Right in Time: Reactive Reasoning in Regulated Traffic Spaces

Researchers developed a reactive reasoning framework that combines probabilistic logic with real-time data processing to enable autonomous vehicles and drones to make safety and compliance decisions during operation. The system achieves orders of magnitude speedup over existing methods by using memoized inference and reactive circuits to only re-evaluate components affected by new sensor data.

• →New framework enables real-time probabilistic reasoning for autonomous vehicles in traffic spaces rather than just pre-flight planning.
• →System combines Probabilistic Mission Design with Reactive Circuits to achieve orders of magnitude performance improvements.
• →Approach uses frequency of change in data streams to subdivide inference into isolated, memoized tasks for efficiency.
• →Successfully tested on real-world vessel data and simulated urban drone traffic scenarios.
• →Enables intelligent transportation systems to actively assert safety and legal compliance during operations.