Multimodal Safety-Critical Scenarios Generation for Decision-Making Algorithms Evaluation [article]

Wenhao Ding, Baiming Chen, Bo Li, Kim Ji Eun, Ding Zhao
<span title="2020-12-26">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Existing neural network-based autonomous systems are shown to be vulnerable against adversarial attacks, therefore sophisticated evaluation on their robustness is of great importance. However, evaluating the robustness only under the worst-case scenarios based on known attacks is not comprehensive, not to mention that some of them even rarely occur in the real world. In addition, the distribution of safety-critical data is usually multimodal, while most traditional attacks and evaluation
more &raquo; ... focus on a single modality. To solve the above challenges, we propose a flow-based multimodal safety-critical scenario generator for evaluating decisionmaking algorithms. The proposed generative model is optimized with weighted likelihood maximization and a gradient-based sampling procedure is integrated to improve the sampling efficiency. The safety-critical scenarios are generated by querying the task algorithms and the log-likelihood of the generated scenarios is in proportion to the risk level. Experiments on a self-driving task demonstrate our advantages in terms of testing efficiency and multimodal modeling capability. We evaluate six Reinforcement Learning algorithms with our generated traffic scenarios and provide empirical conclusions about their robustness.
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.08311v3">arXiv:2009.08311v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/knigednisrhxde3nerd5x2pcbm">fatcat:knigednisrhxde3nerd5x2pcbm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201231032913/https://arxiv.org/pdf/2009.08311v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/92/4f/924fa4fae8427635c81d7ef21108c82ebaacceab.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.08311v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>