OCCUQ: Exploring Efficient Uncertainty Quantification for 3D Occupancy Prediction
This work addresses the robustness of autonomous driving systems in safety-critical scenarios with unseen data, though it appears incremental as an adaptation of existing uncertainty estimation techniques.
The paper tackles the problem of uncertainty quantification in 3D occupancy prediction for autonomous driving under adverse conditions like camera corruptions, and the result is a method that shows superior performance in Out-of-Distribution detection and confidence calibration compared to baselines such as Deep Ensembles and MC-Dropout.
Autonomous driving has the potential to significantly enhance productivity and provide numerous societal benefits. Ensuring robustness in these safety-critical systems is essential, particularly when vehicles must navigate adverse weather conditions and sensor corruptions that may not have been encountered during training. Current methods often overlook uncertainties arising from adversarial conditions or distributional shifts, limiting their real-world applicability. We propose an efficient adaptation of an uncertainty estimation technique for 3D occupancy prediction. Our method dynamically calibrates model confidence using epistemic uncertainty estimates. Our evaluation under various camera corruption scenarios, such as fog or missing cameras, demonstrates that our approach effectively quantifies epistemic uncertainty by assigning higher uncertainty values to unseen data. We introduce region-specific corruptions to simulate defects affecting only a single camera and validate our findings through both scene-level and region-level assessments. Our results show superior performance in Out-of-Distribution (OoD) detection and confidence calibration compared to common baselines such as Deep Ensembles and MC-Dropout. Our approach consistently demonstrates reliable uncertainty measures, indicating its potential for enhancing the robustness of autonomous driving systems in real-world scenarios. Code and dataset are available at https://github.com/ika-rwth-aachen/OCCUQ .