エンドツーエンド自動運転モデルに潜むバイアス
Hidden Biases of End-to-End Driving Models
CARLA上のエンドツーエンド自動運転モデルに共通する2つのバイアス（目標点追従への強い帰納バイアスとマルチモーダル経路予測の縦方向平均化）を特定し、その欠点を分析して代替手法を提案。これによりLongest6とLAVベンチマークで首位となるTF++を開発した。
著者: Bernhard Jaeger, Kashyap Chitta, Andreas Geiger
分類: cs.CV, cs.AI, cs.LG, cs.RO
原文アブストラクト
End-to-end driving systems have recently made rapid progress, in particular on CARLA. Independent of their major contribution, they introduce changes to minor system components. Consequently, the source of improvements is unclear. We identify two biases that recur in nearly all state-of-the-art methods and are critical for the observed progress on CARLA: (1) lateral recovery via a strong inductive bias towards target point following, and (2) longitudinal averaging of multimodal waypoint predictions for slowing down. We investigate the drawbacks of these biases and identify principled alternatives. By incorporating our insights, we develop TF++, a simple end-to-end method that ranks first on the Longest6 and LAV benchmarks, gaining 11 driving score over the best prior work on Longest6.
