Autonomous driving relies on computationally intensive perception pipelines to continuously detect and track objects in the surrounding environment. While some objects are key to plan safe and effective maneuvers, others may not be relevant and have no impact on the autonomous vehicle's driving decisions. Focusing on relevant objects allows a more efficient usage of available computational resources, reduces processing latencies, and limits the downstream propagation of perception noise. In this work, we propose a novel self-supervised approach based on counterfactual analysis to develop a relevance model - an AI-based tool that quantifies the relevance of objects for an autonomous vehicle. To demonstrate the potential of the proposed approach, we train a relevance model on a synthetic causal dataset generated in a selected urban scenario. Results show that the relevance model is able to accurately estimate the objects' relevance with millisecond-level latency, enabling real-time relevance estimation also in high-density scenarios. We also show that the relevance model can be used to build relevance heatmaps that offer valuable insights into the autonomous vehicle's driving policy and can be used to proactively inform perception and planning tasks. We openly release both the relevance model and the causal dataset.

翻译：自动驾驶依赖于计算密集型的感知流水线，以持续检测和跟踪周围环境中的物体。部分物体对于规划安全有效的行驶操作至关重要，而另一些物体则可能无关紧要，对自动驾驶车辆的驾驶决策毫无影响。聚焦于相关物体可更高效地利用可用计算资源，降低处理延迟，并限制感知噪声的下游传播。本文提出了一种基于反事实分析的新型自监督方法，用于开发相关性模型——一种基于人工智能的工具，可量化物体对自动驾驶车辆的相关性。为展示所提方法的潜力，我们基于选定城区场景生成的合成因果数据集训练了一个相关性模型。结果表明，该相关性模型能够以毫秒级延迟准确估计物体的相关性，即使在密集场景中也能实现实时相关性估算。我们还证明，该相关性模型可用于构建相关性热力图，为自动驾驶车辆的驾驶策略提供宝贵洞察，并主动为感知与规划任务提供信息。我们公开了相关性模型及因果数据集。