CUQDS: Conformal Uncertainty Quantification under Distribution Shift for Trajectory Prediction

2024-06-17

AI Summary

To address unreliable uncertainty quantification and the absence of online calibration for trajectory prediction under distributional shift in autonomous driving, this paper proposes a novel framework integrating Learning-based Gaussian Process Regression (L-GPR) with p-value-based conformal prediction (Conformal P). Methodologically, L-GPR is first embedded into the neural network backbone, enabling joint optimization of uncertainty-aware and accuracy-oriented loss functions; during inference, Conformal P performs distribution-shift-adaptive online confidence calibration. Evaluated on Argoverse and nuScenes benchmarks, the framework reduces coverage deviation by 38%, expected calibration error (ECE) by 52%, and average displacement error (ADE) by 7%, demonstrating substantial improvements in both uncertainty estimation reliability and prediction accuracy.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Uncertainty Representations
• Natural Language Processing: Safety and Robustness

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Trajectory prediction models that can infer both finite future trajectories and their associated uncertainties of the target vehicles in an online setting (e.g., real-world application scenarios) is crucial for ensuring the safe and robust navigation and path planning of autonomous vehicle motion. However, the majority of existing trajectory prediction models have neither considered reducing the uncertainty as one objective during the training stage nor provided reliable uncertainty quantification during inference stage under potential distribution shift. Therefore, in this paper, we propose the Conformal Uncertainty Quantification under Distribution Shift framework, CUQDS, to quantify the uncertainty of the predicted trajectories of existing trajectory prediction models under potential data distribution shift, while considering improving the prediction accuracy of the models and reducing the estimated uncertainty during the training stage. Specifically, CUQDS includes 1) a learning-based Gaussian process regression module that models the output distribution of the base model (any existing trajectory prediction or time series forecasting neural networks) and reduces the estimated uncertainty by additional loss term, and 2) a statistical-based Conformal P control module to calibrate the estimated uncertainty from the Gaussian process regression module in an online setting under potential distribution shift between training and testing data.

Problem

• Vehicle trajectory prediction
• Uncertainty reduction
• Reliable uncertainty estimation

Innovation

• CUQDS
• Uncertainty Quantification
• Adaptive Prediction