COMP417: Intro to Robotics and Intelligent Systems, Winter 2019

Overview

Today, robots are our primary way to study other planets, explore the deep ocean, ensure our e-shopping arrives on time, increase the efficiency and safety of our cities, and further increase agricultural productivity to feed the increasing population. Robotics is the discipline concerned with both building robots, mechanically and electrically, as well as designing and coding effective algorithms for their operation.

A robot is an intelligent computer system that can use sensors and act on the world. We will study the definitional problems in robotics through theory and practical coding solutions. The emphasis is on algorithms, probabilistic reasoning, optimization, inference mechanisms, and behavior strategies, as opposed to electromechanical systems design. This course aims to help students improve their probabilistic modeling skills and instill a few of the core concepts in robotics:

• robotic algorithms require our best tools in computing as well as our best knowledge of the physical world; the union of these two fields is a powerful and beautiful place.
• a robot that explicitly accounts for its uncertainty works better than a robot that does not.
• the intuition for many robotic algorithms comes from our understanding of our own physical ability, and that development of robotic solutions can help us better understand this aspect of intelligence.

Course Description

• Geometric Motion Planning: how can a robot plan a sequence of motions that bring it to a goal safely? How do we represent a robot's pose in the world and the shape of its environment?
• Mapping: how can we combine noisy measurements from sensors with the robot’s pose to build a map of the environment?
• State Estimation: the state of the robot is not always directly measurable/observable. How can we determine the relative weighs of multiple sensor measurements in order to form an accurate estimate of the (hidden) state?
• Feedback Control and Planning: how can we compute the state-(in)dependent commands that can bring a robotic system from its current state to a desired state?
• Research and enrichment topics: how do robots see using cameras? How can a robot build models of its own dynamics from data and use these to perform tasks?How do robots interact with humans today, and how do we want them to interact with us in the future?