The quest for real-time, accurate environmental perception is pivotal in the evolution of autonomous driving technologies. In response to this challenge, we present DyRoNet, a Dynamic Router Network that innovates by incorporating low-rank dynamic routing to enhance streaming perception. DyRoNet distinguishes itself by seamlessly integrating a diverse array of specialized pre-trained branch networks, each meticulously fine-tuned for specific environmental contingencies, thus facilitating an optimal balance between response latency and detection precision. Central to DyRoNet's architecture is the Speed Router module, which employs an intelligent routing mechanism to dynamically allocate input data to the most suitable branch network, thereby ensuring enhanced performance adaptability in real-time scenarios. Through comprehensive evaluations, DyRoNet demonstrates superior adaptability and significantly improved performance over existing methods, efficiently catering to a wide variety of environmental conditions and setting new benchmarks in streaming perception accuracy and efficiency. Beyond establishing a paradigm in autonomous driving perception, DyRoNet also offers engineering insights and lays a foundational framework for future advancements in streaming perception. For further information and updates on the project, visit https://tastevision.github.io/DyRoNet/.

翻译：实现实时、准确的环境感知是自动驾驶技术演进中的核心挑战。为应对该问题，我们提出DyRoNet——一种通过引入低秩动态路由机制增强流式感知性能的动态路由网络。DyRoNet的独特之处在于其能够无缝整合一系列经过专业微调的预训练分支网络（针对特定环境场景），从而在响应延迟与检测精度之间实现最优平衡。其架构核心为Speed Router模块，该模块采用智能路由机制，将输入数据动态分配至最适配的分支网络，确保实时场景中性能适应性的提升。通过全面评估，DyRoNet展现出优于现有方法的卓越适应性与性能提升，可高效应对多样化的环境条件，并在流式感知精度与效率方面树立新标杆。除确立自动驾驶感知新范式外，DyRoNet还为工程实践提供洞见，并为流式感知领域的未来发展奠定基础框架。项目详情与更新请参见https://tastevision.github.io/DyRoNet/。