Towards an Autonomous RoboCup Small Size League Robot

摘要

The RoboCup Small Size League (SSL) uses a standard vision system for detecting elements and estimating their positions. However, the League proposes developing more autonomous robots to overcome limitations from this architecture. Furthermore, SSL matches are highly dynamic environments with extremely resource-constrained robots, requiring solutions to consider size, power consumption, accuracy, and processing speed trade-offs. This work presents an architecture that enables these robots to execute basic soccer tasks autonomously, that is, without receiving any external information. An additional processing unit was added for embedded vision and decision making, running at 30 frames per second, and odometry estimation was implemented using inertial sensors. Soccer skills are implemented by defining Finite State Machines (FSM) for desired tasks, which outputs pre-defined movements for navigation and robot desired actions. We evaluate our system on three soccer tasks: grabbing a ball, scoring a goal, and passing the ball, achieving 80%, 80%, and 46.7% success rates, respectively.