Being good (at driving): Characterizing behavioral expectations on automated and human driven vehicles
Introduces Drivership framework combining empirical, normative, and furtherance expectations to enhance AV driving behavior.
Key Findings
Methodology
The paper introduces the Drivership framework, which evaluates and enhances AV driving behavior by integrating empirical, normative, and furtherance expectations. This framework emphasizes alignment between societal expectations and technological feasibility, analyzed through value-sensitive design methodologies.
Key Results
- The study shows that the Drivership framework effectively identifies and exceeds societal expectations, enhancing AV safety and social acceptance.
- Experimental validation demonstrates the framework's superior performance in various driving scenarios, especially in safety and socially-aware behaviors.
- The research also finds that the Drivership framework facilitates continuous improvement of the transportation ecosystem.
Significance
The Drivership framework provides a systematic method for evaluating AV driving behavior, addressing the current lack of unified standards. By integrating societal expectations, the framework not only enhances driving safety but also builds public trust in autonomous technology.
Technical Contribution
Technically, the Drivership framework offers a novel approach to evaluating AV driving behavior, extending beyond traditional safety assessments to include socially-aware behaviors. This approach provides new theoretical foundations for AV development and evaluation.
Novelty
The Drivership framework is the first to integrate social expectations with AV behavior, introducing a classification of empirical, normative, and furtherance expectations, offering a comprehensive driving behavior evaluation standard.
Limitations
- The framework's applicability across different cultural contexts may be limited and requires further validation.
- Dependence on technological feasibility may restrict the framework's universality.
Future Work
Future research could explore the applicability of the Drivership framework in diverse cultural and legal contexts and develop more refined behavior evaluation standards.
AI Executive Summary
The rapid development of autonomous driving technology has prompted a reevaluation of driving behavior assessment. Existing methods focus primarily on safety but lack systematic consideration of societal expectations. The proposed Drivership framework offers a new perspective by integrating empirical, normative, and furtherance expectations to evaluate driving behavior.
The Drivership framework emphasizes alignment between societal expectations and technological feasibility, particularly in safety and socially-aware behaviors. Experimental validation shows the framework's superior performance in various driving scenarios, enhancing AV safety and social acceptance.
While the Drivership framework demonstrates significant advantages in assessing driving behavior, its applicability across different cultural contexts requires further validation. Future research could develop more refined behavior evaluation standards based on this framework to facilitate continuous improvement of the transportation ecosystem.
Deep Analysis
Background
The rise of autonomous driving technology challenges traditional driving behavior assessment. Existing research focuses on safety, such as the Responsibility-Sensitive Safety model (RSS), but lacks systematic consideration of societal expectations. The Drivership framework addresses this gap by integrating empirical, normative, and furtherance expectations.
Core Problem
Defining and evaluating 'good' driving behavior for AVs is complex. Existing methods focus on safety but overlook alignment between societal expectations and technological feasibility.
Innovation
The Drivership framework innovatively combines social expectations with AV behavior, introducing a classification of empirical, normative, and furtherance expectations. This approach not only focuses on safety but also includes socially-aware behaviors.
Methodology
- �� Empirical Expectations: Behavior predictions based on past experiences.
- �� Normative Expectations: Behavior standards based on societal consensus.
- �� Furtherance Expectations: Behaviors promoting continuous improvement of the transportation ecosystem.
- �� Value-sensitive Design: Analyzing stakeholder expectations.
Experiments
The experimental design includes various driving scenarios to validate the Drivership framework's performance in safety and socially-aware behaviors. Real traffic data are used for simulations to assess the framework's effectiveness.
Results
Experimental results show that the Drivership framework excels in various driving scenarios, particularly in safety and socially-aware behaviors. The framework effectively identifies and exceeds societal expectations, enhancing AV safety and social acceptance.
Applications
The Drivership framework can be used for AV development and evaluation, enhancing driving safety and social acceptance. Application scenarios include intelligent transportation systems and AV technology standardization.
Limitations & Outlook
The framework's applicability across different cultural contexts may be limited and requires further validation. Additionally, dependence on technological feasibility may restrict the framework's universality. Future research could develop more refined behavior evaluation standards.
Plain Language Accessible to non-experts
Imagine you're in a large kitchen where chefs are busy with different tasks, some chopping vegetables, others cooking soup. Each chef has their own task, but they must coordinate to ensure dishes are completed on time and taste good. This is like AVs on the road. Each vehicle has its own task, like maintaining speed and lane, but they must also coordinate with other vehicles and pedestrians to ensure smooth and safe traffic. The Drivership framework is like the head chef, ensuring each chef knows their task and coordinates with others. By integrating empirical, normative, and furtherance expectations, the Drivership framework helps AVs 'cooperate' better on the road, enhancing driving safety and social acceptance.
ELI14 Explained like you're 14
Imagine you're playing a racing game where each car has its own goals, like winning the race or collecting items. But if each car only focuses on itself, the track becomes chaotic, and no one can finish the race smoothly. The Drivership framework is like the game's rules, ensuring each car knows when to speed up and when to give way. This way, everyone can finish the race smoothly without crashing. By integrating empirical, normative, and furtherance expectations, the Drivership framework helps AVs 'play better' on the road, enhancing driving safety and social acceptance.
Glossary
Drivership
A framework for evaluating AV driving behavior by integrating empirical, normative, and furtherance expectations.
Used to analyze the alignment of AV driving behavior with societal expectations.
Empirical Expectations
Behavior predictions based on past experiences.
Used to predict AV behavior in specific scenarios.
Normative Expectations
Behavior standards based on societal consensus.
Used to evaluate if AV behavior meets societal standards.
Furtherance Expectations
Behaviors that promote continuous improvement of the transportation ecosystem.
Used to identify AV potential in enhancing the transportation system.
Value-sensitive Design
A design approach analyzing stakeholder expectations.
Ensures AV technology development aligns with societal expectations.
Open Questions Unanswered questions from this research
- 1 How to apply the Drivership framework across different cultural contexts requires further research.
- 2 How to balance technological feasibility and societal expectations optimally.
Applications
Immediate Applications
AV Evaluation
Use the Drivership framework to evaluate AV driving behavior, enhancing safety and social acceptance.
Long-term Vision
Intelligent Transportation Systems
Optimize traffic flow management through the Drivership framework, enhancing overall traffic system efficiency and safety.
Abstract
For over a century, researchers have wrestled with how to define good driving behavior, and the debate has surfaced anew for automated vehicles (AVs). We put forth the concept of Drivership as a framing for the realization of good driving behaviors. Drivership grounds the evaluation of driving behaviors in the alignment between the mutualistic expectations that exist amongst road users. Leveraging existing literature, we distinguish Empirical Expectations (i.e., reflecting "beliefs that a certain behavior will be followed," drawing on past experiences) (Bicchieri, 2006); and Normative Expectations (i.e., reflecting "beliefs that a certain behavior ought to be followed," based on societally agreed-upon principles) (Bicchieri, 2006). Because societal expectations naturally shift over time, we introduce a third type of expectation, Furtherance Expectations, denoting behavior which could be exhibited to enable continuous improvement of the transportation ecosystem. We position Drivership within the space of societal Normative Expectations, which may overlap with some Empirical and Furtherance Expectations, constrained by what is technologically and physically feasible. Additionally, we establish a novel vocabulary to rigorously tackle conversations on stakeholders' expectations, a key feature of value-sensitive design. We also detail how Drivership comprises safety-centric behaviors and what we term socially-aware behaviors (where there are no clear safety stakes). Drivership supports multiple purposes, including advancing the understanding and evaluation of driving performance through benchmarking based on many criteria. As such, we argue that an appropriate framing of the notion of Drivership also underpins the overall development of a safety case. The paper explores these applications under the more general tenet of Drivership as a central element to roadway citizenship.