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.

翻译：端到端驾驶系统近期取得了快速进展，尤其是在CARLA平台上。尽管其贡献重大，但这些系统对次要系统组件也引入了改动，因此性能提升的来源尚不明确。我们识别出几乎所有最先进方法中反复出现的两种偏见，这些偏见对CARLA上观察到的进展至关重要：（1）通过强归纳偏差实现横向恢复，偏向于目标点跟踪；（2）通过纵向平均多模态航点预测以实现减速。我们研究了这些偏见的缺陷，并提出了原则性替代方案。通过融入我们的见解，我们开发了TF++，这是一种简单的端到端方法，在Longest6和LAV基准测试中排名第一，在Longest6上相比先前最佳工作提升了11个驾驶分数。