Using commodity-off-the-shelf robots (COTSBots) for evolutionary learning from demonstration

Author(s): Terence Soule

Category: Advanced Introduction Invited talk

Abstract: Learning from demonstration (LFD) is an approach to training robots. In learning from demonstration a human demonstrates a specific task to a robot that attempts to learn to imitate the human?s actions. This allows humans to train robots without requiring the human to have any specialized knowledge beyond knowledge of the task domain, e.g. they don?t have to know any programming. However, complex tasks or tasks performed in complex and changing environments require either a very large number of demonstrations (to capture the complexity of the task and the range of possible environments) or a learning algorithm that is very good at generalizing from a relatively small number of demonstrations. Evolutionary computation?s ability to generalize from a small training set, i.e. a small number of demonstrations, makes it a very promising approach for learning from demonstration. But evolutionary computation requires a computationally powerful robot to run the learning algorithms. One approach to this problem is the use of Commodity-off-the-shelf robots (COTSBots). COTSBots are relatively low-cost robots, built from inexpensive, commodity parts, that have the computational power to run evolutionary algorithms on-board and in real-time. This presentation covers both how to build COTSBots and research directions in evolutionary learning from demonstration.

CS-DC'15 talk

Keywords: COTS, evolutionary computation, learning from demonstration, robotics

About the author(s):

• Terence Soule
  Dept of Computer Science
  University of Idaho

Automatic programming via evolution

Author(s): Lee Spector

Category: Advanved Introduction Invited talk

Abstract: Darwinian evolution is a significant architect of complexity in the natural world. The mechanisms by which evolution operates, including mutation, recombination, and selection, can be embodied in software and used to produce complex systems with a range of practical applications. Systems that use evolutionary mechanisms to produce software are called “genetic programming” systems. In this talk I will demonstrate the basic principles of genetic programming and survey some of the results that it has achieved. I will then discuss the potential that genetic programming has for automating the kind of programming work that is normally performed by humans.

CS-DC'15 talk by Lee Spector

Keywords: artificial evolution, evolutionary computing, genetic algorithms, genetic programming, machine learning, artificial intelligence

About the author(s):

• Lee Spector
  Lee Spector is a Professor of Computer Science in the School of Cognitive Science at Hampshire College in Amherst, Massachusetts, and an adjunct professor in the College of Information and Computer Sciences at the University of Massachusetts, Amherst. He received a B.A. in Philosophy from Oberlin College in 1984 and a Ph.D. from the Department of Computer Science at the University of Maryland in 1992. His areas of teaching and research include genetic and evolutionary computation, quantum computation, and intersections between computer science, cognitive science, evolutionary biology, and the arts. He is the Editor-in-Chief of the journal Genetic Programming and Evolvable Machines (published by Springer) and a member of the editorial board of Evolutionary Computation (published by MIT Press). He is a member of the ACM-SIGEVO executive committee and he was named a Fellow of the International Society for Genetic and Evolutionary Computation.
  http://hampshire.edu/lspector/