Kasra Khosoussi

About

Kasra Khosoussi is a leading researcher in robotics and sensor networks, specializing in simultaneous localization and mapping (SLAM) for extreme environments. His work addresses fundamental challenges in estimation-over-graphs, collaborative SLAM, and resource-aware autonomy. Khosoussi made major contributions to the DARPA Subterranean Challenge, co-authoring the highly cited survey "Present and Future of SLAM in Extreme Environments" (176 citations), which charted the path for SLAM in underground tunnels, caves, and even Martian lava tubes. He pioneered the concept of separability in SLAM, showing how to exploit the linear structure of measurement functions for more efficient back-end optimization. His research on reliable graphs for SLAM (61 citations) established new theoretical connections between graphical representations and estimation-theoretic performance. Khosoussi also developed near-optimal, provably guaranteed algorithms for distributed inter-robot loop closure detection, addressing critical resource constraints in collaborative missions. His work on energy-aware information gathering for heterogeneous robot teams further demonstrates his commitment to practical, deployable solutions. With over 400 total citations and a consistent focus on both theory and real-world validation, Khosoussi is shaping the future of autonomous navigation in the most challenging environments on Earth and beyond.

Research Focus

Key Achievements

Top Papers

1. 1
   Present and Future of SLAM in Extreme Environments: The DARPA SubT Challenge

   176 citations · 2023
2. 2
   Reliable Graphs for SLAM

   61 citations · 2019
3. 3
   Present and Future of SLAM in Extreme Underground Environments

   38 citations · 2022
4. 4
   A resource-aware approach to collaborative loop-closure detection with provable performance guarantees

   27 citations · 2020
5. 5
   Near-Optimal Budgeted Data Exchange for Distributed Loop Closure Detection

   27 citations · 2018
6. 6
   A Sparse Separable SLAM Back-End

   17 citations · 2016
7. 7
   Dimensionality reduction for point feature SLAM problems with spherical covariance matrices

   16 citations · 2014
8. 8
   Exploiting the Separable Structure of SLAM

   14 citations · 2015
9. 9
   Tree-connectivity: Evaluating the graphical structure of SLAM

   13 citations · 2016
10. 10
    Energy-Aware, Collision-Free Information Gathering for Heterogeneous Robot Teams

    11 citations · 2023

Key Collaborators

Contact & Links