COURSES

Goals

The objective of this course to obtain theoretical and practical knowledge of the basics of service and humanoid robotics, control, learning and applications of service and humanoid robots. The emphasis is on modern approaches of the integration of robot systems into human-like environments. The obtained knowledge will allow the students to understand the basic principles of motion and handle modern technologies of service robotics and to apply these technologies into real practice.

Curriculum

Basic structure of humanoid and service robots Parametric policy representation - Discrete and periodic policies, - Representations using Hidden Markov model, Gaussian mixture model, Gaussian mixture regression, Dynamic motion primitives, Probability motion primitives, Interactive motion primitives, Compliant motion primitives Learning for humanoid and service robots: - Imitation learning - Reinforcement learning - Transfer Learning - using large language models Motion generalization: - Statistical generalization methods Autonomous motion adaptation: - Using iterative learning control - Using compliant control - Using (deep) reinforcement learning - Using neural networks Robot learning and adaptation in latent spaces - Latent space policy representation - Learning and task execution in latent spaces Optimal robot control - Using linear quadratic regulator - Extension to non-linear robot dynamics - Model predictive control in robotics Humanoid and service robots in human environments: - Human – robot cooperation - Physical human – robot and robot – environment interaction - Motion synchronization and adaptation Bimanual robot control - Leader - follower approach - Symmetric task decomposition Use of advanced sensory systems for environment detection and localization: - RGBD cameras - Laser scanners - Proximity sensors Examples of practical used of algorithms in service robotics