CS4313 Advanced Robotic Systems

AI methods for robots and unmanned vehicles. The first part of the course will discuss generic sensing and control mechanisms, including reactive and hierarchical control. The second part of the course will focus on specialized areas of robotics, including biologically inspired robotics, developmental robotics, swarm robotics, and unmanned autonomous vehicles.

Prerequisite

CS3310

Lecture Hours

3

Lab Hours

2

Course Learning Outcomes

Upon completion of this course, students will be able to:

• Employ appropriate robot motion-planning algorithms to safely navigate in known and unknown environments.
• Utilize probabilistic and sensor models to derive and maintain a Bayesian robotic state estimate.
• Employ various techniques to develop and maintain occupancy-grid maps for use in maintaining robot situational awareness.
• Computationally develop area coverage (e.g., search) patterns for autonomous employment by single- and multirobot systems.
• Employ consensus algorithms, task decomposition, and market-based assignment within multirobot system to cooperatively achieve complex objectives in a communications-constrained environment.
• Utilize Kalman Filters and Extended Kalman Filters as appropriate to track stationary and moving targets and maintain feature-based and occupancy-grid maps (i.e., SLAM)
• Demonstrate practical mastery of course material through the completion of lab assignments and a comprehensive final project programmed in Python or C++ using the Robot Operating System middleware.