CaRE: Finding Root Causes of Configuration Issues in Highly-Configurable Robots
This addresses the challenge of fault diagnosis in complex robotic systems for robotics engineers, but it is incremental as it applies causal methods to a specific domain.
The paper tackles the problem of diagnosing root causes of functional faults in highly-configurable robots by proposing CaRE, a method that uses causality to learn relationships between configuration options and performance, and demonstrates its efficacy by finding and validating root causes in physical robots and simulation, with transferability across platforms.
Robotic systems have subsystems with a combinatorially large configuration space and hundreds or thousands of possible software and hardware configuration options interacting non-trivially. The configurable parameters are set to target specific objectives, but they can cause functional faults when incorrectly configured. Finding the root cause of such faults is challenging due to the exponentially large configuration space and the dependencies between the robot's configuration settings and performance. This paper proposes CaRE -- a method for diagnosing the root cause of functional faults through the lens of causality. CaRE abstracts the causal relationships between various configuration options and the robot's performance objectives by learning a causal structure and estimating the causal effects of options on robot performance indicators. We demonstrate CaRE's efficacy by finding the root cause of the observed functional faults and validating the diagnosed root cause by conducting experiments in both physical robots (Husky and Turtlebot 3) and in simulation (Gazebo). Furthermore, we demonstrate that the causal models learned from robots in simulation (e.g., Husky in Gazebo) are transferable to physical robots across different platforms (e.g., Husky and Turtlebot 3).