Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 6 of 6
Full-Text Articles in Physical Sciences and Mathematics
Pyro: A Python-Based Versatile Programming Environment For Teaching Robotics, Doug Blank, Deepak Kumar, Lisa Meeden, Holly Yanco
Pyro: A Python-Based Versatile Programming Environment For Teaching Robotics, Doug Blank, Deepak Kumar, Lisa Meeden, Holly Yanco
Computer Science Faculty Research and Scholarship
In this paper we describe a programming framework called Pyro which provides a set of abstractions that allows students to write platformindependent robot programs. This project is unique because of its focus on the pedagogical implications of teaching mobile robotics via a topdown approach. We describe the background of the project, novel abstractions created, its library of objects, and the many learning modules that have been created from which curricula for different types of courses can be drawn. Finally, we explore Pyro from the students' perspective in a case study.
Self-Motivated, Task-Independent Reinforcement Learning For Robots, Lisa Meeden, James Marshall, Doug Blank
Self-Motivated, Task-Independent Reinforcement Learning For Robots, Lisa Meeden, James Marshall, Doug Blank
Computer Science Faculty Research and Scholarship
This paper describes a method for designing robots to learn self-motivated behaviors rather than externally specified be- haviors. Self-motivation is viewed as an emergent property arising from two competing pressures: the need to accu- rately predict the environment while simultaneously wanting to seek out novelty in the environment. The robot’s inter- nal prediction error is used to generate a reinforcement signal that pushes the robot to focus on areas of high error or nov- elty. A set of experiments are performed on a simulated robot to demonstrate the feasibility of this approach. The simulated robot is based directly on an …
An Emergent Framework For Self-Motivation In Developmental Robotics, James Marshall, Doug Blank, Lisa Meeden
An Emergent Framework For Self-Motivation In Developmental Robotics, James Marshall, Doug Blank, Lisa Meeden
Computer Science Faculty Research and Scholarship
This paper explores a philosophy and connectionist al- gorithm for creating a long-term, self-organizing develop- mental robot control system. This intrinsic algorithm and architecture implements self-motivation by creating a sys- tem capable of anticipating its next state, while simultane- ously attempting to seek out that which it cannot predict. These competing internal pressures are designed to drive the system in a manner reminiscent of a co-evolutionary arms race.
Robot Self-Motivation: Balancing "Boredom" And "Confusion", James Marshall, Doug Blank, Lisa Meeden
Robot Self-Motivation: Balancing "Boredom" And "Confusion", James Marshall, Doug Blank, Lisa Meeden
Computer Science Faculty Research and Scholarship
No abstract provided.
The Governor Architecture: Avoiding Catastrophic Forgetting In Robot Learning, Jeremy Strober, Lisa Meeden, Doug Blank
The Governor Architecture: Avoiding Catastrophic Forgetting In Robot Learning, Jeremy Strober, Lisa Meeden, Doug Blank
Computer Science Faculty Research and Scholarship
The governor architecture is a new method for avoiding catatrophic forgetting in neural networks that is particularly useful in online robot learn- ing. The governor architecture uses a categorizer to identify events and excise long sequences of repetitive data that cause catastrophic forgetting in neural networks trained on robot-based tasks. We examine the performance of several variations of the governor architecture on a number of re- lated localization tasks using a simulated robot. The results show that governed networks perform far better than ungoverned networks. Governored networks are able to reliably and robustly prevent catastrophic forgetting in robot learning tasks.
Avoiding The Karel-The-Robot Paradox: A Framework For Making Sophisticated Robotics Accessible, Doug Blank, Holly Yanco, Deepak Kumar, Lisa Meeden
Avoiding The Karel-The-Robot Paradox: A Framework For Making Sophisticated Robotics Accessible, Doug Blank, Holly Yanco, Deepak Kumar, Lisa Meeden
Computer Science Faculty Research and Scholarship
As educators, we are often faced with the paradox of having to create simplified examples in order to demon- strate complicated ideas. The trick is in finding the right kinds of simplifications—ones that will scale up to the full range of possible complexities we eventually would like our students to tackle. In this paper, we argue that low-cost robots have been a useful first step, but are now becoming a dead-end because they do not allow our stu- dents to explore more sophisticated robotics methods. We suggest that it is time to shift our focus from low- cost robots to …