This summer, Taerim Yoon from Korea University joined our lab through the ETH Robotics Student Fellowship and developed a "Parkour Controller" using RL, enabling agile moves over obstacles. We’re excited to push this further for more agile legged locomotion. Please stay tuned!

InterTrack: tracking human-object interaction without any pre-scanned object template. We build the shapes from scratch and track them from a single RGB video. Key idea: 4D tracking = one global shape + per-frame pose. Great collaboration with Gerard Pons-Moll Jan Eric Lenssen

GaussianFormer code dropped! github.com/huang-yh/Gauss…

Large codebase refactor. Getting ready for the public release. Looks like I didn't break anything (yet). Woohoo! 🤣

We have a new paper at CoRL, opening both push and pull doors with a single policy.

Also, another shout-out to my collaborators Krishna Suresh and Aditya Rauniyar! They did the hard work implementing everything and generating all these pretty figures 🌟 I just like to run my mouth 😃

For more detail: Check out our website (w/ code on github!): greedyperspectives.github.io The paper is on arxiv: arxiv.org/abs/2310.10863 Or track us down at ieeeIROS in October!

Gaussian Garments: Reconstructing Simulation-Ready Clothing with Photorealistic Appearance from Multi-View Video Contribution quote from the paper: In summary, our main contributions are • a comprehensive pipeline for reconstructing the shape, appearance, and behavior of

Also, I recently formed NAPPLab at Mines. We will be continuing this line of work so if this thread interests you, consider giving us a follow!

Shhhhh. The robots are sleeping 🤫

🤖 My lab has a Twitter! Follow us for more on Navigation, Aerial robots, and Perception Planning (we're NAPPLab 😄). We do research on topics like inspection for reconstruction and autonomous videography! (the sleeping robots are just a bonus ☺️)

CS@Mines is hiring for two faculty positions with a focus on AI/ML and quantum CS respectively. If you are on the market and doing research in one of these areas, I'd highly recommend applying!

🤖 Getting ready to head to Abu Dhabi 🛫 for #IROS24! 🤖 Please feel free to reach out or DM if you are attending and would like to chat or meet up! 🎥 Two of my collaborators from CMU will be presenting on work related to multi-robot videography:

Krishna Suresh ⛏️🪨 If you made it this far and are planning to apply to graduate programs in robotics, consider Mines! And, if you are interested in my research specifically, check out NAPPLab robotics.mines.edu

🤖🎥 I will be presenting on coordinating multiple cameras for videography tasks at #CDC24 next week! This thread presents some details on methods: x.com/CorahMicah/sta… 👇See below for examples from our results!

Robots 🤖 and cameras 🎥 oh my! Our lab site is live! Check out: napplab.org

🤖 I am going to be in LA for the Robotics Science and Systems (RSS) conference this week! Please reach out to discuss topics like aerial robots 🚁, active perception 📸, inspection 🔎, and robot videography ⛹️‍♂️🎥!

The preprint of our Paper ‘Nightmare Dreamer: Dreaming About Unsafe States And Planning Ahead’ is finally available! arxiv.org/abs/2601.04686