Luca Carlone

About

Luca Carlone is a professor at the Massachusetts Institute of Technology in the Department of Aeronautics and Astronautics. His research interests include nonlinear estimation, numerical and distributed optimization, learning and probabilistic inference, applied to sensing, perception, and decision making in single and multi-robot systems. He specializes in the design of certifiable perception algorithms for high-integrity autonomous systems and the development of algorithms and systems for real-time 3D scene understanding on mobile robotics platforms operating in the real world. He holds a Ph.D. from the Polytechnic University of Turin, earned in 2012, and has completed additional master's degrees from the Polytechnic University of Turin and Milan, both with highest honors. His academic background also includes a B.S. from the Polytechnic University of Turin. Carlone has held various positions at MIT, including Boeing Career Development Associate Professor, Sloan Research Fellow, and Raymond L. Bisplinghoff Faculty Fellow. His previous roles include postdoctoral fellow at Georgia Tech and visiting scholar positions at the University of California Santa Barbara and the University of Zaragoza. He is a senior member of the IEEE and an associate fellow of the AIAA. His contributions have been recognized with numerous awards, including the Outstanding Systems Paper Award at RSS 2024, the IEEE Transactions on Robotics King-Sun Fu Memorial Best Paper Award in 2023, and the AIAA…

Research topics

• Computer Science
• Artificial Intelligence
• Human–computer interaction
• Machine Learning
• Mathematical optimization
• Algorithm
• Mathematics
• Geography
• Engineering
• Systems engineering

Selected publications

• TEASER: Fast and Certifiable Point Cloud Registration

  IEEE Transactions on Robotics · 2020 · 797 citations

  Senior authorCorresponding

  We propose the first fast and certifiable algorithm for the registration of two sets of three-dimensional (3-D) points in the presence of large amounts of outlier correspondences. A <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">certifiable algorithm</i> is one that attempts to solve an intractable optimization problem (e.g., robust estimation with outliers) and provides readily checkable conditions to verify if the returned solution is optimal…

  DOI

• NeBula: Quest for Robotic Autonomy in Challenging Environments; TEAM\n CoSTAR at the DARPA Subterranean Challenge

  arXiv (Cornell University) · 2021 · 105 citations

  This paper presents and discusses algorithms, hardware, and software\narchitecture developed by the TEAM CoSTAR (Collaborative SubTerranean\nAutonomous Robots), competing in the DARPA Subterranean Challenge.\nSpecifically, it presents the techniques utilized within the Tunnel (2019) and\nUrban (2020) competitions, where CoSTAR achieved 2nd and 1st place,\nrespectively. We also discuss CoSTAR's demonstrations in Martian-analog surface\nand subsurface (lava tubes) exploration. The paper introduces…

  PublisherOA PDFDOI

• Shonan Rotation Averaging: Global Optimality by Surfing SO(p) &lt;sup&gt;n&lt;/sup&gt;

  Lecture notes in computer science · 2021 · 60 citations

  Senior authorCorresponding
  DOI

• Handbook of Dynamic Data Driven Applications Systems

  Springer eBooks · 2022 · 39 citations

  DOI

• PyPose: A Library for Robot Learning with Physics-based Optimization

  2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 2023 · 34 citations

  Deep learning has had remarkable success in robotic perception, but its data-centric nature suffers when it comes to generalizing to ever-changing environments. By contrast, physics-based optimization generalizes better, but it does not perform as well in complicated tasks due to the lack of high-level semantic information and reliance on manual parametric tuning. To take advantage of these two complementary worlds, we present PyPose: a robotics-oriented, PyTorch-based library that combines deep…

  DOI

Recent grants

• CAREER: Certifiable Perception for Autonomous Cyber-Physical Systems

  NSF · $580k · 2021–2026

Frequent coauthors

• Yun Chang

  88 shared

• Sertaç Karaman

  Massachusetts Institute of Technology

  81 shared

• Jingnan Shi

  76 shared

• Heng Yang

  67 shared

• Antoni Rosinol

  Stanford University

  49 shared

• Nathan Hughes

  44 shared

• Allan Axelrod

  University of Pittsburgh

  42 shared

• Frank Dellaert

  39 shared

Labs

• Human-System CollaborationPI

Awards & honors

• Outstanding Systems Paper Award at the Robotics: Science and…
• IEEE Transactions on Robotics King-Sun Fu Memorial Best Pape…
• AIAA Aeronautics and Astronautics Advising Award (2022)
• Best Student Paper Award at the IEEE/RSJ International Confe…
• Outstanding Associate Editor Award, International Conference…

Similar researchers at Massachusetts Institute of Technology

• Olivier L. de Weckh-52
• Edward F. Crawleyh-44
• Hamsa Balakrishnanh-37