Who is Responsible? Explaining Safety Violations in Multi-Agent Cyber-Physical Systems

TL;DR

This paper presents an automated, principled method using counterfactual reasoning and the Shapley value to assign responsibility to individual agents in multi-agent cyber-physical systems for safety violations, enhancing explainability and accountability.

Contribution

It introduces a novel automated responsibility assignment approach based on counterfactual analysis and the degree of responsibility metric, improving over manual or complex existing methods.

Findings

The DoR metric effectively quantifies agent contributions to safety violations.

Experiments in urban driving scenarios demonstrate improved explainability.

The approach scales with agent interaction structures and reduces human effort.

Abstract

Multi-agent cyber-physical systems are present in a variety of applications. Agent decision-making can be affected due to errors induced by uncertain, dynamic operating environments or due to incorrect actions taken by an agent. When an erroneous decision that leads to a violation of safety is identified, assigning responsibility to individual agents is a key step toward preventing future accidents. Current approaches to carrying out such investigations require human labor or high degree of familiarity with operating environments. Automated strategies to assign responsibility can achieve a significant reduction in human effort and associated cognitive burden. In this paper, we develop an automated procedure to assign responsibility for safety violations to actions of any single agent in a principled manner. We base our approach on reasoning about safety violations in road safety. Given a safety violation, we use counterfactual reasoning to create alternative scenarios, showing how different outcomes could have occurred if certain actions had been replaced by others. We introduce the degree of responsibility (DoR) metric for each agent. The DoR, using the Shapley value, quantifies each agent's contribution to the safety violation, providing a basis to explain and justify decisions. We also develop heuristic techniques and methods based on agent interaction structures to improve scalability as agent numbers grow. We examine three safety violation cases from the National Highway Traffic Safety Administration (NHTSA). We run experiments using CARLA urban driving simulator. Results show the DoR improves the explainability of decisions and accountability for agent actions and their consequences.