CAS CN810: Topics in adaptive mobile robotics: This course, first offered in 2010, is a hands-on introduction to the challenges of implementing adaptive behavior on an iRobot Create platform. Using simple and reliable hardware, students will design and implement computational models that allow the robot to perform behavioral functions, such as learning to approach or avoid objects and locations in its environment. Students are expected to have a sufficient interdisciplinary grounding in the fundamentals of computational modeling of mammalian vision, planning, and navigation to read primary research sources.Projects will be executed by small groups, and will require the use of Cog Ex Machina (Cog), the software framework realized by HP and Boston University in the context of the DARPA SyNAPSE project. Students will have the chance to use the ASIMOV robotic interface. This will enable students to rapidly prototype large scale (millions of neurons, billions of synapses) on high-performance computing resources, testing them in realistic virtual environments. Cog has been successfully interfaced to land and aerial robots, and students will leverage the work done in the Neuromorphics Lab to bootstrap efforts. The 2011 edition will have an early visit to iRobot.
Links to the 2010 and 2011 class projects blog entries: