Behavior analysis focuses on what environmental factors occur to establish learning in humans and animals. Since the 1990s attempts have been made to take information learned in this area and help develop robots that can learn from the same environmental factors. Often this is referred to as selectionist approaches to robotics. This group is a special interest group of the Association for Behavior Analysis International(http://www.abainternational.org/ ). The group is focused on research and development in the area of improving robots to learn by consequences. Topics covered include reinforment learning, neural networks, stacked neural networks, matching models of reinforcement, motor learning, and building of relational frames, acquisition of communication skills and personality in robots from behavior analytic models. This group hopes to further the discussion between behavior analysts and robotics engineers. If you want to discuss what behavior analysis can contribute to lasers learning to target cancer cells and not healthy cells or how to create a robot that can find a human in a fire and get him out of a fire this is then this is the group for you.

In addition, Robots offer a new way to assess how basic principles of learning combine to select complex behavior as Dave Palmer stated describing a book by Betsy Constantine and William Hutchenson"Owing to ethical constraints on researchers, the scientific study of human behavior has nearly exhausted the veins that can be explored by its experimental procedures. Breakthroughs in our understanding of human behavior will come, ironically, from our simulations of it. We understand much about fundamental principles of behavior, but these principles are like the elements in atomic theory. How complex behavior emerges from the action of these principles as humans interact with the relentless blizzard of environmental events cannot be understood without the aid of computers in simulations of the sort discussion."