Burhanuddin Shirose

Warehouse experiment, 60 m × 24 m, 50× speed

IROS 2025IEEE Trans. (TAP)

Connectivity-aware coverage path planning in unknown environments

CAP builds a coverage guidance graph online from LiDAR that records how explored and unexplored subareas connect. A hierarchical planner orders subareas with a global tour and covers each one locally, which removes the revisits that greedy frontier planners make. Tested in simulation and on Spot and wheeled robots in 60 m × 24 m warehouses.

Paper BibTeX

−20%total coverage time

−15%traversal in unknown space

5baselines compared

GESCE Figure 1: 3D maze with an information peak and the planned ergodic trajectory

Ergodic path through a cluttered maze

IROS 2024First author

Graph-based ergodic search in cluttered environments

Ergodic planners spend time where targets are likely, but treat obstacles as soft costs and can still collide. GESCE builds a graph of the free space and searches it with ergodicity as the heuristic, so paths are collision-free by construction.

Paper Full results

125benchmark scenarios

100%collision-free paths

5MAPF clutter maps

Reaching between tight spaces, 3× speed

IEEE RA-LIn preparation

Hierarchical motion planning for high-DoF snake robots

Reaching lets a snake robot anchor its tail and extend across gaps, turning it into a 16-DoF serial manipulator. BINSAT searches over Bézier-curve backbones in 6-D, then lifts each candidate to joint space with a trajectory optimizer that enforces whole-body collision and torque limits.

16→6planning dimensions

98%simulation success

16-DoFhardware deployment

Decentralized convoy, aerial view

GVSETS 2025Field deployment

Decentralized heterogeneous convoys and high-speed autonomy

A decentralized planning stack lets mixed teams of wheeled UGVs and Spot quadrupeds form, resize, and hold convoys without a central planner. Compact footprint geometry keeps collision checks fast enough for 20 Hz replanning at 6 m/s, and robots peel off as communication relays to keep the team linked to base.

MMPUG Project

6 m/sautonomous ground speed

20 Hzonline replanning

UGV+Spotmixed fleet

97.2× Speedup of the lazy ILP allocator, with min-max optimality preserved.

IEEE RA-LAAAI MAPF-W

Scalable multi-agent multi-objective ergodic search

Assigning agents to competing search objectives is combinatorial in team size. I cast allocation as clustering in Fourier space, warm-start it with an infinite-horizon approximation, and solve a lazy ILP that exploits the resulting structure.

97.2×faster allocation

min-maxoptimality kept

ILPlazy constraints

MuJoCo simulation (top) driving the hardware emulator (bottom)

Hardware-in-the-loopSpace robotics

Microgravity docking emulator

Four synchronized UR10e arms reproduce spacecraft proximity operations on the ground. A MuJoCo model computes free-floating and contact dynamics, velocity control on the arms tracks the simulated client and tool-tip states with sub-millimeter, sub-millisecond accuracy, and measured contact forces feed back into the simulation.

4× UR10esynchronized arms

<1 mmtracking accuracy

<1 mssynchronization

@inproceedings{shen2025cap, title = {{CAP}: A Connectivity-Aware Hierarchical Coverage Path Planning Algorithm for Unknown Environments using Coverage Guidance Graph}, author = {Shen, Zongyuan and Shirose, Burhanuddin and Sriganesh, Prasanna and Travers, Matthew}, booktitle = {2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)}, year = {2025}, month = oct, doi = {10.1109/IROS60139.2025.11247648}, }

@inproceedings{noren2025convoy, title = {Communication Network Construction Behaviors for Robotic Convoying}, author = {Noren, Charles and Chaudhary, Sahil and Shirose, Burhanuddin and Vundurthy, Bhaskar and Travers, Matthew}, booktitle = {Proceedings of the 2025 Ground Vehicle Systems Engineering and Technology Symposium (GVSETS)}, organization = {NDIA}, address = {Novi, MI}, year = {2025}, month = aug, }

@article{sriganesh2025stairs, title = {A Bayesian Modeling Framework for Estimation and Ground Segmentation of Cluttered Staircases}, author = {Sriganesh, Prasanna and Shirose, Burhanuddin and Travers, Matthew}, journal = {IEEE Robotics and Automation Letters}, volume = {10}, number = {5}, pages = {4164}, year = {2025}, month = may, doi = {10.1109/LRA.2025.3549662}, eprint = {2501.04170}, archiveprefix = {arXiv}, primaryclass = {cs.RO}, }

@inproceedings{shirose2024gesce, title = {{GESCE}: Graph-based Ergodic Search in Cluttered Environments}, author = {Shirose, Burhanuddin and Johnson, Adam and Vundurthy, Bhaskar and Choset, Howie and Travers, Matthew}, booktitle = {2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)}, pages = {7611--7616}, year = {2024}, month = oct, doi = {10.1109/IROS58592.2024.10802461}, }

@inproceedings{sriganesh2024subt, title = {Modular, Resilient, and Scalable System Design Approaches -- Lessons Learned in the Years after {DARPA} Subterranean Challenge}, author = {Sriganesh, Prasanna and Maier, James and Johnson, Adam and Shirose, Burhanuddin and Chandrasekar, Rohan and Noren, Charles and Spisak, Joshua and Darnley, Ryan and Vundurthy, Bhaskar and Travers, Matthew}, booktitle = {IEEE ICRA Workshop on Field Robotics}, year = {2024}, month = apr, eprint = {2404.17759}, archiveprefix = {arXiv}, primaryclass = {cs.RO}, }

@inproceedings{noren2024vegetation, title = {An Interaction-Aware Two-Level Robotic Planning and Control System for Vegetation Override}, author = {Noren, Charles and Vundurthy, Bhaskar and Scherer, Sebastian and Travers, Matthew and Shirose, Burhanuddin}, booktitle = {Proceedings of the International Society for Terrain-Vehicle Systems (ISTVS) Conference}, year = {2024}, }

@inproceedings{vundurthy2024moes, title = {Generalized Multi-Agent Multi-Objective Ergodic Search}, author = {Vundurthy, Bhaskar and Gutow, Geordan and Srinivasan, Akshaya and Xu, A. and Shirose, Burhanuddin and others}, booktitle = {AAAI Workshop on Multi-Agent Path Finding}, year = {2024}, }

@article{shirose2022brake, title = {Robotic Arm for Brake Performance Testing}, author = {Shirose, Burhanuddin and Yadav, Kunal and Meenatchi, L. S. and Vedhanarayan, K.}, journal = {Journal of Physics: Conference Series (RoAI 2021)}, publisher = {IOP Publishing}, volume = {2251}, number = {1}, pages = {012002}, year = {2022}, month = apr, doi = {10.1088/1742-6596/2251/1/012002}, }

@inbook{premkumar2022tceres, title = {T-Ceres: An Automated Machine for Any T-Shirt to Bag Conversion}, author = {Premkumar, S. and Prakash, Yash and Shirose, Burhanuddin and Dhivakar, K. and Kapur, Mayank and Puthiyavan, L. N. and Arul, Ssmrithi}, publisher = {Springer}, pages = {247--257}, year = {2022}, month = jan, isbn = {978-981-19-0295-6}, doi = {10.1007/978-981-19-0296-3_22}, }

@inproceedings{kizor2021rov, title = {Design of a Remotely Operated Vehicle ({ROV}) for Biofoul Cleaning and Inspection of Variety of Underwater Structures}, author = {V, Nandha Kizor and Shirose, Burhanuddin and Adak, Mainak and Kumar, Mitesh and J, Sudarsana Jayandan and Srinivasan, Arun and Muhammad, Raashid Sheikh}, booktitle = {2021 9th RSI International Conference on Robotics and Mechatronics (ICRoM)}, pages = {451--457}, publisher = {IEEE}, year = {2021}, doi = {10.1109/ICRoM54204.2021.9663518}, }

Burhanuddin ShiroseMotion planning for constrained and multi-agent robots.

01Selected research