Active Optimization and Self Driving Cars
Jeff Schneider · Adaptive Agents and Multi-Agents Systems · 2017
Self driving cars hold the promise of making transportation safer and more efficient than ever before possible. They will also be among the most complex robotic systems ever fielded and thus require an unprecedented level of machine learning throughout to achieve their desired performance. These learners create an ever-changing environment for all algorithms operating in the system and optimizing their performance will become a perpetual activity rather than a one-off task. I will present active optimization methods and their application in robotics applications, focusing on scaling up the dimensionality and managing multi-fidelity evaluations. I will summarize lessons learned and thoughts on future directions as these methods move into fielded systems. Finally, I will describe current efforts on self driving cars and give some views on the future of them.