PerceMon: Online Monitoring for Perception Systems
This addresses the problem of ensuring safety in autonomous vehicles by enabling runtime verification of perception outputs, which is critical for decision-making in scenarios like collision avoidance.
The paper tackles the challenge of runtime monitoring for perception systems in autonomous vehicles by presenting PerceMon, a tool that monitors arbitrary specifications in Timed Quality Temporal Logic and its extensions, integrated with CARLA and ROS to monitor state-of-the-art object detection and tracking algorithms.
Perception algorithms in autonomous vehicles are vital for the vehicle to understand the semantics of its surroundings, including detection and tracking of objects in the environment. The outputs of these algorithms are in turn used for decision-making in safety-critical scenarios like collision avoidance, and automated emergency braking. Thus, it is crucial to monitor such perception systems at runtime. However, due to the high-level, complex representations of the outputs of perception systems, it is a challenge to test and verify these systems, especially at runtime. In this paper, we present a runtime monitoring tool, PerceMon that can monitor arbitrary specifications in Timed Quality Temporal Logic (TQTL) and its extensions with spatial operators. We integrate the tool with the CARLA autonomous vehicle simulation environment and the ROS middleware platform while monitoring properties on state-of-the-art object detection and tracking algorithms.