# Liability, Ethics, and Culture-Aware Behavior Specification using Rulebooks

arXiv: https://arxiv.org/abs/1902.09355 · HTML: https://mlsanity.com/paper/1902.09355/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Feb 2019.

## Built on by (most cited first, 30 of 43)

- [Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems](https://mlsanity.com/paper/2405.06624/) (2024)
- [LaserMix for Semi-Supervised LiDAR Semantic Segmentation](https://mlsanity.com/paper/2207.00026/) (2022)
- [Conditional Predictive Behavior Planning with Inverse Reinforcement Learning for Human-like Autonomous Driving](https://mlsanity.com/paper/2212.08787/) (2022)
- [A Review of Reward Functions for Reinforcement Learning in the context of Autonomous Driving](https://mlsanity.com/paper/2405.01440/) (2024)
- [The Reasonable Crowd: Towards evidence-based and interpretable models of driving behavior](https://mlsanity.com/paper/2107.13507/) (2021)
- [Finding Critical Scenarios for Automated Driving Systems: A Systematic Literature Review](https://mlsanity.com/paper/2110.08664/) (2021)
- [Fine-Tuning Language Models Using Formal Methods Feedback](https://mlsanity.com/paper/2310.18239/) (2023)
- [Safety of the Intended Driving Behavior Using Rulebooks](https://mlsanity.com/paper/2105.04472/) (2021)
- [Parallel and Multi-Objective Falsification with Scenic and VerifAI](https://mlsanity.com/paper/2107.04164/) (2021)
- [Hierarchical Potential-based Reward Shaping from Task Specifications](https://mlsanity.com/paper/2110.02792/) (2021)
- [Receding Horizon Planning with Rule Hierarchies for Autonomous Vehicles](https://mlsanity.com/paper/2212.03323/) (2022)
- [Dreaming to Assist: Learning to Align with Human Objectives for Shared Control in High-Speed Racing](https://mlsanity.com/paper/2410.10062/) (2024)
- [Informed Reinforcement Learning for Situation-Aware Traffic Rule Exceptions](https://mlsanity.com/paper/2402.04168/) (2024)
- [Hybrid Deep Reinforcement Learning and Planning for Safe and Comfortable Automated Driving](https://mlsanity.com/paper/2301.00650/) (2022)
- [Multi-Predictor Fusion: Combining Learning-based and Rule-based Trajectory Predictors](https://mlsanity.com/paper/2307.01408/) (2023)
- [GENESIS-RL: GEnerating Natural Edge-cases with Systematic Integration of Safety considerations and Reinforcement Learning](https://mlsanity.com/paper/2403.19062/) (2024)
- [Immune Moral Models? Pro-Social Rule Breaking as a Moral Enhancement Approach for Ethical AI](https://mlsanity.com/paper/2107.04022/) (2021)
- [Quantification of Actual Road User Behavior on the Basis of Given Traffic Rules](https://mlsanity.com/paper/2202.09269/) (2022)
- [Provable Traffic Rule Compliance in Safe Reinforcement Learning on the Open Sea](https://mlsanity.com/paper/2402.08502/) (2024)
- [RuleFuser: An Evidential Bayes Approach for Rule Injection in Imitation Learned Planners and Predictors for Robustness under Distribution Shifts](https://mlsanity.com/paper/2405.11139/) (2024)
- [Learning to falsify automated driving vehicles with prior knowledge](https://mlsanity.com/paper/2101.10377/) (2021)
- [Predictive Traffic Rule Compliance using Reinforcement Learning](https://mlsanity.com/paper/2503.22925/) (2025)
- [Balancing Progress and Safety: A Novel Risk-Aware Objective for RL in Autonomous Driving](https://mlsanity.com/paper/2505.06737/) (2025)
- [PoSafeNet: Safe Learning with Poset-Structured Neural Nets](https://mlsanity.com/paper/2601.22356/) (2026)
- [ScenicRules: An Autonomous Driving Benchmark with Multi-Objective Specifications and Abstract Scenarios](https://mlsanity.com/paper/2602.16073/) (2026)
- [RECTOR: Priority-Aware Rule-Based Reranking for Compliance-Aware Autonomous Driving Trajectory Selection](https://mlsanity.com/paper/2605.25095/) (2026)
- [Steering Generative Robot Policies with Lexicographic Preferences](https://mlsanity.com/paper/2609.15014/) (2026)
- [Safe Policy Improvement in Constrained Markov Decision Processes](https://mlsanity.com/paper/2210.11259/) (2022)
- [Specification-Guided Data Aggregation for Semantically Aware Imitation Learning](https://mlsanity.com/paper/2303.17010/) (2023)
- [Virtue Ethics For Ethically Tunable Robotic Assistants](https://mlsanity.com/paper/2407.16361/) (2024)

## Abstract (arXiv)

The behavior of self-driving cars must be compatible with an enormous set of conflicting and ambiguous objectives, from law, from ethics, from the local culture, and so on. This paper describes a new way to conveniently define the desired behavior for autonomous agents, which we use on the self-driving cars developed at nuTonomy. We define a "rulebook" as a pre-ordered set of "rules", each akin to a violation metric on the possible outcomes ("realizations"). The rules are partially ordered by priority. The semantics of a rulebook imposes a pre-order on the set of realizations. We study the compositional properties of the rulebooks, and we derive which operations we can allow on the rulebooks to preserve previously-introduced constraints. While we demonstrate the application of these techniques in the self-driving domain, the methods are domain-independent.