Case solutions on Autonomous Intellectual Systems

Four steps to construct autonomous drive along the Duckietown road lane. Contestants get four problems to be solved using the Duckietown simulation environment.

Details:

  • You can send commands to the Duckiebot by controlling its translational and rotational speeds.
  • A command is executed until the next command is sent.
  • The simulator processes incoming commands until the robot either executes them or moves outside the road. There is no automatic stop when the "task point" is reached.
  • In tasks, where the use of computer vision is foreseen, access to the video frame is provided for each beat when the robot receives a control command. The video camera is mounted on the robot front.
  • Your job is to implement the source code and send it to the check system, where the simulator will run. Immediate interaction with the simulator "on the fly" is not possible, but each simulator run ends with providing solution logs to the user, they are supported by the video of the robot's movement in accordance with the source code. Register and get personal access to cases on the Moodle platform.

Case solutions on AI in Physiology and Medicine Science

The case deals with the ECG signal analysis using logistic regression. One of the most pressing cardiology challenges today is to improve the quality of automated electrocardiogram (ECG) analysis. Efficient algorithms allow physicians to use long-duration recordings in order to obtain important diagnostic information about a patient's cardiac activity. Contestants solve the task of developing an algorithm, which classifies the QRS complexes into "pathological" and "healthy" categories using the method of logistic regression. The input data include ECG recordings, as well as QRS complexes positions already marked. The task is to identify features for classification, construct and optimize the model, and evaluate its sensitivity and predictive power. Register and get personal access to cases on the Moodle platform.

Case solutions on AI Security and Ethics

This case offers several cryptography and security problems, it follows the Olympiad principle. So its tasks are not interrelated, and the points are earned independently for each task. Cryptography knowledge is not needed to solve the case tasks, they are aimed at testing the logical abilities of contestants. Cryptography is currently used in all AI systems to ensure data transfer security, user authorization, access differentiation, secure data storage and user identification. These tasks give contestants an opportunity to test their analytical skills and have a practical exercise with problem solutions integrated into the today’s cryptographic applications. Register and get personal access to cases on the Moodle platform.

Кейс "Безопасность и этика искусственного интеллекта"

Кейс "Применение искусственного интеллекта в физиологии и медицине"

Кейс "Автономные интеллектуальные системы"