论文/arXiv 2308.14329·2 个月前

SSIL：面向端到端驾驶的自监督模仿学习

SSIL无需驾驶指令数据或预训练模型，利用激光雷达估计位姿生成伪转角，在三个基准数据集验证端到端驾驶。

AI 整理

• 本体 SDK 与控制
• 数据与采集
• 具身模型

原文链接：SSIL: Self-Supervised Imitation Learning for End-to-End Driving（arXiv 2308.14329 · 发布日期：2026-08-01）

SSIL: Self-Supervised Imitation Learning for End-to-End Driving

SSIL无需驾驶指令数据或预训练模型，利用激光雷达估计位姿生成伪转角，在三个基准数据集验证端到端驾驶。

核心要点

• 端到端驾驶需大量人类驾驶控制数据，公开数据场景有限且控制数据难获取。
• SSIL由当前与前一时刻车辆位姿构造伪转向角，无需驾驶命令数据或预训练模型。
• 提出CACA，用高层指令作为视觉信息条件信号，改进视觉编码器条件化。
• 三个基准数据集实验显示，SSIL精度接近监督学习，伪标签预测器和CACA优于对比方法。

验证范围与局限：验证范围为三个基准数据集上的数值实验。

英文摘要 (Abstract)

In autonomous driving, the end-to-end (E2E) driving approach that predicts vehicle control signals directly from sensor data is rapidly gaining attention. To learn a safe E2E driving system, one needs an extensive amount of driving data and human intervention. Vehicle control data is constructed by many hours of human driving, and it is challenging to construct large vehicle control datasets. Often, publicly available driving datasets are collected with limited driving scenes, and collecting vehicle control data is only available by vehicle manufacturers. To address these challenges, this paper proposes the first self-supervised learning framework, Self-Supervised Imitation Learning (SSIL), for E2E driving. The proposed SSIL framework can learn vision-based E2E driving networks without using driving command data or a pre-trained model. To construct pseudo steering angle data, proposed SSIL predicts a pseudo target from the vehicle's poses at the current and previous time points that are estimated with light detection and ranging sensors. In addition, we propose a new cross-attention-based conditioning approach (CACA) for a vision encoder in E2E driving, where a high-level instruction serves as the conditioning signal for visual information. Our numerical experiments with three different benchmark datasets demonstrate that the proposed SSIL framework achieves very comparable E2E driving accuracy with the supervised learning counterpart. Furthermore, the proposed pseudo-label predictor outperformed an existing one using proportional integral derivative controller, and proposed CACA achieved superior performance over existing conditioning approaches.

作者：Jin Bok Park, Jinkyu Lee, Muhyun Back, Hyun-Min Han, Tianwei Ma, Sang Min Won, Sung Soo Hwang, Il Yong Chun

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2308.14329：SSIL: Self-Supervised Imitation Learning for End-to-End Driving访问 2026-10-21