Realistic Counterfactual Explanations for Machine Learning-Controlled Mobile Robots using 2D LiDAR
It addresses the need for explainable AI in mobile robotics to help understand, debug, and improve ML-based autonomous control, though it is incremental as it builds on existing counterfactual explanation methods.
This paper tackles the problem of interpreting black-box machine learning models in safety-critical mobile robot control by generating realistic counterfactual explanations using 2D LiDAR data, demonstrating logical and realistic results on a TurtleBot3 in real-world and simulated scenarios.
This paper presents a novel method for generating realistic counterfactual explanations (CFEs) in machine learning (ML)-based control for mobile robots using 2D LiDAR. ML models, especially artificial neural networks (ANNs), can provide advanced decision-making and control capabilities by learning from data. However, they often function as black boxes, making it challenging to interpret them. This is especially a problem in safety-critical control applications. To generate realistic CFEs, we parameterize the LiDAR space with simple shapes such as circles and rectangles, whose parameters are chosen by a genetic algorithm, and the configurations are transformed into LiDAR data by raycasting. Our model-agnostic approach generates CFEs in the form of synthetic LiDAR data that resembles a base LiDAR state but is modified to produce a pre-defined ML model control output based on a query from the user. We demonstrate our method on a mobile robot, the TurtleBot3, controlled using deep reinforcement learning (DRL) in real-world and simulated scenarios. Our method generates logical and realistic CFEs, which helps to interpret the DRL agent's decision making. This paper contributes towards advancing explainable AI in mobile robotics, and our method could be a tool for understanding, debugging, and improving ML-based autonomous control.