REVIEW 6 cited by
Evaluating Uncertainty Quantification in End-to-End Autonomous Driving Control
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
A rise in popularity of Deep Neural Networks (DNNs), attributed to more powerful GPUs and widely available datasets, has seen them being increasingly used within safety-critical domains. One such domain, self-driving, has benefited from significant performance improvements, with millions of miles having been driven with no human intervention. Despite this, crashes and erroneous behaviours still occur, in part due to the complexity of verifying the correctness of DNNs and a lack of safety guarantees. In this paper, we demonstrate how quantitative measures of uncertainty can be extracted in real-time, and their quality evaluated in end-to-end controllers for self-driving cars. To this end we utilise a recent method for gathering approximate uncertainty information from DNNs without changing the network's architecture. We propose evaluation techniques for the uncertainty on two separate architectures which use the uncertainty to predict crashes up to five seconds in advance. We find that mutual information, a measure of uncertainty in classification networks, is a promising indicator of forthcoming crashes.
Forward citations
Cited by 6 Pith papers
-
The Origins of Stochasticity: Comprehensive Investigations on Uncertainty Quantification for Large Language Models
The paper introduces a four-source uncertainty taxonomy for LLMs and finds that consensus-based UQ methods outperform others while larger models show lower uncertainty estimates.
-
Uncertainty Quantification for Regression: A Unified Framework based on kernel scores
Kernel-score divergences define a unified family of regression uncertainty measures whose kernel choice controls robustness, tail sensitivity, and OOD responsiveness.
-
Graph Evidential Learning for Anomaly Detection
GEL detects anomalous nodes by scoring evidential uncertainty from feature and topology reconstruction, reporting gains on four of five benchmark datasets.
-
Challenger: Affordable Adversarial Driving Video Generation
A framework for automatic generation of photorealistic adversarial driving videos, shown to sharply increase collision rates of end-to-end autonomous driving models.
-
Confidence-Gated Vision-Only Heading Alignment for UAV-UGV Cooperative Systems
Under identical gate decisions, a bounded-blend fallback during holds reduces issued-command error from 3.22° to 0.50° at the strongest centroid perturbation, versus freeze-hold.
-
Explorations of the Softmax Space: Knowing When the Neural Network Doesn't Know
Distance from a softmax prediction to the mean softmax vector of correct examples can serve as a confidence score for flagging low-confidence and out-of-distribution predictions, based on MNIST and CIFAR-10 experiments.
Discussion (0). Continue with ORCID to comment.