Timed automata, which extend finite state automata by introducing clock variables, serve as a popular formalism for specifying and analyzing the timed behaviors of real-time systems. Extracting the timed behaviors of a black-box, safety-critical system is crucial for designing and analyzing its real-time requirements, yet it remains challenging. In this paper, we address this problem by generating a deterministic timed automaton (DTA) consistent with a given set of system behaviors, comprising both positive and negative examples. To this end, we adapt the formalism of simple elementary languages (sEL) and introduce the timed augmented prefix tree acceptor (tAPTA). Our approach proceeds as follows: First, we preprocess samples by translating them into sEL, which discards redundancy and detects conflicts; then, we rewrite the resulting sELs in an incremental form and construct a tAPTA to further simplify the samples; finally, we encode the search for a DTA that accepts the simplified tAPTA as an SMT formula. We evaluate our approach on randomly generated benchmarks and a scheduling case study. The results demonstrate the effectiveness of our simplification method in reducing the size of the encoded SMT formula and the efficiency of our approach in mining a DTA.
Driving world models are often interpreted as counterfactual simulators for observed driving episodes: given a factual driving log, they are asked what would have happened under an alternative ego action. In this paper, we identify a fundamental mismatch between this goal and direct action-conditioned prediction. The direct prediction uses the shared history and the alternative action but not the factual continuation observed after that history. It can therefore generate a plausible future without preserving what actually happened in this episode. We formalize this gap using the causal recipe of abduction, action, and prediction and study it in a setting with a short time horizon, where the alternative ego action does not alter how surrounding agents evolve. To make the gap measurable, we construct a controlled simulation benchmark with factual outcomes and matched counterfactual outcomes. Across two representative world models, direct predictions fail to match the counterfactual ground truth, supporting our analysis. As a constructive check of this analysis, we introduce a deliberately simple, training-free pipeline that moves observed evidence into the counterfactual view and lets the frozen model complete what remains unknown. Even this simple construction raises the overall recovered fraction substantially and reduces perceptual distance to the matched counterfactual on both models. We hope this work draws attention to this gap and motivates better counterfactual prediction methods for driving world models.
This survey delivers a comprehensive and critical synthesis of the emerging role of GenAI across the autonomous driving stack, delving into the frontier applications of GenAI in image, LiDAR, trajectory, occupancy, and video generation, as well as LLM-guided reasoning and decision-making.
Yuping Wang, Shuo Xing, Cui Can et al.· ACM Computing Surveys· 57 citations· ⚡2
A unified view of post-training for autonomous driving is presented by defining its scope and organizing the existing literature into four major families based on the form of supervision they use, which aim to facilitate a systematic understanding of this emerging area and stimulate future research on reliable and efficient post-training for autonomous driving.
Ruining Yang, Mu Wang, Yi-Xiao Chen et al.· arXiv.org· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
