roboticsclubatucf / robosub Goto Github PK

The core functionality of controlling the sub in all 6 degrees of freedom given a sufficient set of thrusters in arbitrary positions is complete, but the automatic detection and re-computation of the thruster matrix hasn't been tested pending the thruster manager being able to send thruster alive data

A node that accepts input from joysticks and whatever autonomy is running and decides which to send to the vector thrust controller. Use one of the throttle levers to select for now.

The sensor fusion system should provide a state estimation for the decision making system to allow task localization. The system should take as input the output from each sensor and the vision system and return the inferred state the sub is in for the competition. The system will use a dynamic Bayesian network operating at at an time step determined by testing. The system will use an appropriate inference algorithm such as Gibbs sampling or Monte Carlo inference methods and use appropriate learning techniques to adapt the sensor errors to their true values based on test data.

Develop a system to track the buoys and return some indication of their position to ROS

The buy chips task begins when the sub has detected that it has navigated to within vision range of the chip dispenser(s). The task ends when the sub has collected the maximum number of chips. The next task should be acoustic navigation to proceed to the active pinger, making no initial assumptions as to which task is at the pinger. The task is responsible for tracking the dispenser button and tray, commanding the manipulator to pick up the golf balls, pressing the dispenser button, and keeping track of how many balls are in the manipulator.

The particle filter will be used to provide direct visual servoing with the sub and its various tasks. The visual servoing will take in a desired visual landmark and will attempt to align the subs cameras to the landmark. Each particle corresponds to the thruster commands that will yield a new camera postion. Thus they will be 6 dimensional with each dimension referring to a degree of freedom in the sub. Each iteration the best particle will be sent as a thruster command to the sub and the particles will be resampled based on the new location of the visual landmark.

Particle filter-based direct visual servoing