Testing in Real: Sample-efficient failure discovery of contextual failures with Bayesian active learning
Discovering failures that cannot be expressed analytically, in limited samples, using coverage-driven active learning
Portfolio
Testing in sim: Failure discovery with sampling-based techniques
Improving the efficiency of sampling based evaluation using data-driven techniques
Testing in Sim and Real: Failure prediction using both sources
Combining sample-extensive failure search in sim and sample efficient exploration in real-world platform for model validation