Robotics

How can agile micro aerial vehicles operate autonomously in cluttered environments? This module delves into the mechanics of flight, the design of quadrotor robots, and the challenges of using noisy sensors for localization. Students will develop dynamic models and controllers for operating in three-dimensional environments.

This course considers the problem of how a robot decides what to do to achieve its goals, known as Motion Planning. Students will learn common approaches to addressing this problem, including graph-based methods, randomized planners, and artificial potential fields. The module discusses the challenges that make planning difficult.

Participants will explore how robots can move in unstructured environments using their motors and sensors. The module covers the design of robot bodies and behaviors to confer reliable mobility, as well as the composition of simple dynamical abstractions to automate the generation of sensorimotor programs.

This module focuses on how robots perceive the world and their movements to accomplish navigation and manipulation tasks. Students will study how images and videos acquired by robots are transformed into representations for extracting 3D information about the environment and object posing.

Students will learn how robots estimate their state and properties of the environment from noisy sensor measurements. The module covers probabilistic generative models, Bayesian filtering for localization and mapping, and techniques for incorporating uncertainty into estimating and learning from a dynamic and changing world.

The Robotics Capstone provides an opportunity to implement a solution for a real-world problem based on the content learned in the specialization. Participants can choose from simulation or hardware tracks, demonstrating their programming skills in robot movement, planning, and perception for practical applications.