AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

RAG-TP: A General Framework for Vehicle Trajectory Prediction via Retrieval-Augmented Generation

Ziyi Wang, Yang Zhang, Guijian Tang, Chao Zhang, Shibo Zhang, Xueqiong Li, Shaowu Yang

CVPR 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Multimodal trajectory prediction

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add retrieval from a knowledge base (without map information) (ablation)RAG-TP base model · Argoverse 2 validationminADE6: 0.81 -> 0.73Improved
add map information to the RAG knowledge base (ablation)RAG-TP · Argoverse 2 validationminADE6: 0.73 -> 0.60 (full model)Improved
use behavioral K-Means clustering instead of random sampling to build the knowledge base (ablation)RAG-TP · Argoverse 2 validationminADE6: 0.68 -> 0.60Improved
add Retrieval-Driven MoE fusion (ablation)RAG-TP · Argoverse 2 validationminADE6: 0.65 -> 0.60Improved
plug RAG module into MTRMTR · Argoverse 2minADE6: 0.82 -> 0.76Improved
plug RAG module into Forecast-MAEForecast-MAE · Argoverse 2minADE6: 0.80 -> 0.73Improved
replace online map with retrieved priors (map-free RAG-TP vs MLB-Traj)RAG-TP · Argoverse 1 map-freeminFDE6: minADE6 0.77 -> 0.72; minFDE6 1.25 -> 1.31Mixed
retrieve from the target domain's knowledge base (zero-shot, trained on Argoverse 2, evaluated on WOMD) (ablation)RAG-TP · WOMD zero-shotminADE6: 1.32 -> 1.05Improved
retrieve from the target domain's knowledge base (zero-shot, trained on WOMD, evaluated on Argoverse 2) (ablation)RAG-TP · Argoverse 2 zero-shotminADE6: 0.98 -> 0.75Improved
train and retrieve on unified Argoverse 2 + WOMD dataset (ablation)RAG-TP · Argoverse 2 / WOMD cross-domainminADE6: 0.67 -> 0.63 (AV2); 0.72 -> 0.69 (WOMD)Improved
add RAG retrieval and fusion at inferenceRAG-TP · Latency, RTX 4090End-to-end latency (ms): 23.6 -> 35.9 ms; memory 4.8 GBHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy