Content, progress and pedagogy of the module

The module is based on knowledge achieved in Probability Theory, Stochastic Processes and Applied Statistics.

Learning objectives

Knowledge

• Have comprehension of the benefits of using a probabilistic approach to design robotic systems
• Have comprehension of the probabilistic approaches used in modern robotic systems
• Have comprehension on Markov processes and Bayesian filtering
• Have fundamental knowledge on decision making systems, Markov Decision Processes and Partially Observable Markov Decision Processes
• Have fundamental knowledge on state estimation, sensor fusion as well as planning and control
• Have fundamental knowledge of reinforcement learning and end-to-end systems
• Have comprehension on robot kinematics and dynamics

Skills

• Be able to analyse state estimation techniques such as Kalman filtering, particle filtering
• Be able to select the appropriate state estimation and sensor fusion methods in a real-world application in robotics
• Be able to use Markov or Bayesian localization methods
• Be able to model how a dynamic robotic system interacts within an uncertain environment
• Be able to use computer vision and/or odometry to make a robot navigate in an uncertain environment

Competences

• Be able to design, implement, and validate probabilistic models that can represent uncertainty and variability in the environment and the robot's perception.
• Be able to implement state estimation techniques such as Kalman filtering, particle filtering, and Markov localization to estimate the robot's pose, the map of the environment, and other relevant states.
• Be able to design planning and control algorithms that can optimize the behavior of robots while they navigate in uncertain and dynamic environments.
• Be able to use simulation environments to test probabilistic robotic systems
• Be able to use programming frameworks and libraries to design probabilistic robotic systems

Type of instruction

Lecture followed by numerical and simulation exercises and possible e-learning activities.

Extent and expected workload

Since it is a 5 ECTS course module, the work load is expected to be 150 hours for the student.

Exam

Exams