Reinforcement Learning in Autonomous Driving

This advanced micro-credential course delves into the cutting-edge realm of reinforcement learning applied to autonomous driving systems. Participants will explore the intersection of AI and transportation, learning how reinforcement learning algorithms enable vehicles to make complex decisions in real-time scenarios. The course covers foundational concepts in reinforcement learning, including Markov decision processes, deep Q-networks, policy gradients, and model-based methods tailored specifically for autonomous driving. Through practical simulations and projects, students will analyze and implement reinforcement learning techniques to train autonomous agents, navigate dynamic environments, and optimize driving behaviors. Emphasis will be placed on understanding safety, ethical considerations, and the challenges of deploying reinforcement learning in the context of autonomous vehicles.

Neurotechnologies in Automation

Course makes introduction to artificial neural network methods, to methods of learning, to implementation for object recognition with NeuroSolutions software. Based on neural networks sumulation software it helps to support virtual learning methods.
Learning Outcomes 1: Application of modern modeling approaches and methods and optimization for research and creation of effective automation systems for reducing waste generation, promoting circular economy practices, and supporting sustainable procurement policies on base of Neurotechnology.
Learning Outcomes 2: Analyses of production and technical systems in a certain industry activities as objects of automation and determine their strategy automation and digital transformation, in their transition to a circular economy involing designing of products for longevity, repairability, and recyclability with analyses, monitoring and prediction on base of Neurotechnology.

Autonomous ROBOTICS

sensoring, vision, energy storage and movig systems; autonomous robotic platform management etc.