Jahir Sadik Monon

LGRC A308, UMass Amherst

Amherst, Massachusetts

Hello, I’m Jahir, a second-year MS/PhD student in Computer Science at the University of Massachusetts Amherst, advised by Dr. Donghyun Kim in the Dynamic and Autonomous Robotic Systems (DARoS) Lab.

I work on embodied intelligence for assistive navigation for blind and low-vision travelers: reinforcement learning and vision-language-action policies that operate under partial observability and within the memory, latency, and power constraints of onboard compute. Much of this is part of our lab’s guide dog robot project. I am also interested in multi-agent embodied collaboration and representation learning for robotic control, extending my earlier work on decentralized multi-agent RL.

Before UMass, I was a research assistant at CCDS, Independent University Bangladesh, where I worked on VLM-based agent-centric representations for RL with Dr. Riashat Islam (Mila, McGill University & Microsoft Research), and on multimodal reasoning and LLM-based multi-agent collaboration with Dr. Amin Ahsan Ali and Dr. AKM Mahbubur Rahman of CCDS, IUB and Muntasir Wahed of UIUC. I did my B.Sc. in Computer Science and Engineering at the University of Dhaka, graduating with the Dean’s Honor Award; my thesis with Dr. Md Mosaddek Khan was on decentralized multi-agent reinforcement learning.

recent news

updated Sep 9, 2026

Mar 01, 2026	Our paper GuideNav — my first as a graduate student — received an Honorable Mention (Systems Track, top 3.6% of accepted papers) at HRI 2026.
Jan 15, 2026	Honored to receive the Paul Utgoff Memorial Graduate Scholarship from the Manning College of Information and Computer Sciences, UMass Amherst.
Dec 05, 2025	Our paper GuideNav, a vision-only robotic navigation assistant for blind travelers, was accepted at HRI 2026.
Nov 06, 2025	Our paper BAPPA, a benchmark of agents, plans and pipelines for Text-to-SQL generation (with collaborators at CCDS), is out on arXiv.
Sep 02, 2025	Started my MS/PhD in Computer Science at UMass Amherst, joining the DARoS Lab with Dr. Donghyun Kim.

selected publications

NeurIPS

NavAble: A Large-Scale Dataset and Synthetic Data Generation Pipeline for Blind Navigation

Hochul Hwang^*, Jahir Sadik Monon^*, Soowan Yang^*, Sahil U. Patel, Anh N. H. Nguyen, Khoa Nguyen, Keshav Garg, Daniel Gage, Dawit Hordofaa, Anjna Anjna, Eshed Ohn-Bar, and Donghyun Kim

In NeurIPS Datasets and Benchmarks Track (under review), 2026

Bib Dataset

@inproceedings{hwang2026navable,
  title = {NavAble: A Large-Scale Dataset and Synthetic Data Generation Pipeline for Blind Navigation},
  author = {Hwang, Hochul and Monon, Jahir Sadik and Yang, Soowan and Patel, Sahil U. and Nguyen, Anh N. H. and Nguyen, Khoa and Garg, Keshav and Gage, Daniel and Hordofaa, Dawit and Anjna, Anjna and Ohn-Bar, Eshed and Kim, Donghyun},
  booktitle = {NeurIPS Datasets and Benchmarks Track (under review)},
  year = {2026},
}

HRI
GuideNav: User-Informed Development of a Vision-Only Robotic Navigation Assistant for Blind Travelers

Hochul Hwang, Soowan Yang, Jahir Sadik Monon, Nicholas A. Giudice, Sunghoon Ivan Lee, Joydeep Biswas, and Donghyun Kim

In Proceedings of the 21st ACM/IEEE International Conference on Human-Robot Interaction (HRI), 2026

Honorable Mention Abs arXiv Bib Dataset Website

While commendable progress has been made in user-centric research on mobile assistive systems for blind and low-vision (BLV) individuals, references that directly inform robot navigation design remain rare. To bridge this gap, we conducted a comprehensive human study involving interviews with 26 guide dog handlers, four white cane users, nine guide dog trainers, and one O&M trainer, along with 15+ hours of observing guide dog-assisted walking. After de-identification, we open-sourced the dataset to promote human-centered development and informed decision-making for assistive systems for BLV people. Building on insights from this formative study, we developed GuideNav, a vision-only, teach-and-repeat navigation system. Inspired by how guide dogs are trained and assist their handlers, GuideNav autonomously repeats a path demonstrated by a sighted person using a robot. Specifically, the system constructs a topological representation of the taught route, integrates visual place recognition with temporal filtering, and employs a relative pose estimator to compute navigation actions - all without relying on costly, heavy, power-hungry sensors such as LiDAR. In field tests, GuideNav consistently achieved kilometer-scale route following across five outdoor environments, maintaining reliability despite noticeable scene variations between teach and repeat runs. A user study with 3 guide dog handlers and 1 guide dog trainer further confirmed the system’s feasibility, marking (to our knowledge) the first demonstration of a quadruped mobile system retrieving a path in a manner comparable to guide dogs.
@inproceedings{hwang2026guidenav, title = {GuideNav: User-Informed Development of a Vision-Only Robotic Navigation Assistant for Blind Travelers}, author = {Hwang, Hochul and Yang, Soowan and Monon, Jahir Sadik and Giudice, Nicholas A. and Lee, Sunghoon Ivan and Biswas, Joydeep and Kim, Donghyun}, booktitle = {Proceedings of the 21st ACM/IEEE International Conference on Human-Robot Interaction (HRI)}, year = {2026}, }
AAMAS
Learning Heterogeneous Agent Collaboration in Decentralized Multi-Agent Systems via Intrinsic Motivation

Jahir Sadik Monon^*, Deeparghya Dutta Barua^*, and Md. Mosaddek Khan

In Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2025

Abs arXiv Bib PDF Code

Multi-agent Reinforcement Learning (MARL) is emerging as a key framework for various sequential decision-making and control tasks. Unlike their single-agent counterparts, multi-agent systems necessitate successful cooperation among the agents. The real-world deployment of these systems requires decentralized training and execution (DTE), diverse agents, and learning from infrequent environmental rewards. These challenges become more pronounced under partial observability and the lack of prior knowledge about agent heterogeneity. While notable studies use intrinsic motivation (IM) to address reward sparsity or cooperation in decentralized execution settings, those dealing with heterogeneity typically assume centralized training for decentralized execution (CTDE). To overcome these limitations, we propose the CoHet algorithm, which utilizes a novel Graph Neural Network (GNN) based intrinsic motivation to facilitate the learning of heterogeneous agent policies in fully decentralized settings, under the challenges of partial observability and reward sparsity. Evaluation of CoHet in the Multi-agent Particle Environment (MPE) and Vectorized Multi-Agent Simulator (VMAS) benchmarks demonstrates superior performance compared to the state-of-the-art in a range of cooperative multi-agent scenarios.
@inproceedings{monon2025cohet, title = {Learning Heterogeneous Agent Collaboration in Decentralized Multi-Agent Systems via Intrinsic Motivation}, author = {Monon, Jahir Sadik and Barua, Deeparghya Dutta and Khan, Md. Mosaddek}, booktitle = {Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems (AAMAS)}, year = {2025}, }

See the full list of publications.