A bit about me:

• I was Graduate Student in Artificial Intelligence. I was member of the Robotics and Computer Vision Research Group.
• Until December 1999, I was the Head Teaching Assistant for ECE 110 - Introduction to Electrical and Computer Engineering. The current schedules available for this course are for Spring Semester, Summer II Semester, and Fall Semester. For information about the ECE Department, check out the ECE Department's Home Page.
• From September, 1997 through May, 1998, I spent some time in this lab.
• Some publications.
• Some demos.

The project for my PhD was to design a path planner for robots operating in changing environments. My thesis (Double-sided book version).

Abstract

We present a new method for generating collision-free paths for robots operating in changing environments. Our approach is closely related to recent probabilistic roadmap approaches. These planners use preprocessing and query stages, and are aimed at planning many times in the same environment. In contrast, our preprocessing stage creates a representation of the configuration space that can be easily modified in real time to account for changes in the environment. As with previous approaches, we begin by constructing a graph that represents a roadmap in the configuration space, but we do not construct this graph for a specific workspace. Instead, we construct the graph for an obstacle-free workspace, and encode the mapping from workspace cells to nodes and arcs in the graph. When the environment changes, this mapping is used to make the appropriate modifications to the graph, and plans can be generated by searching the modified graph.

As part of our presentation, we discuss the construction of the roadmap, including how samples of the configuration space may be generated and how to connect the samples to form the roadmap. We then discuss the mapping from the workspace to the roadmap, explaining efficient techniques for its generation and representation. We continue with some robustness measures and how these may be used to enhance the robustness of the roadmap. We then present an extension of our method for mobile robots. Finally, we evaluate an implementation of our approach for serial-link manipulators with up to 20 joints.

The project for my master's thesis was to enable this robot to perform useful tasks.

This resulted in my Master's thesis. (Double-sided book version)

Abstract

Providing a uniform interface between a host computer and a robot controller is an important problem in robotics. RCCL, a Robot Control C Library, is a system that provides such an interface. The implementation of RCCL presents three interesting challenges: how to define the robots and to communicate with them, how to implement robot control, and how to design RCCL so that it can be used on more than one type of computer. This thesis discusses these challenges and how our implementation of RCCL confronts them.

An archive of some versions of RCCL can be found here.

Some cool stuff:

• Some robot paths Curtesy of Michael Barbehenn's master's thesis (page 127). (More visually interesting on slower computers.)
• Two example robot paths generated using randomized potential field path planning (from an ECE450 class project): 1 and 2.
• I took ECE498 in the ADSL lab. My project.
• What do you do when the users of your mobile robot forget to attach the battery charger (and also leave the computer and other components turned on) after using the robot? Add more hardware, of course ;).