@AirLabCMU

We develop perception, control, & planning algorithms for robot autonomy | @CMU_Robotics | https://xitter.cf/t.co/gWjGiUaBeP | https://xitter.cf/t.co/9wO6amxfFc

 Pittsburgh, PA
theairlab.org
Joined June 2014
  • Tweets535
  • Following138
  • Followers3.4K
167Media
We don’t test with crash dummies. We test with Micah, at 10m/s, fully autonomous, off-road. His body made it through every corner. His soul made it through most of them. Check out our work on learned perception-conditioned dynamics models for high-speed off-road driving 👇
Micah Nye@micahnye31Oct 20
How your robot moves depends on what it’s driving over, especially when moving at >10m/s over loose gravel or ice 🚙💨 What if dynamics models could be conditioned on exactly the terrain they expect to drive over? Introducing SpatialBEV! Accepted at #CoRL2026 🤠 0/7
4
1
19
1,964
How your robot moves depends on what it’s driving over, especially when moving at >10m/s over loose gravel or ice 🚙💨 What if dynamics models could be conditioned on exactly the terrain they expect to drive over? Introducing SpatialBEV! Accepted at #CoRL2026 🤠 0/7
2
7
2
25
1,934
AirLab retweeted
Bowen Li@Bw_Li1024Oct 13
Failures are inevitable for robots that are deployed in the *big* world. We introduce ReSYNC, a system that leverages large-scale RL sim2real to recover from local failures and concept discovery to explain/avoid new failures. Check it out here: jaraxxus-me.github.io/ReSYNC…
12
28
4
85
7,804
MAC-I² learns how much to trust vision and IMU. Metrics-aware covariance for both modalities enables robust VI fusion. We apply it to initialization and calibration in challenging scenes and motions. mac-i2.github.io/ 1/9
1
6
19
1,135
Where do foundational models actually meet the real world? That's the question behind the 3rd AI Meets Autonomy workshop at IROS 2026! 📍 Pittsburgh | 🗓️ Thu, Oct 1 | 8:00–12:30 AM #IROS2026 🧵👇
1
3
6
998
Our workshop, Intelligent Information Gathering for Single and Multi-Robot Systems, has been accepted to #IROS2026! Join us in Pittsburgh for invited talks, paper submissions, and an Indoor Exploration Competition. #Robotics #IIG
1
3
3
302
AirLab retweeted
Shibo@ShiboZhaoSLAMJul 14
Excited to present our work "SuperMap: A Spatio-Temporal SLAM System for Visual-Language Navigation" at RSS 2026! SuperMap is a living spatial memory for embodied AI — it perceives the world, remembers its evolution, and supports reasoning and action. Perceive → Remember → Reason → Act 🌍 Project Page: superodometry.com/supermap #RSS2026 #Robotics #SLAM #EmbodiedAI #SpatialAI #CMURobotics
15
66
4
401
30,442
AirLab retweeted
Parv Kapoor
@ParvkprJul 6
Working on robotics and attending ICML 2026? (and also overwhelmed by the number of sessions like me?) I made a website to help me navigate my first ICML with an emphasis on robotics papers! Link: parvkpr.github.io/robotics-a… Sharing it here so people can use it. Check it out and let me know if you want me to add your paper/have any feedback! Oh and also come checkout our poster on safety guardrails for navigation VLAs! Link: constrained-robot-fms.github… We’ll be presenting how constrained decoding can enforce safety requirments for robot navigation models at runtime, without retraining. 📍 Hall A #400 🗓️ Tue, July 7 ⏰ 10:30–11:30 AM KST #icml #robotics #physicalai – at Seoul, Republic of Korea
3
8
45
3,148
AirLab retweeted
Cherie Ho@hocherie1Jul 2
What can different navigation domains (e.g. offroad, AV, humanoid, aerial, quadruped, digital) learn from each other? 🎉 Excited to announce the Workshop on “Bridging Perspectives in Navigation” @ IROS 2026 (Pittsburgh, 9/27/2026). Submit your paper by August 21! 👇
1
4
1
8
1,104
Proud to see Co-Me accepted to CVPR 2026 🎉 Now supporting MapAnything 1.1, Depth Anything 3, and Pi3 - and 2× faster than the original, up to 21.5× speedup on long VGGT sequences. Congrats to the team!
Yutian Chen
@YutianChen03May 18
All your favorite 3D models — now faster with Co-Me. 🎉 Accepted to CVPR 2026, Co-Me now supports more 3D foundation models: MapAnything 1.1, Depth Anything 3, and Pi3. Same simple confidence-guided token merging idea — now accelerating even more 3D reasoning models. 👇
4
12
3,391
AirLab retweeted
Parv Kapoor
@ParvkprMay 12
I’m excited to share that I successfully defended my Ph.D. thesis on Specification-Driven Planning for Safe Autonomy! I’m deeply grateful to my committee Sebastian Scherer, Changliu Liu, Karen Leung and Eunsuk Kang for their time and guidance throughout this journey. More in 🧵
5
1
1
38
6,445
Meet KinDER — a stress test for robot physical reasoning. All 13 methods failed 😈 🌎 25 environments ♾️ Infinite tasks 🏋️ Gymnasium API ⚒️ Over 20 parameterized skills 🪧 Human demonstrations 📊 13 baselines (planning and learning) From @Princeton @CMU_Robotics @ICatGT @CambridgeMLG @nvidia @MIT_CSAIL 🧵 1/n
1
25
7
132
37,225
I'm excited to share that RAVEN was accepted to ICRA 2026! Paper: arxiv.org/abs/2509.23563 Website: raven-semantic.github.io Collaboration with @OmarAlama, Dmytro Kurdydyk, John Keller, @Nik__V__ , Wenshan Wang, @ybisk , @smash0190 See you in Vienna!

RAVEN: Resilient Aerial Navigation via Open-Set Semantic Memory...

Aerial outdoor semantic navigation requires robots to explore large, unstructured environments to locate target objects. Recent advances in semantic navigation have demonstrated open-set...

arxiv.org
Seungchan Kim@seungchankim252 Oct 2025
We introduce RAVEN, a 3D open-set memory-based behavior tree framework for aerial outdoor semantic navigation. RAVEN not only navigates reliably toward detected targets, but also performs long-range semantic reasoning and LVLM-guided informed search
1
8
27
3,249
#IROS2026 will convene in Pittsburgh from Sept 27 – Oct 1! As one of the largest & most dynamic robotics conferences, IROS brings together world-leading researchers, educators, govt. leaders, startups, industry innovators, practitioners, & investors👇 2026.ieee-iros.org/
16
98
8,169
Fast & light 2D and 3D zero-shot open-vocabulary semantic segmentation is here 🚀🪶!! Meet RADSeg: - 6-30% mIoU improvement while being 3.95x faster and using 2.5x fewer parameters. - Outperforms combinations of huge vision models (850-1350M) with just 105M ! 💡The key is building on the agglomerative model, RADIO, and improving spatial consistency.
6
22
4
150
22,058
We are honored to share that Super Odometry is now published in @ScienceRobotics and featured as a highlight article! 🚀 This work rethinks the SLAM paradigm: true resilience should not rely solely on external perception—it should begin from within. science.org/stoken/author-to… #SLAM
8
6
1
36
5,129
Human peripheral vision reduces detail in out-of-focus areas. This “annoying” feature saves massive computation while preserving spatial cues. And for the most human-like artifact we build—ROBOT—that efficiency matters. Checkout our recent work:👉🔗 co-me-tokens.github.io
2
6
534
🧵[3/n] Co-Me distills a tiny confidence predictor that identifies low-confidence regions before most layers even run, letting us merge those tokens and cut redundant compute. ✨That’s it — simple and effective.
1
1
1
8
1,440
🧵[2/n] We noticed the model burns most of its compute on uncertain regions that are later discarded by downstream tasks. Can we avoid wasting this computation?
1
2
8
847
More and more visual-geometric transformers are coming out, like VGGT and MapAnything—but pushing them to real robot is still challenging. What if we could make them 10× faster? 👉🔗co-me-tokens.github.io ⚡Co-Me speeds up VGGT and MapAnything by up to 11.3x and 7.2x. How? 👇🧵
1
20
2
96
16,434
Load more