-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2023_CVPR, author = {Wang, Xishun and Su, Tong and Da, Fang and Yang, Xiaodong}, title = {ProphNet: Efficient Agent-Centric Motion Forecasting With Anchor-Informed Proposals}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21995-22003} }
ProphNet: Efficient Agent-Centric Motion Forecasting With Anchor-Informed Proposals
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 forecasting. 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 context, to induce multimodal prediction that covers a wide range of future trajectories. The network architecture is highly uniform and succinct, leading to an efficient model amenable for real-world 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.
Related Material