Towards Autonomous Shooting Rover via Situation Aware Visual-Perception and Dynamic Action Execution

In this system paper, we present our approach to the DJI Robomaster AI Challenge, 2022 where our team ERA-IITK was ranked 3
^rd
worldwide among 83 teams. We primarily focus on system hardware design and algorithmic components to achieve full autonomy. We first detail the hardware infrastructure, including intricate details on sensors and communication setup. Then we comprehensively describe our algorithmic pipeline and a state machine based on them to realize an autonomous system. Our major novelty is the high-speed and accurate visual perception module for target detection, and high-speed self-localization to maximize the likelihood of a target being shot. Our research endeavor in this paper can serve as a foundation for more complex systems and holds immense potential for various real-world applications.