Xusheng Luo

I'm currently a Posdoctoral Fellow at Intelligent Control Lab of Robotics Institute, Carnegie Mellon University, working with Dr. Changliu Liu, starting from April 2023. I received the Ph.D. degree in Mechanical Engineering and Materials Science from Duke University in December 2020, under the supervision of Dr. Michael M. Zavlanos. Prior to it, I received the B.S. and M.S. degrees in Aerospace Engineering from the Harbin Institute of Technology, China, in 2015 and 2017, respectively.

I’m currently on the academic job market! Please feel free to reach out if you think I’d be a good fit for your institution.

Email  /  Resume  /  Google Scholar  /  Github  /  LinkedIn

profile photo

News and Updates

  • Jul. 2025:
    Selected as ASME Dynamic Systems & Control Division (DSCD) Rising Star
  • Jul. 2025:
    We are organizing Workshop on Foundation Models for Control (FM4Control) at MECC 2025
  • May 2025:
    One paper accepted to T-RO
  • May 2025:
    Serving as Session Chair of ICRA 2025
  • May 2025:
    One paper accepted to ICRA Workshop on Public Trust in Autonomous Systems (PTAS)
  • May 2025:
    One paper accepted to ICRA Workshop on Robot Safety
  • Apr. 2025:
    One paper accepted to RSS 2025
  • Apr. 2025:
    One paper accepted to ACM Transactions on Cyber-Physical Systems (T-CPS)
  • Apr. 2025:
    One paper accepted to Conference on Computer Aided Verification (CAV) 2025
  • May 2024:
    One paper accepted to RA-L
  • Apr. 2024:
    Selected as NSF Rising Star in Cyber-Physical Systems (16.4% = 36/220)
  • Oct. 2023:
    One paper accepted to CoRL Workshop on Learning Effective Abstractions for Planning (LEAP)
  • Sep. 2023:
    One paper accepted to IROS Workshop on Formal Methods Techniques in Robotics Systems: Design and Control
  • Apr. 2023:
    Joined Intelligent Control Lab (ICL) as a Postdoctoral Fellow

Research

My research agenda is centered on building assured and scalable autonomy via logic, control, and learning by building on knowledge from the fields of system and control, machine learning/AI, and formal methods. My research philosophy is to leverage mathematical structure and data-informed analysis to establish new algorithms and theorems that make AI-enabled autonomy dependable in the real world. A recurring theme throughout my work is scalability: I strive to deliver solutions that handle richer task descriptions, high-dimensional sensor data, and ever larger teams of robots. These contributions organize into three thrusts:

  1. Formal, temporally extended task specifications: designing rigorous and expressive formal specification for a rich set of goals, constraints, and preferences that capture human instructions while remaining use-friendly (CDC 2020, T-RO 2022, T-RO 2025, Arxiv 2025).
  2. Correct-by-construction planning and control: automatically synthesizing provably-correct planners and controllers for multi-robot systems under high-level task specifications (CDC 2019, T-RO 2021, T-RO 2022, RA-L 2024, T-RO 2025, RSS 2025).
  3. Data-driven verification and certification: devising techniques that quantify and guarantee the safety and reliability of learning-enabled, safety critical autonomous systems (Automatica 2021, T-CPS 2025, CAV 2025).

Publications

Representative papers are highlighted (* denotes equal contribution).

Simultaneous Task Allocation and Planning for Multi-Robots under Hierarchical Temporal Logic Specifications
Xusheng Luo, Changliu Liu
IEEE Transaction on Robotics (TRO), 2025
ICRA Workshop on Robot safety, 2025
PDF / Video / Code
Hierarchical Temporal Logic Task and Motion Planning for Multi-Robot Systems
Zhongqi Wei*, Xusheng Luo*, Changliu Liu
Robotics: Science and Systems (RSS), 2025
PDF / Video / Code
safs_small Certifying Robustness of Learning-Based Keypoint Detection and Pose Estimation Methods
Xusheng Luo, Tianhao Wei, Simin Liu, Ziwei Wang, Luis Mattei-Mendez, Taylor Loper, Joshua Neighbor, Casidhe Hutchison, Changliu Liu
ACM Transaction on Cyber-Physical Systems (T-CPS), 2025
ICRA Workshop on Public Trust in Autonomous Systems (PTAS), 2025
PDF
safs_small ModelVerification. jl: a Comprehensive Toolbox for Formally Verifying Deep Neural Networks
Tianhao Wei, Luca Marzari, Kai S. Yun, Hanjiang Hu, Peizhi Niu, Xusheng Luo, Changliu Liu
International Conference on Computer Aided Verification (CAV), 2025
PDF / Code
NL2HLTL2PLAN: Scaling Up Natural Language Understanding for Multi-Robots Through Hierarchical Temporal Logic Task Representation
Shaojun Xu*, Xusheng Luo*, Yutong Huang, Letian Leng, Ruixuan Liu, Changliu Liu
CoRL Workshop on Learning Effective Abstractions for Planning (LEAP) , 2023
arXiv , 2024
PDF / Project Page
Decomposition-based Hierarchical Task Allocation and Planning for Multi-Robots under Hierarchical Temporal Logic Specifications
Xusheng Luo, Shaojun Xu, Ruixuan Liu, Changliu Liu
IEEE Robotics and Automation Letters (RA-L), 2024, with presentation at ICRA 2025
IROS Workshop on Formal Methods Techniques in Robotics Systems: Design and Control , 2023
PDF / Video / Code
safs_small Simulation-aided Learning from Demonstration for Robotic LEGO Construction
Ruixuan Liu, Alan Chen, Xusheng Luo, Changliu Liu
arXiv , 2023
PDF / Video
Temporal Logic Task Allocation in Heterogeneous Multi-robot Systems
Xusheng Luo, Michael M Zavlanos
IEEE Transactions on Robotics (T-RO), 2022
PDF / Extended version / Code
safs_small Formal Verification of Stochastic Systems with ReLU Neural Network Controller
Shiqi Sun, Yan Zhang, Xusheng Luo, Panagiotis Vlantis, Miroslav Pajic, Michael M Zavlanos
ICRA, 2022
PDF
safs_small An abstraction-free Method for Multi-robot Temporal Logic Optimal Control Synthesis
Xusheng Luo, Yiannis Kantaros, Michael M Zavlanos
IEEE Transactions on Robotics (T-RO), 2021
PDF / Code
safs_small An optimal Graph-Search Method for Secure State Estimation
Xusheng Luo, Miroslav Pajic, Michael M Zavlanos
Automatica, 2021
PDF

safs_small Human-in-the-loop Robot Planning with Non-contextual Bandit Feedback
Yijie Zhou, Yan Zhang, Xusheng Luo, Michael M Zavlanos
IEEE Conference on Decision and Control (CDC), 2021
PDF
safs_small Socially-aware Robot Planning via Bandit Human Feedback
Xusheng Luo*, Yan Zhang*, Michael M Zavlanos
ACM International Conference on Cyber-Physical Systems (ICCPS), 2020
PDF

Single-agent Indirect Herding of Multiple Targets using Metric Temporal Logic Switching
Duc Le, Xusheng Luo, Leila J. Bridgeman, Michael M Zavlanos, Warren E. Dixon
IEEE Conference on Decision and Control (CDC), 2020
PDF
safs_small Transfer Planning for Temporal Logic Tasks
Xusheng Luo, Michael M Zavlanos
IEEE Conference on Decision and Control (CDC), 2019
PDF

Academic Service

  • Journals reviewing:
    T-RO, T-ASE, T-CNS, TMECH, RA-L, J. Dyn. Syst. Meas. Control, L-CSS
  • Conferences reviewing:
    RSS, ICRA, IROS, ACC, ICCPS, UR, MECC
  • Session Chair:
    Verification and Formal Methods, ICRA 2025
  • Workshop Organizer:
    Foundation Models for Control (FM4Control): Bridging Language, Vision, and Control Workshop, MECC 2025