Throughout the course, students will engage in practical projects and laboratory sessions, working with hardware platforms and simulation tools commonly used in service robotics research and development. They will collaborate in teams to design and implement innovative robotic solutions, leveraging their knowledge of sensors, embedded systems, and algorithms. By the end of the course • Students will have a deep conceptual understanding of autonomous mobile robots’ systems. • They will experiment the integration between sensors, embedded systems, and algorithms in the context of service robotics. • They will be proficient in designing and implementing intelligent robotic systems capable of perceiving their environment, making informed decisions, and executing complex tasks. • They will acquire practical know-how with standard robotics programming languages and frameworks.

Mathematics: linear algebra and matrix analysis, rotations and reference frames, quaternions, probability theory, linearization, and Taylor expansion. Control systems: basic elements of closed loop control (PID). Software: basic skills in object-oriented programming (Python) Electronics: basic knowledge of embedded systems and sensors integration

Theory and tutorials [50 h]: - Service robotics introduction [3h] Typical missions and requirements - Mathematical background: [3h] * Linear algebra Robot control paradigms (general overview of the pipeline) Probability theory - Programming background: introduction to object-oriented programming in Python [3h] * Variables, Arrays, lists, functions NumPy: math operations with multi-dimensional arrays, slicing and indexing Classes and objects - Mobile robots’ architecture (locomotion, power train, battery, BMS, etc): [3h] * UGV UAV HW/SW architectures (RT low-layer, navigation layer, etc) - Wheeled Mobile Robots: [1.5h] Locomotion models of mobile robots Differential drive, Ackermann drive Mechanum Wheels - ROS/ROS 2 [6h] Introduction Nodes, topics and services/actions How to write a ROS Node (tutorial) Advanced tutorials - Simulation setup and tools [1.5h] Gazebo Rviz - Perception & sensors for mobile robots: [1.5h] Proprioperception: Wheel Encoder, IMU Exteroperception: Proximity sensors: LiDAR, Cameras, Ultrasound, Infrared - Probabilistic motion models [3h] Odometry model Velocity based model - Probabilistic sensors models [3h] - Localization: [9h] Bayes filter Kalman Filter, Extended Kalman Filter and Unscented Kalman Filter Particle filter and Monte Carlo Localization - Mapping: [3h] Grid maps and Mapping with known poses Introduction to SLAM - Path and trajectory planning: [3h] Search-based Global Planner: A*, Dijkstra - Motion control, Obstacle avoidance and Trajectory tracking: [3 h] Local planner/controller: DWA, Pure pursuit - Written test example & Guidelines for Oral discussion of lab reports [1.5] Laboratory [30h]: - ROS/ROS 2, Gazebo/Rviz [9h] Nodes, topics Services/actions Simulation in Gazebo (sensors, platform, worlds) - Hands-on first practice with a real robot [3h] Bring-up Navigation test - Robot Localization [9h] Motion and Sensors model EKF Localization (in simulation and with real robot) / Particle Filter Localization - Path planning and control with real robot [9h]* DWA for obstacle avoidance and local planning (in simulation and with real robot) / Path planning on gridmaps + Pure Pursuit path tracking *it is NOT mandatory for students of the 2nd year that have enrolled for 6 cfu.

The course is proposed in a 8 cfu format for 1st year students of the MSc in Mechatronic Engineering and in a 6 cfu format for 2nd year students (free choice course).

The course is composed by a theory part typically done in classrooms and some technical tutorials about HW/SW tools that will be used during the course itself (5 CFU/4 CFU). The course also includes experimental laboratory exercises (3 CFU/2 CFU) to be performed at the LED laboratories. The labs are organized in groups of 3/4 students. Presence is required for 70% of the labs. Groups must prepare a technical report for the three main lab activities conducted, that will be evaluated offline, then orally discussed, and will be part of the final evaluation.

Suggested textbooks: - Probabilistic Robotics: Wolfram Burgard, Dieter Fox, Sebastian Thrun (2005) http://www.probabilistic-robotics.org/ - Introduction to Autonomous Mobile Robots: (2nd Edition) Roland Siegwart, Illah Reza Nourbakhsh, Davide Scaramuzza (2011) https://mitpress.mit.edu/9780262015356/introduction-to-autonomous-mobile-robots/ - A Concise Introduction to Robot Programming with ROS2, Rico, Taylor & Francis Ltd, 2022

Lecture slides; Lecture notes; Lab exercises; Video lectures (current year); Video lectures (previous years); Multimedia materials; Simulation tools;

Exam: Written test; Compulsory oral exam; Group project;

Written test (in presence); Practical lab reports (to be delivered according to the deadlines defined with the annual calendar); Oral discussion of lab reports. The final exam consists of two distinct parts: - evaluation of the experimental activities carried out in the laboratory. The evaluation consists in offline evaluation of each technical report (2 for 6 CFU students) + oral discussion of the reports. Lab activity counts MAX 15 points / MIN 8 points to pass the exam, given by report evaluation score +- 3 points from mandatory oral discussion (always keeping MAX 15 points). - written exam focused ONLY on the theoretical aspects of the course (90 minutes, 4/5 open questions, closed book, no material admitted) - MAX 18 points / MIN 8 points to pass the exam.

In addition to the message sent by the online system, students with disabilities or Specific Learning Disorders (SLD) are invited to directly inform the professor in charge of the course about the special arrangements for the exam that have been agreed with the Special Needs Unit. The professor has to be informed at least one week before the beginning of the examination session in order to provide students with the most suitable arrangements for each specific type of exam.