Delving into Mapping Uncertainty for Mapless Trajectory Prediction

2025-07-24

AI Summary

This work addresses trajectory prediction for autonomous driving under map-free conditions, focusing on how mapping uncertainty—arising from imperfect online map construction—affects prediction performance. Method: We identify the ego-vehicle’s future motion state as a key modulator of uncertainty utilization efficacy, and propose an adaptive fusion framework: (i) a scene-gating mechanism conditioned on predicted ego-motion dynamically integrates mapping uncertainty—characterized via covariance modeling and geometric consistency constraints; and (ii) a lightweight self-supervised learning module enhances online mapping reliability. Contribution/Results: The method significantly improves perception–prediction co-adaptation and model interpretability. On nuScenes, it achieves up to 23.6% improvement in map-free trajectory prediction over prior state-of-the-art methods, demonstrating strong generalization and practical applicability.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Intelligent Robots: State Estimation
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Recent advances in autonomous driving are moving towards mapless approaches, where High-Definition (HD) maps are generated online directly from sensor data, reducing the need for expensive labeling and maintenance. However, the reliability of these online-generated maps remains uncertain. While incorporating map uncertainty into downstream trajectory prediction tasks has shown potential for performance improvements, current strategies provide limited insights into the specific scenarios where this uncertainty is beneficial. In this work, we first analyze the driving scenarios in which mapping uncertainty has the greatest positive impact on trajectory prediction and identify a critical, previously overlooked factor: the agent's kinematic state. Building on these insights, we propose a novel Proprioceptive Scenario Gating that adaptively integrates map uncertainty into trajectory prediction based on forecasts of the ego vehicle's future kinematics. This lightweight, self-supervised approach enhances the synergy between online mapping and trajectory prediction, providing interpretability around where uncertainty is advantageous and outperforming previous integration methods. Additionally, we introduce a Covariance-based Map Uncertainty approach that better aligns with map geometry, further improving trajectory prediction. Extensive ablation studies confirm the effectiveness of our approach, achieving up to 23.6% improvement in mapless trajectory prediction performance over the state-of-the-art method using the real-world nuScenes driving dataset. Our code, data, and models are publicly available at https://github.com/Ethan-Zheng136/Map-Uncertainty-for-Trajectory-Prediction.

Problem

• Analyzes impact of mapping uncertainty on trajectory prediction scenarios
• Proposes adaptive integration of map uncertainty via kinematic state forecasts
• Introduces geometry-aligned uncertainty method to enhance prediction accuracy

Innovation

• Proprioceptive Scenario Gating integrates map uncertainty adaptively
• Covariance-based Map Uncertainty aligns with map geometry
• Self-supervised approach enhances online mapping and prediction