Jumman Hossain

Research

Research focuses on reinforcement learning and embodied AI under uncertainty and physical constraints. Learned representations of motion cost, risk, and recoverability guide decisions in navigation and whole-body control.

Current work studies how to use demonstrations selectively for humanoid locomotion and manipulation, manage risk in language-guided navigation, and transfer policies from simulation to physical robots.

Education

• PhD candidate, Information Systems

  University of Maryland, Baltimore County

  2021 - present

  Advisor: Prof. Nirmalya Roy. Research in reinforcement learning, robot navigation, and reliable autonomy.

• MS, Artificial Intelligence and Machine Learning

  University of Maryland, Baltimore County

  2021 - 2023

• Bachelor of Engineering, Computer Science and Engineering

  Shahjalal University of Science and Technology

  2009 - 2013

  Specialization in machine learning.

Research experience

• Research Assistant

  Center for Research in Use-Inspired Cyber-Physical Systems (CYPRESS)

  University of Maryland, Baltimore County

  Baltimore, MD

  Aug 2025 – Present

• Research Assistant

  Center for Distributed Sensing and Autonomy (CARDS)

  University of Maryland, Baltimore County

  Baltimore, MD

  Aug 2022 – Aug 2025

• PhD Research Internship

  Stormfish Scientific Corporation

  Baltimore, MD

  May 2024 – Aug 2024

  Developed reinforcement learning models for navigation and connected ROS-based robots with AuroraXR and Unity simulations.

• Research Assistant

  Mobile, Pervasive and Sensor Computing Lab (MPSC)

  University of Maryland, Baltimore County

  Baltimore, MD

  Aug 2021 – Present

Industry experience

• Senior Software Engineer

  BJIT Limited

  Dhaka, Bangladesh

  Oct 2018 – Aug 2021

  Worked on the PockeTalk translation SDK, image translation integration, and the JAJA TV application.

• Software Engineer

  IPvision Canada Inc.

  Dhaka, Bangladesh

  Sept 2015 – Sept 2018

  Developed distributed cloud storage systems using OpenStack Swift.

• Software Engineer

  Eyeball Networks Inc.

  Dhaka, Bangladesh

  July 2014 – Aug 2015

  Developed the Android uGrow Smart Baby Monitor application for Philips Avent hardware.

Publications & manuscripts

1. CoGeL: Constraint-to-Geometry Learning from Demonstrations and Failures for Safe Long-Horizon Robot Navigation
   Jumman Hossain, Nirmalya Roy
   CoRL 2026
   Project overview ↗
2. Learning Anisotropic Value Geometry with Finsler Reinforcement Learning
   Jumman Hossain, Nirmalya Roy
   ICML 2026
   PaperProject overview ↗PDF
3. SERN: Bandwidth-Adaptive Cross-Reality Synchronization for Simulation-Enhanced Robot Navigation
   Jumman Hossain, Emon Dey, Snehalraj Chugh, Masud Ahmed, MS Anwar, Abu-Zaher Faridee, Jason Hoppes, Theron Trout, Anjon Basak, Rafidh Chowdhury, Rishabh Mistry, Hyun Kim, Jade Freeman, Niranjan Suri, Adrienne Raglin, Carl Busart, Timothy Gregory, Anuradha Ravi, Nirmalya Roy
   ICCCN 2026
   PaperProject overview ↗arXiv preprintVideo
4. QPRL: Learning Optimal Policies with Quasi-Potential Functions for Asymmetric Traversal
   Jumman Hossain, Nirmalya Roy
   ICML 2025
   PaperProject overview ↗PDF
5. QuasiNav: Asymmetric Cost-Aware Navigation Planning with Constrained Quasimetric Reinforcement Learning
   Jumman Hossain, Abu-Zaher Faridee, Nirmalya Roy, Jade Freeman, Timothy Gregory, Theron Trout
   ICRA 2025
   PaperProject overview ↗arXiv
6. TopoNav: Topological Navigation for Efficient Exploration in Sparse Reward Environments
   Jumman Hossain, Abu-Zaher Faridee, Nirmalya Roy, Jade Freeman, Timothy Gregory, Theron Trout
   IROS 2024
   PaperProject overview ↗arXivVideo
7. EnCoMP: Enhanced Covert Maneuver Planning with Adaptive Target-Aware Visibility Estimation using Offline Reinforcement Learning
   Jumman Hossain, Abu-Zaher Faridee, Nirmalya Roy, Jade Freeman, Timothy Gregory, Theron Trout
   ACSOS 2024
   PaperProject overview ↗arXiv
8. CoverNav: Cover Following Navigation Planning in Unstructured Outdoor Environment with Deep Reinforcement Learning
   Jumman Hossain, Abu-Zaher Faridee, Anjon Basak, Derrik Asher, Nirmalya Roy
   ACSOS 2023
   PaperProject overview ↗arXiv
9. SynchroSim: An Integrated Co-simulation Middleware for Heterogeneous Multi-robot System
   Emon Dey, Jumman Hossain, Nirmalya Roy, Carl Busart
   IEEE DCOSS 2022
   PaperProject overview ↗arXiv
10. GapNav: Margin-Aware Gap Entry and Traversal Control for Legged Robots
    Jumman Hossain, Snehalraj Chugh, Abu-Zaher Faridee, Nirmalya Roy
    Under review
    Project overview ↗

Ongoing research

• Reliable language-guided robot navigation. Studying how robots can follow language instructions while recognizing hazards and adapting their behavior in complex environments.
• Learning whole-body humanoid skills. Learning policies that combine locomotion and manipulation, with an emphasis on adapting demonstrated skills to physical constraints and new situations.

Teaching & mentoring

• Teaching. Teaching assistant at UMBC for IS 420, Database Application Development, and IS 620, Advanced Database Projects (2021-2024). Led lab sessions for undergraduate and graduate students.
• Mentoring. Mentored students through NSF Research Experiences for Undergraduates in 2022 and 2023, and MPS Data Science research at UMBC from 2024.

Technical experience

Research tools

PyTorch, JAX, Stable-Baselines3, RLlib, ROS 1/2, Isaac Sim/Lab, MuJoCo, Unity, Gazebo

Programming

Python, C/C++, Java, MATLAB, shell scripting

Robot platforms

Unitree G1, Boston Dynamics Spot, Clearpath Husky and Jackal, Ghost Robotics Vision 60, TurtleBot