Long-tail and rare event problems become crucial when autonomous driving algorithms are applied in the real world. For the purpose of evaluating systems in challenging settings, we propose a generative framework to create safetycritical scenarios for evaluating specific task algorithms. We first represent the traffic scenarios with a series of autoregressive building blocks and generate diverse scenarios by sampling from the joint distribution of these blocks. We then train the generative model as an agent (or a generator) to investigate the risky distribution parameters for a given driving algorithm being evaluated. We regard the task algorithm as an environment (or a discriminator) that returns a reward to the agent when a risky scenario is generated. Through the experiments conducted on several scenarios in the simulation, we demonstrate that the proposed framework generates safetycritical scenarios more efficiently than grid search or human design methods. Another advantage of this method is its adaptiveness to the routes and parameters.
In order to analyze the compressive stress state of a cotton fiber assembly in the compression process, a new cotton fiber assembly model, the tetrakaidecahedral porous cotton fiber assembly model, is presented based on the idea of three-dimensional open-cell foam material modeling. Based on the model, the compression process of cotton fiber assembly is analyzed using the finite element method. The change in the compressive stress of the cotton fiber assembly in the compression process is successfully described. The measurement method of compressive modulus of the cotton fiber assembly is also studied, and the relation between compressive modulus and relative density of the cotton fiber assembly is determined. Finally, the effect of different moisture regain on compressive stress of the cotton fiber assembly is analyzed, and the reference value of moisture regain in the cotton baling process is given. The results show that the simulation results are consistent with the actual situation. Therefore, the established model of cotton fiber assembly has validity.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.