Inter-triggering hybrid automata: a formalism for responsibility-sensitive safety

Abstract

This paper introduces inter-triggering hybrid automata, a formalism to represent multi-agent systems where each agent is represented as a hybrid automaton and agents interact by triggering discrete transitions (jumps and resets) on their "neighboring" agents. Using this formalism, we define responsibility-sensitive safety as respecting one another's invariances while triggering jumps and resets. This allows us to make a formal connection between responsibility and robust controlled invariant sets for individual agents, therefore leading to a compositional verification framework for the safety of the overall multi-agent system. We discuss several advantages of this viewpoint and illustrate it on a highway driving example.