CMU Robotics Institute

Pioneering the future of robotics since 1979. We’re transforming industries and everyday life through cutting-edge innovation and world-class education.

[CMU Robotics Institute @CMU_Robotics]

Team Chiron is down in Disaster City, Texas competing in the DARPA Triage Challenge finals! #TartanProud

They're using AI and sensors to identify people, assess their conditions & relay info to emergency responders to support critical triage decisions.

https://t.co/Fjqu1hj2gZ

[Kaihua Chen @kaihuac5]

Why do long generated videos drift? Each new chunk only sees the last few frames, so errors pile up.

What if every frame could see the whole video?

Long, camera-controlled videos from a single image 🧵

[CMU Robotics Institute @CMU_Robotics]

At CMU's Robotics Innovation Center, more than 50 labs and working groups will chase breakthroughs that will reshape how robots operate on land, underground, in the air and deep beneath the water’s surface.

Take a look inside. 👇

https://t.co/LvcanNLHg4

[CMU Robotics Institute @CMU_Robotics]

Robots just got better at handling ropes and cables! 🤖🪢

With "Wiggle and Go," a robot wiggles a rope/cable while a camera tracks the wave. Computer vision + AI models use that motion to estimate the rope's physical properties for precise manipulation!

https://t.co/Q711pi512R

[Guanya Shi @GuanyaShi]

Launching a new humanoid learning course at @CMU_Robotics in Spring 2027!

Every team will get its own (small) humanoid robot for hands-on labs.

Will open-source everything (lecture slides, codes). Stay tuned!

[Micah Nye ✈️ CoRL '26 @micahnye31]

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

[zeji yi @ZejiYi]

Common belief: Robot policies need continuous action heads; discrete actions are 𝐥𝐞𝐬𝐬 𝐧𝐚𝐭𝐢𝐯𝐞 𝐚𝐧𝐝 𝐥𝐞𝐬𝐬 𝐩𝐫𝐞𝐜𝐢𝐬𝐞.

❗We find policies w/ the simplest discrete representations 𝐦𝐚𝐭𝐜𝐡 𝐨𝐫 𝐛𝐞𝐚𝐭 continuous ones—in sim & real, in single-step & diffusion/flow settings.

Here's why 🧵

[CMU Robotics Institute @CMU_Robotics]

@andrea_bajcsy is on an absolute roll – She's been named a 2026 Packard Fellow for Science and Engineering!

Awarded by the David and Lucile Packard Foundation, it provides early-career faculty 5 yrs of flexible funding to pursue bold, innovative work.

https://t.co/AOjyzbHQZ8

[CMU Robotics Institute @CMU_Robotics]

@andrea_bajcsy has been named a 2026 AI2050 Early Career Fellow alongside @LTIatCMU's @AkariAsai and @dan_fried!

The AI2050 initiative supports researchers working on AI and how it can benefit society in the coming decades. Congratulations to all! 👏

https://t.co/QrRPAdIxoD

[Yilin Wu ✈️ CoRL 2026 @YilinWu11]

What to remember in the past to act—spatial, temporal or motion details?

We often assume what’s useful, but that’s hard to know in advance.

Meet IMPRINT 🧠: retain rich memory first, then learn to use it for control. Compact latents keep inference fast as history grows. 🧵 1/10

[Laude Institute @LaudeInstitute]

“As educators ourselves in a classroom, we need to adapt our strategy to make sure students understand and learn. That’s a critical capability in ARISTOS.”

Work could look completely different in ten years. @RamananDeva, @ChangliuL, Raj Reddy, Katia Sycara and @junyanz89 are building an open-source platform for training tomorrow's skilled tradespeople. This summer, @ChrisRytting and team stopped by @CarnegieMellon to hear how advances in computer vision and video generation are enabling a tool that, like a good teacher, adapts as people learn.

More on the Moonshot: https://t.co/gD8S0jTDLH

[CMU Kenneth C. Griffin School of Computer Science @GriffinCMU]

Placing a peg in a hole is child’s play — until it's 22,000 miles in space! 🛰️

@CMU_Robotics and @northropgrumman are teaching space robots how to dock, refuel, and fix old satellites, ending the days of single-use spacecraft: https://t.co/eoUqznQeMv

[Nie (Elon) Lin @nie__lin]

Bonus pic: Sprout settling in at CMU with its very own RI @CMU_Robotics mug ☕️🤖

[CMU Robotics Institute @CMU_Robotics]

As part of #IROS2026, hundreds of academics and industry leaders toured CMU's robotics + engineering facilities on Oct. 1.

They got an inside look at what CMU researchers are working on inside the Robotics Innovation Center, Mill 19 and @NREC_CMU! 👀 🧠

https://t.co/aeAUB9LdwN

[CMU Kenneth C. Griffin School of Computer Science @GriffinCMU]

Robots just got a lot more delicate! 🤖🤏

@CMU_Robotics researchers designed human-inspired robotic fingertips with silicone skin & tiny fingernails. By combining force & sound sensors, the hands can handle fragile items without crushing them! #IROS2026

https://t.co/LONkPFfmnz

[Andrea Bajcsy @andrea_bajcsy]

I'm honored to be part of this amazing cohort of scientists! AI interacts with millions of people via screens, but the next step is interaction with the physical world via robots. Our @schmidtsciences project studies how robot "brains" can be safely deployed in the physical world

[CMU Kenneth C. Griffin School of Computer Science @GriffinCMU]

As part of Citadel founder and CEO Ken Griffin’s transformative investment, we’re now known as the Kenneth C. Griffin School of Computer Science! With this new support, we’re ready to ask bigger questions!
https://t.co/3BB8L3cl6S

[CMU Robotics Institute @CMU_Robotics]

Long-Horizon Adaptive Manipulation Planning (LAMP) helps robots plan not only where an object needs to go, but also how they can work together to get it there🤖🤝

MSR student and project co-lead Shuai Zhou presented this research at #IROS2026 yesterday!

https://t.co/1Q5LX6Xc3j

[CMU Robotics Institute @CMU_Robotics]

Humanoids can’t always just hit the brakes and power down 🤖🛑

CMU researchers and @Siemens developed PRISM, a new way to monitor when a humanoid can safely stop, helping robots know when to stop before things get risky! #IROS2026

https://t.co/IDFfb1e4Aw

[Ayush Jain @ayushjain1144]

1/ We introduce TrackEverything: a 3D point tracker that tracks all points across all frames of long videos (1000+ frames).

Our key idea is to tie computation to unique 3D scene content rather than redundant 2D pixels in a video.

https://t.co/NYHPTTg0Gr