 1


Applications are now open for NVIDIA Graduate Fellowship. - For PhD students who have completed at least one year - Deadline Sep 13 - Requires a research proposal and 2 LoRs - Includes a summer internship blogs.nvidia.com/blog/applicati…


Nice collection of recent works for anyone looking to explore 3D vision and robotics.

✨Our 3D vision meets robotics papers list in the era of large models now has 80+ papers and crossed 50 stars and growing🚀 github.com/zubair-irshad/… Topics include policy learning, VLMs and VLAs, 3D Representations including NeRF, Gaussian Splatting, Simulations and Benchmarks…



Happy to share our work 3D-MVP, where we explore how to pretrain 3D manipulation policy. We observe both improved generalization and better in-domain performance. Please checkout the thread by @JasonQSY 👇

Exciting News! Our new paper "3D-MVP" is out! We propose a novel approach for 3D multi-view pretraining using masked autoencoders, leveraging Robotic View Transformer (RVT) to improve generalization for downstream robotics tasks. jasonqsy.github.io/3DMVP/

Tweet Image 1


Ankit Goyal Reposted

Exciting News! Our new paper "3D-MVP" is out! We propose a novel approach for 3D multi-view pretraining using masked autoencoders, leveraging Robotic View Transformer (RVT) to improve generalization for downstream robotics tasks. jasonqsy.github.io/3DMVP/

Tweet Image 1

Excited to attend #RSS2024 and catch up with everyone! Please DM if you are around and would like to meet. Will present our work RVT-2, a SOTA method for robotic manipulation. [July 17 8:30 - 9:30 am]. Paper: github.com/nvlabs/rvt Thread: 👇

Robots can perform several tasks via behavior cloning. But what about tasks that require high precision? We are excited to introduce RVT-2! Using just a single RGBD camera and as few as ten demonstrations, RVT-2 achieves millimeter-level precision for tasks like inserting a…



What a win!

INDIA HAVE WON THE T20 WORLD CUP....!!! 🇮🇳 - The 11 year jinx finally ends.

Tweet Image 1


Thanks @chris_j_paxton for the nice summary of our work! Check it out 👇

Perform *precise* 3d manipulation tasks using language and perception with RVT-2, with only a few examples. Gets SOTA on RLBench, and look at the videos! High-precision tasks are very hard for vision-language-action models, but crucial for real-world applications. ->



Ankit Goyal Reposted

Perform *precise* 3d manipulation tasks using language and perception with RVT-2, with only a few examples. Gets SOTA on RLBench, and look at the videos! High-precision tasks are very hard for vision-language-action models, but crucial for real-world applications. ->


Excited to give a keynote at the Future Roadmap for Manipulation Skills workshop in #ICRA. Please join if you are around [11:20am - 11:40am Tokyo Time, G6 North].

We have a fantastic lineup of speakers! Submit your workshop paper and share your thoughts on what kind of manipulation skills we should learn! Submission deadline is: March 31st! tinyurl.com/449y8yvn

Tweet Image 1


Loading...

Something went wrong.


Something went wrong.