Introduction: The Interdisciplinary Team project is a challenge-based learning project in which students collaborate in teams to apply their knowledge of Artificial Intelligence and Engineering Systems to resolve a practical engineering problem either in a company or with a laboratory set-up on campus. The project involves an application that is relevant to the specific track that the students follow in the AI&ES program. The project results in a presentation, a demonstration, a report, and a defense of the work that is scheduled by the end of the quartile. In this course, the students largely determine the direction, organization, and individual objectives themselves. Teams will be defined prior to the start of the project. Teams have regular (weekly or bi-weekly) progress meetings with project owners and/or coaches to discuss planning, organizational aspects, technical progress, and division of tasks and responsibilities among the team members. Teams are responsible for defining their own challenges in the project, combining the competencies of team members, realizing a design process in close cooperation, and reporting on its outcome. The size of the team will depend on the project. Multiple applications and challenges are provided and various challenges are relevant for multiple tracks. During the course of the project, various trainings and workshops are provided to improve and train the professional skills of students on (i) Academic and technical writing, (ii) Collaboration skills in teamwork, (iii) Research planning, and (iv) Presentation skills.

Introduction: TAS is a complimentary course that is held every winter semester at the Technical University of Munich (TUM),  by the School of Computation, Information, and Technology (CIT). The main target of the TAS course is to develop the student's capability of designing and coding autonomous mobile robots in navigation tasks. The course provides the students with a self-designed remote-controlled robot car with a brushless motor, a steering motor, and a variety of sensors including laser scanners, cameras, inertia measurement units (IMU), and an on-board computing unit. The students are expected to work with the robot car by developing novel algorithms and libraries to improve its performance in an autonomous navigation task, in terms of goal achievement, successful rates, and speed. Meanwhile, the students are expected to select one additional maneuver task, such as parallel parking or slalom course, to validate the algorithms. The course also gives theoretical lectures exploring a variety of scopes related to autonomous driving systems, including optimization, planning, sampling, localization, and game theory. In general, the objectives of the course are summarized as follows.

• To enhance the experiences of the students in terms of working with realistic robotic systems.

• To provide the students with basic knowledge about localization, navigation, and autonomous driving systems.

• To enable the capabilities of students to analyze the performance of robotic systems and solve engineering problems

• To improve the skills of the students, including teamwork, time management, organization, etc.

[course introduction, page 559]