- Ph.D., Robotics / Mechanical Engineering, Oregon State University, 2015
- M.S., Mechanical Engineering, Oregon State University, 2012
- B.S., Mechanical Engineering, Arizona State University, 2010
Logan Yliniemi received his Ph.D. with a dual robotics/mechanical engineering concentration from Oregon State University in 2015. His research exists at the interface of the fields of multi-objective optimization and multiagent systems. He has developed computationally inexpensive algorithms for multi-objective optimization that achieve performance at or above other state-of-the-art methods at one tenth of the computation cost. His work has been published in various international venues, including AI Magazine, the International Conference on Autonomous Agents and Multiagent Systems (AAMAS), the Genetic and Evolutionary Computation Conference (GECCO), and the International Conference on Simulated Evolution and Learning (SEAL).
His work has been funded by NASA, the U.S. Department of Energy, and the National Science Foundation.
Dr. Yliniemi has taught undergraduate and graduate courses in controls, dynamics, optimization, and robotics.
- Unmanned aerial systems (UAS/UAV)
- Multiagent systems
- Learning controllers
- Stochastic optimization
- Multi-objective problems
- Transfer learning
- Evolutionary algorithms
- Probabilistic robotics
- Introduction to System Control (ME 410)
Selected and recent publications
- Yliniemi, L. and Agogino, A. and Tumer, K. Multi-Robot Coordination for Space Exploration. AI Magazine, 2015.
- Yliniemi, L. and Tumer, K. PaCcET: An Objective Space Transformation to Iteratively Convexify the Pareto Front. In: 10th International Conference on Simulated Evolution and Learning (SEAL2014), 2014.
- Yliniemi, L. and Tumer, K. Multi-Objective Multiagent Credit Assignment through Difference Rewards in Reinforcement Learning. In: 10th International Conference on Simulated Evolution and Learning (SEAL2014), 2014.
- Devlin, S. and Yliniemi, L. and Kudenko, D. and Tumer, K. Potential-Based Difference Rewards for Multiagent Reinforcement Learning. In: 13th International Conference on Autonomous Agents and Multiagent Systems (AAMAS2014), 2014.