Assurance-based Learning-enabled Cyber-Physical Systems

This simulation presents a pipe tracking scenario, default parameters and high battery level with static box obstacles.
With use_behaviour_tree = true, the autonomy is controlled by a BT based logic in the ALC Toolchain.
Obstacle avoidance is enabled by default during the whole mission, and obstacles will spawn directly ahead of the UUV. UUV applies obstacle avoidance and after maneuver it returns to Pipe Following.
 

In the video at sim t=102 BlueROV detects an obstacle, updates the obstacle map (grid) and avoids the obstacle using this map.
After the avoidance maneuver, the UUV slowly closes back to the pipe to maintain SLS image quality and resolution.
When LEC2 assurance monitor reports that the image quality is bad, UUV slows down and temporarily disables pipe mapping.
From the created pipe map, the UUV still knows what is the pipe heading, even if that cannot be detected on the SLS for a short time - that is also good for buried sections.