By day, Anthony Francis teaches robots to learn; by night he writes science fiction and draws comic books. Anthony has been studying artificial intelligence for forty years, and has a quarter century's experience in applying artificial intelligence to information technology in areas including reinforcement learning, robotics, and search. For the past eight years he has worked primarily on robotics, including deep reinforcement learning for robot navigation, principles of social robotics, and language model planning for robot control.
-
Francis, A., Faust, A., Chiang, H., Hsu, J., Kew, J., Fiser, M., Lee, T. (2020) Long-Range Indoor Navigation with PRM-RL. IEEE Transactions on Robotics 36 (4), 1115-1134, arxiv.org/abs/1902.09458
-
Francis, A. (2021). Template Tricks for Data-Driven Behavior Trees, Game AI Pro Online Edition www.gameaipro.com/GameAIProOnlineEdition2021/
-
Francis, A. (2017) Overcoming Pitfalls in Behavior Tree Design. Game AI Pro 3: Collected Wisdom of Game AI Professionals, 115-126, A K Peters/CRC Press.
-
Francis, A., Mehta, M., Ram, A. (2009) Emotional Memory and Adaptive Personalities. In Vallverdu, J & Casacuberta, D., (Eds.) Handbook of Research on Synthetic Emotions and Sociable Robotics: New Applications in Affective Computing and Artificial Intelligence. Information Science Publishing.
-
Francis, A., Devaney, M., Ram, A., Santamaria, J. (2001) Scaling Spreading Activation for Production Information Retrieval. In Arabina, H.R., (Ed.) Proc. of the International Conference on Artificial Intelligence IC-AI’2001,. CSREA Press.
-
Francis, A., Ram, A., Devaney, M. (2000). IRIA: The Information Research Intelligent Assistant. In Arabina, H.R., (Ed.) Proc. of the International Conference on Artificial Intelligence IC-AI’2000. CSREA Press.
-
Francis, A. (2000) Context-Sensitive Asynchronous Memory: A General Experience-Based Method for Managing Information Access in Cognitive Agents. Doctoral dissertation. College of Computing, Georgia Institute of Technology
-
Francis, A., Ram, A. (1995). A comparative utility analysis of case-based reasoning and control-rule learning systems. European Conference on Machine Learning, 138-150