News
About
I am an Assistant Professor in Computing Science at Simon Fraser University and director of the Autonomous Intelligence and Robotics (AIRob) lab.
My interests are mainly in artificial intelligence, robotics, and machine learning. Specifically, I am interested in topics on automated planning, multi-agent/robot systems, spatio-temporal and constraint reasoning, and applications of probabilistic methods and other topics related to graphs, combinatorial optimization, and algorithms.
Research Opportunities
I am always looking for self-motivated students at all levels. See my research highlights here or watch my AAAI-21 New Faculty Highlights talk below to learn more about my research.
If you are interested in working with me on AI, robotics, and multi-agent/robot systems, please mention my name in your application to the SFU CS graduate program. Applicants should also refer to the SFU CS graduate program page for more information on the admission requirements and application deadlines. Eligible students with only a bachelor's degree are encouraged to apply directly to the PhD program.
The SFU main campus is located on the Burnaby Mountain, 12 miles from downtown Vancouver.
Recent Service
Conference and Workshop Organization
- Co-Chair, International Symposium on Combinatorial Search (SoCS) 2021
- Systems Demo Co-Chair, International Conference on Automated Planning and Scheduling (ICAPS) 2021
- Co-Chair, 3rd International Workshop on Multi-Agent Path Finding at IJCAI 2019
Conference Area Chair and (Senior) Program Committee Member
- AAAI Conference on Artificial Intelligence (AAAI) 2022, 2021, 2020
- International Joint Conference on Artificial Intelligence (IJCAI) 2022, 2021 (SPC), 2020, 2019
- International Conference on Autonomous Agents and Multiagent Systems (AAMAS) 2021, 2020, 2019
- International Conference on Automated Planning and Scheduling (ICAPS) 2022, 2021
- International Conference of the Florida Artificial Intelligence Research Society (FLAIR) 2022, 2021
- ACM/SIGGRAPH conference on Motion, Interaction and Games (MIG) 2021
- International Symposium on Multi-Robot and Multi-Agent Systems (MRS) 2021 (AC)
- International Symposium on Combinatorial Search (SoCS) 2022, 2020
Journal Editing
- Guest Editor, SN Applied Sciences Topical Collection on Distributed Mobile Robotic Systems
Teaching
- CMPT 417/827: Intelligent Systems (Fall 2021, Spring 2021, Spring 2020)
Education
- 2014 to 2019, Ph.D. Computer Science, University of Southern California
- 2012 to 2014, M.Sc. Computer Science, McGill University
- 2010 to 2012, B.Sc. (First Class with Distinction) Computing Science, Simon Fraser University
- 2008 to 2010, B.Eng. Computer Science and Technology, Zhejiang University
Miscellaneous
- My Erdös number is 2 : Paul Erdös 0 ↔ Craig Tovey 1 ↔ Hang Ma 2.
Recent Publications
-
@inproceedings{TangAAAI26, author = {Jingtao Tang and Hang Ma}, title = {GHOST: Solving the Traveling Salesman Problem on Graphs of Convex Sets}, booktitle = {{AAAI} Conference on Artificial Intelligence}, pages = {(in print)}, year = {2026} } -
We address the Multi-Robot Motion Planning (MRMP) problem of computing collision-free trajectories for multiple robots in shared continuous environments. While existing frameworks effectively decompose MRMP into singlerobot subproblems, spatiotemporal motion planning with dynamic obstacles remains challenging, particularly in cluttered or narrow-corridor settings. We propose Space-Time Graphs of Convex Sets (ST-GCS), a novel planner that systematically covers the collision-free space-time domain with convex sets instead of relying on random sampling. By extending Graphs of Convex Sets (GCS) into the time dimension, ST-GCS formulates time-optimal trajectories in a unified convex optimization that naturally accommodates velocity bounds and flexible arrival times. We also propose Exact Convex Decomposition (ECD) to "reserve" trajectories as spatiotemporal obstacles, maintaining a collision-free space-time graph of convex sets for subsequent planning. Integrated into two prioritized-planning frameworks, ST-GCS consistently achieves higher success rates and better solution quality than state-of-the-art sampling-based planners—often at orders-of-magnitude faster runtimes—underscoring its benefits for MRMP in challenging settings. Project page: https://sites.google.com/view/stgcs.
@inproceedings{TangIROS25, author = {Jingtao Tang and Zining Mao and Lufan Yang and Hang Ma}, title = {Space-Time Graphs of Convex Sets for Multi-Robot Motion Planning}, booktitle = {{IEEE/RSJ} International Conference on Intelligent Robots and System}, pages = {(in print)}, year = {2025} } -
Multi-Agent Path Finding (MAPF) aims to arrange collision-free goal-reaching paths for a group of agents. Anytime MAPF solvers based on large neighborhood search (LNS) have gained prominence recently due to their flexibility and scalability, leading to a surge of methods, especially those leveraging machine learning, to enhance neighborhood selection. However, several pitfalls exist and hinder a comprehensive evaluation of these new methods, which mainly include: 1) Lower than actual or incorrect baseline performance; 2) Lack of a unified evaluation setting and criterion; 3) Lack of a codebase or executable model for supervised learning methods. To address these challenges, we introduce a unified evaluation framework, implement prior methods, and conduct an extensive comparison of prominent methods. Our evaluation reveals that rule-based heuristics serve as strong baselines, while current learning-based methods show no clear advantage on time efficiency or improvement capacity. Our extensive analysis also opens up new research opportunities for improving MAPF-LNS, such as targeting high-delayed agents, applying contextual algorithms, optimizing replan order and neighborhood size, where machine learning can potentially be integrated.
@inproceedings{TanSOCS25, author = {Jiaqi Tan and Yudong Luo and Jiaoyang Li and Hang Ma}, title = {Reevaluation of Large Neighborhood Search for MAPF: Findings and Opportunities}, booktitle = {International Symposium on Combinatorial Search}, pages = {212--220}, year = {2025} } -
We study Multi-Robot Coverage Path Planning (MCPP) on a 4-neighbor 2D grid $G$, which aims to compute paths for multiple robots to cover all cells of $G$. Traditional approaches are limited as they first compute coverage trees on a quadrant coarsened grid $\mathcalH$ and then employ the Spanning Tree Coverage (STC) paradigm to generate paths on $G$, making them inapplicable to grids with partially obstructed $2 \times 2$ blocks. To address this limitation, we reformulate the problem directly on $G$, revolutionizing grid-based MCPP solving and establishing new NP-hardness results. We introduce Extended-STC (ESTC), a novel paradigm that extends STC to ensure complete coverage with bounded suboptimality, even when $\mathcalH$ includes partially obstructed blocks. Furthermore, we present LS-MCPP, a new algorithmic framework that integrates ESTC with three novel types of neighborhood operators within a local search strategy to optimize coverage paths directly on $G$. Unlike prior grid-based MCPP work, our approach also incorporates a versatile post-processing procedure that applies Multi-Agent Path Finding (MAPF) techniques to MCPP for the first time, enabling a fusion of these two important fields in multi-robot coordination. This procedure effectively resolves inter-robot conflicts and accommodates turning costs by solving a MAPF variant, making our MCPP solutions more practical for real-world applications. Extensive experiments demonstrate that our approach significantly improves solution quality and efficiency, managing up to 100 robots on grids as large as $256 \times 256$ within minutes of runtime. Validation with physical robots confirms the feasibility of our solutions under real-world conditions. A project page with code, demo videos, and additional resources is available at: https://sites.google.com/view/lsmcpp.
@article{TangTRO25, author = {Jingtao Tang and Zining Mao and Hang Ma}, title = {Large-Scale Multirobot Coverage Path Planning on Grids With Path Deconfliction}, journal = {IEEE Transactions on Robotics}, volume = {41}, pages = {3348--3367}, year = {2025} } -
We study a decentralized version of Moving Agents in Formation (MAiF), a variant of Multi-Agent Path Finding aiming to plan collision-free paths for multiple agents with the dual objectives of reaching their goals quickly while maintaining a desired formation. The agents must balance these objectives under conditions of partial observation and limited communication. The formation maintenance depends on the joint state of all agents, whose dimensionality increases exponentially with the number of agents, rendering the learning process intractable. Additionally, learning a single policy that can accommodate different linear preferences for these two objectives presents a significant challenge. In this paper, we propose Mean-Field Control with Envelop Q-learning (MFC-EQ), a scalable and adaptable learning framework for this bi-objective multi-agent problem. We approximate the dynamics of all agents using mean-field theory while learning a universal preference-agnostic policy through envelop Q-learning. Our empirical evaluation of MFC-EQ across numerous instances shows that it outperforms state-of-the-art centralized MAiF baselines. Furthermore, MFC-EQ effectively handles more complex scenarios where the desired formation changes dynamically -- a challenge that existing MAiF planners cannot address.
@inproceedings{LinIROS24, author = {Qiushi Lin and Hang Ma}, title = {MFC-EQ: Mean-Field Control with Envelope Q-Learning for Moving Decentralized Agents in Formation}, booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems}, pages = {14156--14163}, year = {2024} } -
This paper presents a vector HD-mapping algorithm that formulates the mapping as a tracking task and uses a history of memory latents to ensure consistent reconstructions over time. Our method, MapTracker, accumulates a sensor stream into memory buffers of two latent representations: 1) Raster latents in the bird’s-eye-view (BEV) space and 2) Vector latents over the road elements (i.e., pedestrian-crossings, lane-dividers, and road-boundaries). The approach borrows the query propagation paradigm from the tracking literature that explicitly associates tracked road elements from the previous frame to the current, while fusing a subset of memory latents selected with distance strides to further enhance temporal consistency. A vector latent is decoded to reconstruct the geometry of a road element. The paper further makes benchmark contributions by 1) Improving processing code for existing datasets to produce consistent ground truth with temporal alignments and 2) Augmenting existing mAP metrics with consistency checks. MapTracker significantly outperforms existing methods on both nuScenes and Agroverse2 datasets by over 8% and 19% on the conventional and the new consistency-aware metrics, respectively. The code will be available on our project page: https://map-tracker.github.io.
@inproceedings{ChenECCV24, author = {Jiacheng Chen and Yuefan Wu and Jiaqi Tan and Hang Ma and Yasutaka Furukawa}, title = {MapTracker: Tracking with Strided Memory Fusion for Consistent Vector HD Mapping}, booktitle = {European Conference on Computer Vision}, pages = {90--107}, year = {2024} }
Full list of publications