Paper Reading AI Learner

MGTraj: Multi-Granularity Goal-Guided Human Trajectory Prediction with Recursive Refinement Network

2025-09-11 07:13:57
Ge Sun, Jun Ma

Abstract

Accurate human trajectory prediction is crucial for robotics navigation and autonomous driving. Recent research has demonstrated that incorporating goal guidance significantly enhances prediction accuracy by reducing uncertainty and leveraging prior knowledge. Most goal-guided approaches decouple the prediction task into two stages: goal prediction and subsequent trajectory completion based on the predicted goal, which operate at extreme granularities: coarse-grained goal prediction forecasts the overall intention, while fine-grained trajectory completion needs to generate the positions for all future timesteps. The potential utility of intermediate temporal granularity remains largely unexplored, which motivates multi-granularity trajectory modeling. While prior work has shown that multi-granularity representations capture diverse scales of human dynamics and motion patterns, effectively integrating this concept into goal-guided frameworks remains challenging. In this paper, we propose MGTraj, a novel Multi-Granularity goal-guided model for human Trajectory prediction. MGTraj recursively encodes trajectory proposals from coarse to fine granularity levels. At each level, a transformer-based recursive refinement network (RRN) captures features and predicts progressive refinements. Features across different granularities are integrated using a weight-sharing strategy, and velocity prediction is employed as an auxiliary task to further enhance performance. Comprehensive experimental results in EHT/UCY and Stanford Drone Dataset indicate that MGTraj outperforms baseline methods and achieves state-of-the-art performance among goal-guided methods.

Abstract (translated)

准确的人类轨迹预测对于机器人导航和自动驾驶至关重要。近期的研究表明,通过引入目标引导可以显著提高预测精度,减少不确定性,并利用先验知识。大多数目标导向的方法将预测任务分解为两个阶段:首先进行目标预测,然后根据已预测的目标来完成后续的轨迹生成。这两个阶段在粒度上存在极端差异:粗粒度的目标预测用于预测总体意图,而细粒度的轨迹完成则需要生成所有未来时间步长的位置信息。然而,中间时间粒度的潜在价值仍未被充分探索,这促使了多粒度轨迹建模的需求。尽管先前的工作已经展示了多粒度表示能够捕捉到人类动态和运动模式的不同尺度,但如何有效地将这一概念整合进目标导向框架中仍具有挑战性。 在本文中,我们提出了MGTraj(Multi-Granularity goal-guided Trajectory prediction),这是一种新颖的多粒度目标引导的人类轨迹预测模型。MGTraj通过递归编码从粗到细的不同粒度层级的轨迹提案来工作。在每个粒度层次上,基于变压器的递归细化网络(RRN)捕获特征并进行逐步精细化预测。不同粒度级别的特性利用权重共享策略进行整合,并且采用速度预测作为辅助任务进一步提升性能。 全面实验结果显示,在EHT/UCY和Stanford Drone数据集中,MGTraj在基线方法中表现出色,并且在目标导向的方法中达到了最先进的性能水平。

URL

https://arxiv.org/abs/2509.09200

PDF

https://arxiv.org/pdf/2509.09200.pdf


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model LLM Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Robot Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Time_Series Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot