The last decade has shown an increasing interest on advanced driver assistance systems (ADAS) based on shared control, where automation is continuously supporting the driver at the control level with an adaptive authority. A first look at the literature offers two main research directions: 1) an ongoing effort to advance the theoretical comprehension of shared control, and 2) a diversity of automotive system applications with an increasing number of works in recent years. Yet, a global synthesis on these efforts is not available. To this end, this article covers the complete field of shared control in automated vehicles with an emphasis on these aspects: 1) concept, 2) categories, 3) algorithms, and 4) status of technology. Articles from the literature are classified in theory- and application-oriented contributions. From these, a clear distinction is found between coupled and uncoupled shared control. Also, model-based and model-free algorithms from these two categories are evaluated separately with a focus on systems using the steering wheel as the control interface. Model-based controllers tested by at least one real driver are tabulated to evaluate the performance of such systems. Results show that the inclusion of a driver model helps to reduce the conflicts at the steering. Also, variables such as driver state, driver effort, and safety indicators have a high impact on the calculation of the authority. Concerning the evaluation, driver-in-the-loop simulators are the most common platforms, with few works performed in real vehicles. Implementation in experimental vehicles is expected in the upcoming years.

中文翻译：

---

自动驾驶汽车共享控制综述：理论与应用

过去十年中，人们对基于共享控制的高级驾驶辅助系统 (ADAS) 越来越感兴趣，其中自动化通过自适应权限在控制级别持续支持驾驶员。对文献的初步研究提供了两个主要研究方向：1) 不断努力推进对共享控制的理论理解，以及 2) 汽车系统应用的多样性，近年来作品数量不断增加。然而，目前还没有关于这些努力的全球综合报告。为此，本文涵盖了自动驾驶汽车共享控制的完整领域，重点关注以下几个方面：1) 概念，2) 类别，3) 算法，以及 4) 技术现状。文献中的文章分为面向理论和面向应用的贡献。从这些，耦合和非耦合共享控制之间有明显的区别。此外，这两个类别的基于模型和无模型算法分别进行评估，重点是使用方向盘作为控制接口的系统。由至少一名真实驾驶员测试的基于模型的控制器被制成表格，以评估此类系统的性能。结果表明，包含驾驶员模型有助于减少转向时的冲突。此外，驾驶员状态、驾驶员努力和安全指标等变量对权限的计算有很大影响。在评估方面，驾驶员在环模拟器是最常见的平台，很少有在实车上进行的工作。预计未来几年将在实验车辆中实施。分别评估这两个类别的基于模型和无模型算法，重点是使用方向盘作为控制接口的系统。由至少一名真实驾驶员测试的基于模型的控制器被制成表格，以评估此类系统的性能。结果表明，包含驾驶员模型有助于减少转向时的冲突。此外，驾驶员状态、驾驶员努力和安全指标等变量对权限的计算有很大影响。在评估方面，驾驶员在环模拟器是最常见的平台，很少有在实车上进行的工作。预计未来几年将在实验车辆中实施。分别评估这两个类别的基于模型和无模型算法，重点是使用方向盘作为控制接口的系统。由至少一名真实驾驶员测试的基于模型的控制器被制成表格，以评估此类系统的性能。结果表明，包含驾驶员模型有助于减少转向时的冲突。此外，驾驶员状态、驾驶员努力和安全指标等变量对权限的计算有很大影响。在评估方面，驾驶员在环模拟器是最常见的平台，很少有在实车上进行的工作。预计未来几年将在实验车辆中实施。