ProIn: Learning to Predict Trajectory Based on Progressive Interactions for Autonomous Driving
Not on the map. Why?
Abstract (arXiv)
Accurate motion prediction of pedestrians, cyclists, and other surrounding vehicles (all called agents) is very important for autonomous driving. Most existing works capture map information through an one-stage interaction with map by vector-based attention, to provide map constraints for social interaction and multi-modal differentiation. However, these methods have to encode all required map rules into the focal agent's feature, so as to retain all possible intentions' paths while at the meantime to adapt to potential social interaction. In this work, a progressive interaction network is proposed to enable the agent's feature to progressively focus on relevant maps, in order to better learn agents' feature representation capturing the relevant map constraints. The network progressively encode the complex influence of map constraints into the agent's feature through graph convolutions at the following three stages: after historical trajectory encoder, after social interaction, and after multi-modal differentiation. In addition, a weight allocation mechanism is proposed for multi-modal training, so that each mode can obtain learning opportunities from a single-mode ground truth. Experiments have validated the superiority of progressive interactions to the existing one-stage interaction, and demonstrate the effectiveness of each component. Encouraging results were obtained in the challenging benchmarks.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 32 of its 46 references that are in the map. First posted on arXiv 25 Mar 2024.
Builds on
32 of 46 references.
References · 32
- 2017Attention Is All You Needcited by 59,932
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 728
- 2023Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecastingcited by 701
- 2020VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representationcited by 528
- 2020Learning Lane Graph Representations for Motion Forecastingcited by 380
- 2021DenseTNT: End-to-end Trajectory Prediction from Dense Goal Setscited by 292
- 2018Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networkscited by 289
- 2022Wayformer: Motion Forecasting via Simple & Efficient Attention Networkscited by 279
- 2022Motion Transformer with Global Intention Localization and Local Movement Refinementcited by 267
- 2021MultiPath++: Efficient Information Fusion and Trajectory Aggregation for Behavior Predictioncited by 246
- 2021Multimodal Motion Prediction with Stacked Transformerscited by 207
20 more
- 2021IntentNet: Learning to Predict Intention from Raw Sensor Datacited by 158
- 2021GOHOME: Graph-Oriented Heatmap Output for future Motion Estimationcited by 146
- 2021HOME: Heatmap Output for future Motion Estimationcited by 122
- 2019Rules of the Road: Predicting Driving Behavior with a Convolutional Model of Semantic Interactionscited by 117
- 2022HDGT: Heterogeneous Driving Graph Transformer for Multi-Agent Trajectory Prediction via Scene Encodingcited by 109
- 2021THOMAS: Trajectory Heatmap Output with learned Multi-Agent Samplingcited by 101
- 2019Overcoming Limitations of Mixture Density Networks: A Sampling and Fitting Framework for Multimodal Future Predictioncited by 96
- 2021TPCN: Temporal Point Cloud Networks for Motion Forecastingcited by 94
- 2021Multi-modal Motion Prediction with Transformer-based Neural Network for Autonomous Drivingcited by 73
- 2022GoRela: Go Relative for Viewpoint-Invariant Motion Forecastingcited by 68
- 2022GANet: Goal Area Network for Motion Forecastingcited by 49
- 2023ProphNet: Efficient Agent-Centric Motion Forecasting with Anchor-Informed Proposalscited by 47
- 2023MacFormer: Map-Agent Coupled Transformer for Real-time and Robust Trajectory Predictioncited by 32
- 2023Real-Time Motion Prediction via Heterogeneous Polyline Transformer with Relative Pose Encodingcited by 32
- 2020Trajectory Prediction in Autonomous Driving with a Lane Heading Auxiliary Losscited by 30
- 2023Dynamic Scenario Representation Learning for Motion Forecasting with Heterogeneous Graph Convolutional Recurrent Networkscited by 27
- 2022Path-Aware Graph Attention for HD Maps in Motion Predictioncited by 23
- 2021Trajectory Prediction with Graph-based Dual-scale Context Fusioncited by 19
- 2022Diverse Multiple Trajectory Prediction Using a Two-stage Prediction Network Trained with Lane Losscited by 12
- 2022BANet: Motion Forecasting with Boundary Aware Networkcited by 10
Built on by
Citing papers per year: 2024: 1; 2025: 0; 2026: 2.
3 papers.