用进化算法优化轻量CNN模型，实现实时自动转向预测。
Evolutionary Hyperparameter Optimization to Find Lightweight CNN Models for Autonomous Steering
- 采用( N+M)进化策略动态调整卷积核大小和网络结构。
- 模型体积显著减小，仍保持与基准模型相当的转向预测精度。
- 适合资源受限场景下的自动驾驶系统部署，如低成本车载设备。
本研究利用( N+M)进化策略（ES）结合1/5成功法则，优化卷积神经网络（CNN）和全连接网络（DNN）在自主转向任务中的性能。目标是构建一个轻量级CNN模型，实现实时转向角度预测，模拟人类在预设路径上的驾驶行为。数据来自LTU ACTor自动驾驶平台采集的驾驶场景，包含不同路径方向和驾驶风格，数据集为时间戳图像，标注了转向角度，并已预处理以聚焦关键视觉信息。初始阶段训练基础CNN模型，随后通过进化策略优化，显著压缩模型规模，同时保持较高的预测准确性。结果表明，该方法可有效平衡计算效率与性能，验证了轻量级神经网络在实时自动驾驶系统中的可行性。研究不仅推动了进化算法在自动驾驶中的应用，也为低成本、可扩展的自驾车技术部署奠定基础。
原文摘要 · Abstract (English)
This research investigates the optimization of Convolutional and Dense Neural Networks (CNNs and DNNs) for autonomous steering using the (N+M) Evolution Strategy (ES) with the 1/5th success rule. The primary objective is to develop a lightweight CNN based model capable of real-time steering angle prediction, mimicking human driving behavior on predefined paths. The ES algorithm automates hyperparameter tuning, dynamically adjusting parameters such as filter sizes and layer configurations. Data collection encompasses driving scenarios recorded via the LTU ACTor autonomous driving platform, including variations in path direction and driving style. The very small dataset consists of timestamped images labeled with steering angles and pre-processed to focus on relevant visual information. Initial experiments involve training a baseline CNN model, which is then refined using ES to significantly reduce the size of the model while maintaining competitive predictive accuracy. The results highlight the viability of lightweight neural network architectures for real-time autonomous systems, striking a balance between computational efficiency and performance. This study not only advances research initiatives on the use of evolutionary algorithms for autonomous driving applications but also lays the foundation for the deployment of cost-effective and scalable solutions in self-driving technology.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。