Using Educational Robotics to Motivate Complete AI Solutions

Robotics is a remarkable domain that may be successfully employed in the classroom both to motivate students to tackle hard AI topics and to provide students experience applying AI representations and algorithms to real-world problems. This article uses two example robotics problems to illustrate these themes. We show how the robot obstacle-detection problem can motivate learning neural networks and Bayesian networks. We also show how the robot-localization problem can motivate learning how to build complete solutions based on particle filtering. Since these lessons can be replicated on many low-cost robot platforms they are accessible to a broad population of AI students. We hope that by outlining our educational exercises and providing pointers to additional resources we can help reduce the effort expended by other educators. We believe that expanding handson active learning to additional AI classrooms provides value both to the students and to the future of the field itself. One particularly compelling domain is robotics. Robotics combines the fantasy of science fiction with practical real-world applications and engages both the imaginative and sensible sides of students. In addition to providing inspiration, exploring artificial intelligence representations and algorithms using robotics helps students to learn complete solutions. A complete solution is one in which a student considers all the details of implementing AI algorithms in a realworld environment. These details range from system design, to algorithm selection and implementation, to behavior analysis and experimentation, to making the solution robust in the face of uncertainty. In our classes we find that robotics problems encourage students to investigate how AI algorithms interact with each other, with non-AI solutions, and with a real-world environment. Students investigate how to convert sensor data into internal data structures, how to weigh the costs and benefits of physical exploration, whether or not to use offline simulation and tools, and how to deal with the severe resource limitations and time constraints of embedded computation. Despite the added costs of building complete solutions, experience with real-world environments helps ground lessons and stimulates thinking about new challenges and solutions.