Agile Sensing and Intelligence Group (ASIG)

Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence
Faculty of Science and Engineering
University of Groningen, The Netherlands

PI: Kailai Li | Contact: kailai.li[at]rug.nl

News
  • 2025-08: Kailai gave a seminar On Embodied Sensor Intelligence in Mobile Robotics at Linköping University.
  • 2025-08: The paper IRIS: An Immersive Robot Interaction System contributed by Qihao and Kailai is now accpeted by CoRL 2025. Check out our project website!
  • 2025-07: The paper Solving 3D Visual Grounding as Constraint Satisfaction Problems by Qihao and Kailai is now accpeted by BMVC 2025. Check out our project website!
  • 2025-06: Kailai gave a talk on Trustworthy Mobile Sensing for Embodied Intelligence during the first meeting of the Focusgroup High Tech Sensoring hosted by Innovation Cluster Drachten. Check out the news here!
  • 2025-06: Kailai received the NRO Comenius Teaching Fellows grant! Check out news page of University of Groningen and more introduction by our Faculty.
  • 2025-06: Kailai's single-authored article is accepted by IEEE Transactions on Aerospace and Electronic Systems. Check out Early Access!
  • 2025-05: Qihao and Kailai contributed to Co-NavGPT, the first multi-robot visual navigation system using vision-language models with real-world demonstration. Check out the Project Page!
  • 2025-04: We presented and demonstrated our research for the delegation from the Ministry for Science and Culture of Niedersachsen, Germany. Here is the news!
  • 2025-04: Ziyu and Kailai released RESPLE, the first recurisve spline estimator for LiDAR-based odometry. Check out our Project Page!
  • 2025-04: We joined the first National Congress Autonomous Systems in Drachten. Check out the local news here!
  • 2025-02: Qihao and Kailai contributed to a new system for immersive robot interaction. Check out IRIS here!

The Agile Sensing and Intelligence Group (ASIG), led by Kailai Li, is a research team based at the University of Groningen (RUG) in the Netherlands. We are broadly interested in enabling full-stack autonomy for mobile robotic systems in the domain of embodied AI, including agile and trustworthy sensing, inference, learning and control. We constantly look for strong candidates for PhD/postdoc/internship/thesis. Shoot us an email with a brief intro if you are interested, and we will start from this!
Research Highlights
* indicates equal contribution.

RESPLE: Recursive Spline Estimation for LiDAR-Based Odometry
Ziyu Cao, William Talbot, Kailai Li
arXiv preprint, arXiv:2504.11580, 2025
arXiv / Code / Video / Website

On Embedding B-Splines in Recursive State Estimation
Kailai Li
IEEE Transactions on Aerospace and Electronic Systems, 2025
arXiv / Paper / Video

Solving 3D Visual Grounding as Constraint Satisfaction Problems
Qihao Yuan, Kailai Li*, Jiaming Zhang*
The British Machine Vision Conference (BMVC), 2025

IRIS: An Immersive Robot Interaction System
Xinkai Jiang, Qihao Yuan, Enes Ulas Dincer, Hongyi Zhou, Ge Li, Xueyin Li, Julius Haag, Nicolas Schreiber, Kailai Li, Gerhard Neumann, Rudolf Lioutikov
The Conference on Robot Learning (CoRL), 2025

Co-NavGPT: Multi-Robot Cooperative Visual Semantic Navigation using Vision Language Models
Bangguo Yu, Qihao Yuan, Kailai Li, Hamidreza Kasaei, and Ming Cao
arXiv preprint, arXiv:2310.07937, 2025
arXiv / Code / Video / Website

A Third-Order Gaussian Process Trajectory Representation Framework with Closed-Form Kinematics for Continuous-Time Motion Estimation
Thien-Minh Nguyen, Ziyu Cao, Kailai Li, William Talbot, Tongxing Jin, Shenghai Yuan, Timothy D. Barfoot, Lihua Xie
arXiv preprint, arXiv:2410.22931, 2024

Continuous-Time Ultra-Wideband-Inertial Fusion
Kailai Li, Ziyu Cao, Uwe D Hanebeck
IEEE Robotics and Automation Letters, vol. 8, no. 7, pp. 4338-4345, July 2023
arXiv / Paper / Code / Video

Towards High-Performance Solid-State-LiDAR-Inertial Odometry and Mapping
Kailai Li, Meng Li, Uwe D. Hanebeck
IEEE Robotics and Automation Letters, vol. 6, no. 3, pp. 5167-5174, July 2021
arXiv / Paper / Code / Video

Highly Parallelizable Plane Extraction for Organized Point Clouds Using Spherical Convex Hulls
Hannes Möls, Kailai Li, Uwe D. Hanebeck
Proceedings of the 2020 IEEE International Conference on Robotics and Automation (ICRA), Paris, France
© 2025 Kailai Li, Qihao Yuan. All rights reserved. Using, copying, and redistributing the code in any form can be performed only under permission.