Reliable Multimodal Trajectory Prediction via Error Aligned Uncertainty Optimization
This work addresses the need for trustworthy uncertainty estimates in safety-critical domains such as automated driving, representing an incremental advance in calibration methods.
The paper tackles the problem of unreliable uncertainty quantification in deep neural networks for safety-critical applications like automated driving by proposing an error aligned uncertainty optimization method, resulting in improvements of 1.69% and 4.69% in average displacement error and 17.22% and 19.13% in uncertainty correlation with model error on two baselines.
Reliable uncertainty quantification in deep neural networks is very crucial in safety-critical applications such as automated driving for trustworthy and informed decision-making. Assessing the quality of uncertainty estimates is challenging as ground truth for uncertainty estimates is not available. Ideally, in a well-calibrated model, uncertainty estimates should perfectly correlate with model error. We propose a novel error aligned uncertainty optimization method and introduce a trainable loss function to guide the models to yield good quality uncertainty estimates aligning with the model error. Our approach targets continuous structured prediction and regression tasks, and is evaluated on multiple datasets including a large-scale vehicle motion prediction task involving real-world distributional shifts. We demonstrate that our method improves average displacement error by 1.69% and 4.69%, and the uncertainty correlation with model error by 17.22% and 19.13% as quantified by Pearson correlation coefficient on two state-of-the-art baselines.