Qin Yang
Doctor of Computer Science
My paper "Self-Reactive Planning of Multi-Robots with Dynamic Task Assignments" has been accepted by IEEE International Symposium on Multi-Robot and Multi-Agent Systems 2019.
Get the Research Assistantship offer from Department of Computer Science in University of Georgia!
Start to develop a General Swarm Robotic Simulator(SRS).
Start my new research area "Adversarial Swarm Robotics" and finish a proposal about "Optimizing Utility of Swarm Robots Formation Based on Hierarchical Decision in Adversarial Environments".

Brief Bio

I am a Doctor of Computer Science at University of Georgia specialize in Swarm Robotics, Multi-Robots System and Distributed intelligence. Before coming to UGA, I was a senior electrical and automatic control engineer who already has 12 years work experiences in the Intelligence Engineering field and an assistant researcher of Robotics and Artificial Intelligence Laboratory at The Chinese University of Hong Kong, Shenzhen. I obtained my M.S. (2018) in Computer Science from Colorado School of Mines, M.E. (2011) in Software Engineering from Peking University, and a B.S. (2004) in Mechanical Design Manufacturing and Automation from the Harbin Institute of Technology.

Research Summary

My research mainly foucs on Swarm Robotics, Distribited Intelligence(Swarm Intelligence), Computer Vision, Wireless Sensor Networks, Planning & Control and Simulation Technique, which implement in the multi-robots perception, decision, planning and control. Actually, I strive to understand the relationship between things, and how can we simulate their interaction with each other or unknown and adversarial environment efficiently, then implement those into real robots. These works concern with the computational issues of distributed intelligent systems having a physical instantiation in the real world, such as multi-robot system, wireless sensor networks, or software agents. It characterize as multiple entities that integrate perception, reasoning, decision and action to perform cooperative tasks under circumstances that are insufficiently known in advance, and dynamically changing during task execution. Design and develop new algorithms and software architectures that have provable properties. Care about basic research that leads to fundamental new concepts that can be demonstrated on real robot or sensor network hardware. Through these works, I was attracted by more challenging problems in the Artificial Intelligent, Automatic Control and Robotics, for example, real-time (or one-shot) shape acquisition, object recognition, optimization algorithm design, the optimal strategies of robot communication, planning & control, and stuff like that.

Some overlapping focus areas include:


Swarm Robotics

Swarm Robots System is a kind of distributed intelligent system, which means large number of robots are coordinated in a distributed and decentralised way. The whole system’s behaviors are caused by the individual robot’s behaviors. Each robot may have identical or different abilities and can be programmed with several basic laws adapting the environment. In order to adapt the dynamic environment effectively, minimize the system cost and maximize the utility of the group, individual robot need to cooperate with each other, share its information and make a suitable plan according to the specific scenario. Swarm robotics is an approach to the coordination of multiple robots as a system which consist of large numbers of mostly simple physical robots.


Distributed Intelligence

In nature, the complexity results from the interrelationship, interaction and inter-connectivity of elements within a system and between a system and its environment. The interaction of swarm micro elements basing on some simple principle can give rise to the complex behaviors in the whole group, even the fundamental change of the system structures, pattern, and function etc. Based on this idea, people develop an approach to solving complex learning, planning, and decision making problems exploiting large scale computation and spatial distribution of computing resources, which we call Distributed Intelligence. Swarm Intelligence is a kind of Distributed Intelligence, which is the collective behavior of decentralized and self-organized systems.


Computer Vision

Vision is one of the most direct approach when people interact with the outside world. Almost 75% information which human get from the environment through vision. So it is a good way to let machine or robot percept the circumstance and gaining high-level understanding from digital images or videos and interact with people. Computer Vision tasks include methods for acquiring, processing, analyzing and understanding digital images, and extraction of high-dimensional data from the real world in order to produce numerical or symbolic information, e.g., in the forms of decisions.


Wireless Sensor Networks

In the various robots' system design, we usually build a Wireless Sensor Networks(WSN) to make sure our robots can get different kinds of physical or environmental information, such as temperature, sound, pressure, etc. and to cooperatively pass their data through the network to a main locations. Especially in the multi-agent system, in order to expend the whole system perception range, individual usually build a swarm or group to share its information and data with each other, which can help the system to make a suitable decision accroding to the current status and maximize the benefit of every group member.


Planning and Control

Multi-robots Planning and Control in dynamic, unknow or adversarial environment is a NP-hard problem. Simple reactive motion planning strategies cannot guaranteed to be deadlock free and to converge. Previous results either obtain optimal solutions through centralized and exhaustive computing, or achieve distributed implementations without considering optimization issues. Espeically, the outdoor environment is more challenging with terrain features, various threatens and requires online re-planning. In addition, the current planning-based approaches usually can not handle the large scale robot teams, also the star-shaped communication graph which are applied in this system is not realistic for large groups of robots.


Simulation Technique

Simulating continuous motion of multi-agent in the same space is non-trivial to implement, as the motions of one agent may depend on the motions of the surrounding agents. Especially, the emergent behaviors are easy to implement in a time-step agent-based simulation, as the individuals behaviors can simply be encoded as a set of predicates and the resulting transition to the agent at each time step. But it is not computationally efficient as the computational time required is proportional to the amount of steps in the simulation. So implement as a discrete event simulation rather than a time step model, at the cost of reduced implementation ease, and significantly reduced ease of verifying the computational model.


Below you can find a list of my academic publications, along with accompanying project pages and downloads. You can also check out my  CV as a PDF download.

Recent Publications


Academic Experiences:

Term Place Duty Class & Work
Spring 2019 University of Georgia Research Assistant

Academic Experiences:

Term Place Duty Class & Work
Fall 2018 Colorado School of Mines Teaching Assistant CSCI 441: Computer Graphics
Fall 2018 Colorado School of Mines Teaching Assistant CSCI 542: Simulation
Fall 2018 Colorado School of Mines Teaching Assistant CSCI 423: Computer Simulation
Fall 2018 Colorado School of Mines Teaching Assistant CSCI 101: Introduction to Computer Science
Fall 2018 Colorado School of Mines Teaching Assistant CSCI 102: Introduction to CS-LAB
Spring 2018 Colorado School of Mines Teaching Assistant CSCI 274: Introduction to the Linux Operating System
Fall 2017 Colorado School of Mines Teaching Assistant CSCI 358: Discrete Mathematics
Fall 2017 Colorado School of Mines Teaching Assistant CSCI 403: Database Management
06/17-08/17 The Chinese University of Hong Kong, Shenzhen Assistant Research Engineer Auto-jalor Project

Working Experiences:

Intelligent Engineering Department, China Architecture Design Institute Co., Ltd
Time Place Duty
04/14-10/16 Beijing, China Senior Electrical Engineer and Project Manager
China Electronics Eng Design Institute–S.Y. Tech, Eng & Const Co., Ltd
Time Place Duty
06/10-04/14 Beijing, China Electrical Engineer and Project Manager
China Aerospace Architectural Design Research Institute (Group)
Time Place Duty
07/04-05/10 Beijing, China Electrical Engineer and Project Manager


Project 1: Self-Reactive_Swarm-Robots_System(SSRS)

In this project, we formalize the problem of multi-robots fulfilling dynamic tasks using state transitions represented through a Behavior Tree. We design a framework with corresponding distributed algorithms for communications between robots and negotiation and agreement protocols through a novel priority mechanism following Maslow’s law. Finally, we evaluate our framework through extensive experiments.


The simulation video is shown as follow:

Hobbies & Miscellaneous

In my leisure time, I like fitness, hiking, cooking, music, watching movie, playing saxophone and photography. I used to play violin, badminton, football and travel, which I found lots of fun and inspiration.

I also join various organization in my undergraduate, which I am interested: