Machine Learning Methods for Local Motion Planning: A Study of End-to-End vs. Parameter Learning (2021)
Zifan Xu, Xuesu Xiao, Garrett Warnell, Anirudh Nair, and Peter Stone
While decades of research efforts have been devoted to developing classical autonomous navigation systems to move robots from one point to another in a collision-free manner, machine learning approaches to navigation have been recently proposed to learn navigation behaviors from data. Two representative paradigms are end-to-end learning (directly from perception to motion) and parameter learning (from perception to parameters used by a classical underlying planner). These two types of methods are believed to have complementary pros and cons: parameter learning is expected to be robust to different scenarios, have provable guarantees, and exhibit explainable behaviors; end-to-end learning does not require extensive engineering and has the potential to outperform approaches that rely on classical systems. However, these beliefs have not been verified through real-world experiments in a comprehensive way. In this paper, we report on an extensive study to compare end-to-end and parameter learning for local motion planners in a large suite of simulated and physical experiments. In particular, we test the performance of end-to-end motion policies, which directly compute raw motor commands, and parameter policies, which compute parameters to be used by classical planners, with different inputs (e.g., raw sensor data, costmaps), and provide an analysis of the results.
In Proceedings of the 2021 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR 2021), New York, USA, October 2021.

Peter Stone Faculty pstone [at] cs utexas edu
Garrett Warnell Research Scientist warnellg [at] cs utexas edu