Discussion of “some statistical challenges in automated driving systems”

The emergence of automated driving systems (ADS) has been a remarkable technological leap in recent times, holding tremendous potential to revolutionize mobility, minimize energy usage, and enhance safety on our roads. The present paper serves as a valuable contribution, addressing crucial aspects that underscore the significance of statistics in ADS applications and the accompanying challenges. I believe this important work will ignite further statistical research in the field and, consequently, foster the advancement of ADS development.

The request to intervene (RtI) is an indispensable component for Level 3 and Level 4 ADSs when faced with situations that surpass their design capabilities. In this context, figure 2 and algorithm 1 offer a concise and lucid depiction of the statistical framework and crucial factors involved in RtI. The Bayesian method proves valuable not only in ADS development but also as a complementary “white-box” algorithm alongside black-box algorithms, providing interpretable actions. One major complication is whether the driver's reaction time is sufficient to take on the RtI. The paper proposed a model to predict latent driver state based on driver state and environment monitoring, which is crucial in the decision to issue an RtI request. Due to the heterogeneity among human drivers, the reaction time can vary substantially under identical driving scenarios; for example, senior drivers might require more time to react.¹ How to incorporate individual variation under critical situations is an interesting problem.

During emergency scenarios, coming to a complete stop may not always be the optimal course of action. Instead, ADS should consider safety options called “Minimum Risk Maneuver” or MRM.² Identification and comparison of MRM is a challenging statistical problem.

Section 4 offers an insightful exploration of the statistical aspect of ethical decision-making in ADSs, which has remained a significant concern since the inception of ADS development. Ethical challenges in ADSs encompass more than the mere existence of ethical issues, as exemplified by Asimov's three laws of robotics that prioritize the avoidance of harm to humans. An intriguing scenario presented by Awad et al.³ presents a dilemma: if an ADS cannot find a trajectory that would save everyone involved, should it prioritize hitting a teenage pedestrian over three elderly passengers? This situation forces the ADS to make a decision regarding which human lives to potentially harm, highlighting the complexity of ethical decision-making in ADS.

The utilization of game theory and adversarial risk analysis (ARA) methodology to model ADS behavior in mixed traffic with human drivers is a brilliant approach for this paper. The perception of other road users' intentions and the environment can be achieved through either an ego-centric method, which relies on ADS onboard sensors, or a cooperative method, which involves communication with other road users and infrastructure via connected vehicle technology.⁴ While connected vehicle technology can provide more accurate information; it is important to acknowledge that the majority of vehicles on today's road are not connected, and it will likely take decades to replace them all with connected vehicles. Therefore, the ego-centric approach currently dominates, and predicting the behavior of other road users has become a prominent research topic. To predict other road users' trajectories based on sensor and roadway information is an essential task.⁵ However, existing approaches often overlook the interaction between ADS and other users, and this is where the ARA framework brings a creative contribution to prediction methods.

Expanding ARA methodologies to multiple players presents an interesting and challenging topic. The complexity arises from the fact that these players can include other ADS or human drivers, each of whom may respond differently. Formulating the problem and finding solutions, as well as addressing the computational challenges for real-time decision-making, are key statistical considerations.

One potential solution to tackle this problem is the scenario-based ADS developing and testing framework proposed by Thorn et al.⁶ This framework defines and explores various realistic driving scenarios. For instance, Guo et al.⁷ conducted a lane change driving scenario using millions of hours of naturalistic driving data. By encompassing a wide range of driving scenarios, the framework creates a comprehensive space of possible trajectories for road users. This approach significantly reduces the potential outcomes from an ADS prediction perspective. Combining such scenario-based information with ARA methodologies has the potential to greatly enhance prediction accuracy and improve the safe operation of ADSs.

The emergence of ADS has introduced numerous challenges that cannot be easily addressed through traditional statistical methods. While AI and machine learning have been the primary driving force in this domain, it is important to recognize the merits of statistical methods, especially in ADS testing, development, data engineering, and critical dynamic control tasks. The paper by Naveiro, Caballero, and Rios serves as an important contribution that highlights the significance of statistics in the context of ADS. It is expected that their work will stimulate further statistical research in this critical field, emphasizing the need for a comprehensive approach that incorporates statistical methodologies alongside black-box AI models.