Abstract
Motion forecasting is a key module in an autonomous driving system. Due to the heterogeneous nature of multi-sourced input, multimodality in agent behavior, and low latency required by onboard deployment, this task is notoriously challenging. To cope with these difficulties, this paper proposes a novel agent-centric model with anchor-informed proposals for efficient multimodal motion prediction. We design a modality-agnostic strategy to concisely encode the complex input in a unified manner. We generate diverse proposals, fused with anchors bearing goal-oriented scene context, to induce multimodal prediction that covers a wide range of future trajectories. Our network architecture is highly uniform and succinct, leading to an efficient model amenable for real-world driving deployment. Experiments reveal that our agent-centric network compares favorably with the state-of-the-art methods in prediction accuracy, while achieving scene-centric level inference latency.
Abstract (translated)
Motion forecasting是自动驾驶系统的关键模块。由于多种输入来源的异质性、Agent 行为的复杂性以及嵌入式部署所需的低延迟,这项任务众所周知地具有挑战性。为了应对这些困难,本文提出了一种具有锚 informed 提案的新型Agent centric模型,以高效多模式运动预测。我们设计了一种modality-agnostic策略,以简洁地统一编码复杂的输入。我们生成各种提案,与具有目标场景上下文的锚融合,以诱导涵盖广泛未来路径的多模式预测。我们的网络架构非常uniform 和简洁,导致一种适用于现实世界驾驶部署的效率模型。实验表明,我们的Agent centric网络在预测精度上与最先进的方法相媲美,同时实现了场景centric 水平推理延迟。
URL
https://arxiv.org/abs/2303.12071