top of page

DARPA OFFSET Project

Swarm Intelligence to Solve Complex Scenarios with Adversarial Agents.

Fall 2019 - Spring 2020

As a member of the ADAMS Lab at The University at Buffalo, The State University of New York, I was given the opportunity to take part in working on the DARPA OFFSET program:

 

"DARPA’s OFFensive Swarm-Enabled Tactics (OFFSET) program envisions future small-unit infantry forces using swarms comprising upwards of 250 unmanned aircraft systems (UASs) and/or unmanned ground systems (UGSs) to accomplish diverse missions in complex urban environments. By leveraging and combining emerging technologies in swarm autonomy and human-swarm teaming, the program seeks to enable rapid development and deployment of breakthrough capabilities."

​

Our team at UB was composed of a few labs, led by the respective faculty who run those labs. Due to security restrictions, I am not able to showcase much of the work I did as a part of this project.

I took on several assignments as a member of the Machine Learning division of the UB team:

​

I Modeled additional complexities for the machine learning framework to create optimal UAV (unmanned aerial vehicle) and UGV (unmanned ground vehicle) swarm tactics, such as uncertainty due to obscured vision, LIDAR data, and field of view, through encoding in a low-fidelity (pybullet) environment.

​

I developed a multi-robot area monitoring area for surveying an area to gather real-time data in a time-optimal manner. This algorithm was also further expanded upon, and later became Chapter Three of my Master's Thesis.

​

I encoded geographical maps to topological graphs for swarm learning model usage through image processing and clustering methods. This work was later expanded upon to become Chapter Four of my Master's Thesis.

Project Requirements
basenodemap.png

  • Extensive Python usage

  • Clustering methods

  • Optimal waypoint planning methods

  • Machine Learning

  • Graph theory

  • Git version control

  • MATLAB usage

  • LIDAR knowledge

  • Uncertainty modeling

  • Environment modeling

  • Mathematics

  • Interdisciplinary Teamwork

  • Excellent verbal and written communication skills

​

​

​

bottom of page