Enhancing Situation Awareness through Model-Based Explanation Generation
Konstantinos Gavriilidis, Ioannis Konstas, Helen Hastie, Wei Pang · 2024
Robots are often deployed in remote locations for tasks such as exploration, where users cannot directly perceive the agent and its environment.For Human-In-The-Loop applications, operators must have a comprehensive understanding of the robot's current state and its environment to take necessary actions and effectively assist the agent.In this work, we compare different explanation styles to determine the most effective way to convey real-time updates to users.Additionally, we formulate these explanation styles as separate fine-tuning tasks and assess the effectiveness of large language models in delivering in-mission updates to maintain situation awareness.The code and dataset for this work are available at: https://github.com/ konsgavriil/explainable_robotics_lm. XARLM Causal Explanation:After visiting all survey waypoints, Alpha is returning back to its starting point with a northwest heading to be recovered.At the moment, obstacle A is very far from the vessel and there is no need to modify its route. What-if Query: What if Alpha's return is cancelled?Counterfactual Explanation: If Alpha's return state is deactivated, then the vessel will start surveying the area again starting from Point 0. Why-not Query: Why doesn't Alpha continue surveying the area instead of returning back.Contrastive Explanation: Alpha is not surveying, because both its deploy and return states are active.For the return state to be triggered, the vessel needs to visit all survey waypoints or a request needs to be retrieved from C2 for immediate return.