Miniature Autonomy as One Important Testing Means in the Development of Machine Learning Methods for Autonomous Driving: How ML-based Autonomous Driving could be Realized on a 1:87 Scale

摘要

In the current state of autonomous driving machine learning methods are dominating, especially for the environment recognition. For such solutions, the reliability and the robustness is a critical question. A "miniature autonomy" with model vehicles at a small scale could be beneficial for different reasons. Examples are (1) the testability of dangerous and close-to-crash edge cases, (2) the possibility to test potentially dangerous concepts as end-to-end learning or combined inference and learning phases, (3) the need to optimize algorithms thoroughly, and (4) a potential reduction of test mile counts. Presented is the motivation for miniature autonomy and a discussion of testing of machine learning methods. Finally, two currently set up platforms including one with an FPGA-based TPU for ML acceleration are described.