Marco Pavone
@drmapavone
Followers
4K
Following
74
Media
14
Statuses
203
Prof @Stanford, Distinguished Research Scientist and AV research lead @nvidia. PhD from @MITAeroAstro. Robotics, autonomous systems, AI. Opinions are my own.
Stanford, CA USA
Joined November 2018
🚀 First demonstration of learning-accelerated trajectory optimization in space! Our team used a neural network to warm-start trajectory optimization for the @NASA's Astrobee free-flying robot on-board the @Space_Station, cutting solver iterations by up to 60% while maintaining
4
28
153
Honored and humbled to receive the 2026 @IEEEorg Kiyo Tomiyasu Technical Field Award for advancing the science and practice of robot autonomy — on Earth and in space. Even more special to share this announcement with two pioneers of robotics! More here:
ieee-ras.org
Big #robotics and autonomy news - @ETH_en's Roland Siegwart, @Stanford's Marco Pavone, and @PennEngineers and @PennEngAI's George Pappas are receiving 2026 @IEEEorg Technical Field Awards! Get more details in this @ieeeras article: #IEEEAwards2026 #TFAs
2
3
33
We’re now accepting applications for the 2026–2027 NVIDIA Graduate Fellowships! If you’re passionate about advancing cutting-edge reasoning models for Physical AI applications 🚗🤖, apply here: — and be sure to select “Autonomous Vehicles.”. @NVIDIAAI.
1
26
104
Work led by @milanganai, in collaboration with @RohanSinhaSU @agiachris Daniel Morton. Accepted as oral @corl_conf.
0
0
2
Worried about Out-of-Distribution failures in robotics? Our @corl_conf paper FORTRESS presents a novel framework for real-time, semantically safe fallback strategies—bridging open-world reasoning with dynamics-aware planning. 📝 🌐
2
2
8
Work led by @jackyk02, with a phenomenal set of collaborators: @agiachris, @RohanSinhaSU,.@MatthewFoutter, @depetrol1, @istoica05,.@Azaliamirh.
0
1
1
Our work on test-time scaling for robotics has been accepted to @corl_conf! We show that scaling test-time compute via a generate-and-verify paradigm offers a practical and effective path toward building general-purpose robotics foundation models.
✨ Test-Time Scaling for Robotics ✨. Excited to release 🤖 RoboMonkey, which characterizes test-time scaling laws for Vision-Language-Action (VLA) models and introduces a framework that significantly improves the generalization and robustness of VLAs!. 🧵(1 / N). 🌐 Website:
2
12
93
Check out our #IROS2025 work on robot safety! We show low-latency teleop up to the limits of the hardware's capabilities, all while enforcing hundreds of CBF constraints at kilohertz control rates. 📄 🌐 With @danielpmorton
1
19
112
As robot autonomy becomes more data-driven, choosing which data to train on is critical—but current methods are mostly clunky and heuristic. With CUPID, we take a principled step forward using influence functions for smarter data curation. 📄 Paper:
arxiv.org
In robot imitation learning, policy performance is tightly coupled with the quality and composition of the demonstration data. Yet, developing a precise understanding of how individual...
What makes data “good” for robot learning? We argue: it’s the data that drives closed-loop policy success!. Introducing CUPID 💘, a method that curates demonstrations not by "quality" or appearance, but by how they influence policy behavior, using influence functions. (1/6)
0
3
12
We’re hiring! The new Sustainable Mobility Center at @Stanford—co-directed by @RamRajagopal_ and me—is seeking a Managing Director. Join us in shaping a future where mobility is green, safe, accessible & equitable—from ground to air. Apply now! 👇.
1
1
5
Can we use simulation to validate Physical AI? Yes—with far fewer real-world tests. We propose a control variates–based estimation framework that pairs sim & real data to dramatically cut validation costs. #AI #Robotics #Sim2Real". Paper: @NVIDIADRIVE.
1
17
37
RT @NVIDIADRIVE: .@drmapavone (@NVIDIA, @Stanford) joins the latest NVIDIA AI Podcast to break down how AI & simulation are critical for #A….
0
9
0
To learn more about Halos:. Web: Video: Blog: AV Safety Day: Podcast:
youreverydayai.com
You ever autonomously land a robot on Mars? 🪐 Marco Pavone has helped do just that. Marco is NVIDIA's Director, Autonomous Vehicle Research. His next challenge? Bring true autonomy to vehicles on...
0
1
2
At #GTC2025, Jensen unveiled Halos, a comprehensive safety system for AVs and Physical AI. Halos integrates numerous technologies developed by my team @nvidia, and I was thrilled to help coordinate its launch alongside Riccardo Mariani and many amazing colleagues @NVIDIADRIVE.
1
11
30
Check out our latest work on #robotics safety, where we propose a CBF-derived safety filter, which can handle hundreds of simultaneous constraints while retaining real-time control rates. Great work by @danielpmorton @StanfordEng.
Introducing one of the fastest and safest robot controllers, for operational space and hierarchical tasks. Deploy your learned policies, or teleoperate your robot confidently with OSCBF. Website: Preprint: With @drmapavone
0
4
29
For the first time ever, @nvidia is hosting an AV Safety Day at GTC - a multi-session workshop on AV safety. We will share our latest work on safe AV platforms, run-time monitoring, safety data flywheels, and more! #AutonomousVehicles #AI at #GTC25 . ➡️
0
15
32
It was a pleasure and a honor to instruct the @usairforce Test Pilot School on the foundations of robot autonomy and physical AI: @StanfordEng.
engineering.stanford.edu
The two-week Test of AI & Emerging Technologies course helped build foundational skills in the design, testing, and control of AI-enabled systems.
0
2
11
Just published in @Nature_NPJ: we present a data-driven methodology for the high-performance control of continuum robots, including "squishy" robots :). Paper: Great collaboration with @ETH_en @GeorgeHallerETH.
Data-driven, nonlinear, SSM-based model-predictive control of soft robots outperforms other model reduction approaches by a large margin, as shown in Collaborators at @stanford and @ETH_en: @heateralora, @mattiacenedese, and @drmapavone
0
4
20
AI4I, the Italian Institute of Artificial Intelligence for Industry (, has launched an international call for Heads of R&D Units (. This is a unique opportunity to shape the AI roadmap in Italy and beyond! @FabioPammolli.
1
4
13