位置推定・知覚・予測を統合する深層マルチタスク学習
Deep Multi-Task Learning for Joint Localization, Perception, and Prediction
自動運転で位置推定誤差が知覚や予測に与える問題を分析し、知覚・予測・自己位置推定を同時に学習・実行して計算を共有しながら位置誤差を効率的に補正するシステムを提案した。
著者: John Phillips, Julieta Martinez, Ioan Andrei Bârsan, Sergio Casas, Abbas Sadat, Raquel Urtasun
分類: cs.CV, cs.LG, cs.RO
原文アブストラクト
Over the last few years, we have witnessed tremendous progress on many subtasks of autonomous driving, including perception, motion forecasting, and motion planning. However, these systems often assume that the car is accurately localized against a high-definition map. In this paper we question this assumption, and investigate the issues that arise in state-of-the-art autonomy stacks under localization error. Based on our observations, we design a system that jointly performs perception, prediction, and localization. Our architecture is able to reuse computation between both tasks, and is thus able to correct localization errors efficiently. We show experiments on a large-scale autonomy dataset, demonstrating the efficiency and accuracy of our proposed approach.
