학술논문
The NVIDIA PilotNet Experiments
Document Type
Working Paper
Author
Bojarski, Mariusz; Chen, Chenyi; Daw, Joyjit; Değirmenci, Alperen; Deri, Joya; Firner, Bernhard; Flepp, Beat; Gogri, Sachin; Hong, Jesse; Jackel, Lawrence; Jia, Zhenhua; Lee, BJ; Liu, Bo; Liu, Fei; Muller, Urs; Payne, Samuel; Prasad, Nischal Kota Nagendra; Provodin, Artem; Roach, John; Rvachov, Timur; Tadimeti, Neha; van Engelen, Jesper; Wen, Haiguang; Yang, Eric; Yang, Zongyi
Source
Subject
Language
Abstract
Four years ago, an experimental system known as PilotNet became the first NVIDIA system to steer an autonomous car along a roadway. This system represents a departure from the classical approach for self-driving in which the process is manually decomposed into a series of modules, each performing a different task. In PilotNet, on the other hand, a single deep neural network (DNN) takes pixels as input and produces a desired vehicle trajectory as output; there are no distinct internal modules connected by human-designed interfaces. We believe that handcrafted interfaces ultimately limit performance by restricting information flow through the system and that a learned approach, in combination with other artificial intelligence systems that add redundancy, will lead to better overall performing systems. We continue to conduct research toward that goal. This document describes the PilotNet lane-keeping effort, carried out over the past five years by our NVIDIA PilotNet group in Holmdel, New Jersey. Here we present a snapshot of system status in mid-2020 and highlight some of the work done by the PilotNet group.