Instructor Spring 2019: Christopher Heckman

Learning Goal

Design and implement algorithms and hardware that enable autonomy in uncertain, dynamic environments.

Description

This class is the follow-up class to CSCI3302 \Introduction to Robotics." Robots perceive their environment with signal processing and computer vision techniques, reason about them using machine learning, arti cial intelligence and discrete algorithms, and execute their actions based on constraints imposed by sensor uncertainty, their mechanism, and their dynamics. \Advanced Robotics" will teach the key concepts used by autonomous mobile platforms and provide hands-on experience with state-of-the-art software and systems.
Lecture materials are supported by exercises around the \Robot Operating System" ROS and will lead to the completion of a group project. After the Autonomous Vehicle Competition (AVC) at SparkFun, and the F 1/10th Autonomous Racing Competition at CPS Week in Pittsburgh, this class will focus on robust autonomous driving. Exercises will be conducted in a virtual environment and will later be transferred to an autonomous vehicle platform

Prerequisites or Co-requisites

CSCI 3302 Introduction to Robotics or instructor consent required.

Topics

Computer vision including sparse visual odometry, simultaneous localization and mapping (SLAM), sensor fusion and ltering; the Robot Operating System (ROS); planning algorithms, nonholonomic constraints in dynamics and controls; intrinsic and extrinsic sensor calibration; embedded systems; and experimental robotics.

Grading

Attendance and participation: 10%.
Seminar speaker reports: 10%.
Semester project: 35%.
Final exam/presentation: 10%.
Assignments: 35%.