Speeding up deep neural network-based planning of local car maneuvers via efficient B-spline path construction
Piotr Kicki,Piotr Skrzypczyński,Piotr Kicki,Piotr Skrzypczyński
This paper demonstrates how an efficient repre-sentation of the planned path using B-splines, and a construction procedure that takes advantage of the neural network's inductive bias, speed up both the inference and training of a DNN-based motion planner. We build upon our recent work on learning local car maneuvers from past experience using a DNN architecture, introducing a novel B-spline path c...
