🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

It was a great ride!

Team Explorer motivated us from the beginning about what we have to become to win a DARPA Challenge!

Looking forward to going back to CMU for a postdoc with AirLab in a few weeks! I will be working on planning for multidrone reconstruction and am super excited to see where the project goes!

The AirLab had 6 papers accepted into #ICRA2022! We're very excited to see you all there! Read more about the papers here: medium.com/airlabcmu/a-qu…

We are excited to share our work “AirLoop: Lifelong Loop Closure Detection” which has been accepted to ICRA 2022. It is one of the first works to study loop closure detection in the lifelong learning context. Paper: arxiv.org/abs/2109.08975 Chen Wang Sebastian Scherer 1/3

Our model is able to handle cross-environment loop closure detection despite only being trained in individual environments sequentially. This image shows examples of loop closure detections on our different datasets. 2/3

An overview video for “AirLoop: Lifelong Loop Closure Detection” can be found here: youtu.be/Gr9i5ONNmz0 The code can also be found here: github.com/wang-chen/AirL… 3/3

AirLab Chen Wang Sebastian Scherer

This week we're sharing another #ICRA2022 paper. "AirDOS: Dynamic SLAM benefits from Articulated Objects" from Yuheng Qiu, Chen Wang, Wenshan Wang, Mina Henein, and Sebastian Scherer . Paper: arxiv.org/abs/2109.09903 Video: youtube.com/watch?v=gM5iUL… Blog: theairlab.org/airdos/

Chen Wang Sebastian Scherer We show that feature-based vSLAM systems can benefit from the presence of dynamic articulated objects by taking advantage of two observations: The 3D structure of an articulated object remains consistent over time; The points on the same object follow the same motion.

Good luck today at the 2022 Greater Pittsburgh Regional Girls of Steel Robotics! FIRST Ladies #morethanrobots #womeninSTEM #ladiesinFIRST #FIRST

Thrilled to share that I have accepted a fully-funded Masters in Robotics offer from CMU School of Computer Science! Very excited to be joining the AirLab 🤖🕺 Extremely grateful to all the support from my family, friends, mentors and collaborators 🙌❤️ #gradschool #CMU #dreamcometrue #robotics

Check out our latest progress on high-speed autonomous off-road driving! AirLab is part of the CMU/UoR's team in this cutting-edge challenge.

Thanks to our 40+ volunteer developers from 16 institutes and 3 continents, we are finally able to officially release our paper for PyPose, a library for robot learning with physics-based optimization! Check it out at arxiv.org/abs/2209.15428

We are excited to announce the release of our open-source calibration package called TartanCalib, which improves reprojection errors by up to 27%, helps us detect up to 42% more features, and improves performance in dense depth mapping: youtu.be/8WCCS-Ag_Co

Come along for the (autonomous) ride with Yorai Shaoul, and see what a day is like for a Ph.D. student at Carnegie Mellon University Robotics Institute: youtu.be/6Itn8yxFoYg 👆🤖🎥 CMU School of Computer Science Yorai Shaoul CMU Robotics Institute Carnegie Mellon University

Our ieeeIROS #IROS2023 workshop, 🌟Closing the Loop on #Localization🌟 has now full details available here: tinyurl.com/Localization20… And there are exiciting ways for you to get involved 🧵👇

🧠🔬 Excited to share AnyLoc: Towards Universal Visual Place Recognition Foundation Models meet VPR - VPR anywhere🌍🌊🏙️, anytime🌌☁️🌄, and under anyview🚡🚗🛸 - no retraining/finetuning 🔁 - aimed at general-purpose localization & navigation anyloc.github.io 🧵👇

Guess what just arrived? High-Performance 🤖 H100 Nodes! 🤩 Time for some cozy GPU heat 🥵 CMU Robotics Institute

CMU's AirLab team is reaching new heights. 👏 An aerial rescue vehicle developed at AirLab will advance to the next stage of the GoAERO Competition. The Tartan Air Rescue team was named a Stage 1 winner of the competition. ➡️ cmu.is/AirLab