Graduate Projects
Co-evolutionary Multi-objective Optimization of RTS Micro (C++)
Here, We are investigating a co-evolutionary multi-objective optimization approach to generate a diverse set of good micro in RTS game from scratch, enabling a human or AI player to the trade-off that better suits for a short or long-term strategy.
A potential field approach to evolve kiting behaviors in StarCraft II (C++)
Here, We generate high-quality kiting behaviour of Hellions (ranged units ) against Zealots controlled by computer AI in StraCraft II using a potential field appraoch. In the video below, the blue units are Hellions (evolved) and the red units are Zealots (Computer AI).
<An influence Map approach to evolve kiting behaviors in StarCraft II (C++)
Here, We generate high-quality kiting behaviour of Hellions (ranged units ) against Zealots controlled by computer AI in StraCraft II using an influence map. In the video below, the blue units are Hellions(evolved) and the red units are Zealots (Computer AI).
Co-evolving Real-Time Strategy Game Micro (C++)
We investigate competitive co-evolution of unit micromanagement in real-time strategy games. Although good long-term macro-strategy and good short-term unit micromanagement both impact real-time strategy games performance, this project focuses on generating quality micro. Better micro, for example, can help players win skirmishes and battles even when outnumbered.Prior work has shown that we can evolve micro to beat a given opponent. We remove the need for a good opponent to evolve against by using competitive co-evolution to evolve high-quality micro for both sides from scratch. We first co-evolve micro to control a group of ranged units versus a group of melee units.We then move to co-evolve micro for a group of ranged and melee units versus a group of ranged and melee units. Results show that competitive co-evolution produces good quality micro and when combined with the well- known techniques of fitness sharing, shared sampling, and a hall of fame takes less time to produce better quality micro than simple co-evolution. We believe these results indicate the viability of co-evolutionary approaches for generating good unit micro- management.
Bridge crew Simulation in VR (C#)
Developed a VR environment to simulate bridge of a ship. Same environment could be shared by multiple users in different headsets and could interact with each other with realtime voice chat. This could be used for training and mission simulation.
Undergraduate Projects
Automatic Robotic Arm Tracking (Final Year Project) (C, C++)
We developed a prototype model of a Robotic Arm to automatically track and grab a desired object in real environment. We used image processing to detect the desired object (X and Y position of the desired object in 3D environment) and sensors to detect depth (Z position of the desired object in 3D environment). We then programmed a microcontroller to control movements of different servo motors of the Robotic Arm to track and grab the given object.