ScenicRules: An Autonomous Driving Benchmark with Multi-Objective Specifications and Abstract Scenarios
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914336196263936 |
|---|---|
| author | Chang, Kevin Kai-Chun Beyazit, Ekin Sangiovanni-Vincentelli, Alberto Wongpiromsarn, Tichakorn Seshia, Sanjit A. |
| author_facet | Chang, Kevin Kai-Chun Beyazit, Ekin Sangiovanni-Vincentelli, Alberto Wongpiromsarn, Tichakorn Seshia, Sanjit A. |
| contents | Developing autonomous driving systems for complex traffic environments requires balancing multiple objectives, such as avoiding collisions, obeying traffic rules, and making efficient progress. In many situations, these objectives cannot be satisfied simultaneously, and explicit priority relations naturally arise. Also, driving rules require context, so it is important to formally model the environment scenarios within which such rules apply. Existing benchmarks for evaluating autonomous vehicles lack such combinations of multi-objective prioritized rules and formal environment models. In this work, we introduce ScenicRules, a benchmark for evaluating autonomous driving systems in stochastic environments under prioritized multi-objective specifications. We first formalize a diverse set of objectives to serve as quantitative evaluation metrics. Next, we design a Hierarchical Rulebook framework that encodes multiple objectives and their priority relations in an interpretable and adaptable manner. We then construct a compact yet representative collection of scenarios spanning diverse driving contexts and near-accident situations, formally modeled in the Scenic language. Experimental results show that our formalized objectives and Hierarchical Rulebooks align well with human driving judgments and that our benchmark effectively exposes agent failures with respect to the prioritized objectives. Our benchmark can be accessed at https://github.com/BerkeleyLearnVerify/ScenicRules/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_16073 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ScenicRules: An Autonomous Driving Benchmark with Multi-Objective Specifications and Abstract Scenarios Chang, Kevin Kai-Chun Beyazit, Ekin Sangiovanni-Vincentelli, Alberto Wongpiromsarn, Tichakorn Seshia, Sanjit A. Robotics Artificial Intelligence Logic in Computer Science Systems and Control Developing autonomous driving systems for complex traffic environments requires balancing multiple objectives, such as avoiding collisions, obeying traffic rules, and making efficient progress. In many situations, these objectives cannot be satisfied simultaneously, and explicit priority relations naturally arise. Also, driving rules require context, so it is important to formally model the environment scenarios within which such rules apply. Existing benchmarks for evaluating autonomous vehicles lack such combinations of multi-objective prioritized rules and formal environment models. In this work, we introduce ScenicRules, a benchmark for evaluating autonomous driving systems in stochastic environments under prioritized multi-objective specifications. We first formalize a diverse set of objectives to serve as quantitative evaluation metrics. Next, we design a Hierarchical Rulebook framework that encodes multiple objectives and their priority relations in an interpretable and adaptable manner. We then construct a compact yet representative collection of scenarios spanning diverse driving contexts and near-accident situations, formally modeled in the Scenic language. Experimental results show that our formalized objectives and Hierarchical Rulebooks align well with human driving judgments and that our benchmark effectively exposes agent failures with respect to the prioritized objectives. Our benchmark can be accessed at https://github.com/BerkeleyLearnVerify/ScenicRules/. |
| title | ScenicRules: An Autonomous Driving Benchmark with Multi-Objective Specifications and Abstract Scenarios |
| topic | Robotics Artificial Intelligence Logic in Computer Science Systems and Control |
| url | https://arxiv.org/abs/2602.16073 |