Design and Validation of Learning Aware HMI For Learning-Enabled Increasingly Autonomous Systems

TL;DR

This paper addresses safety and trust in learning-enabled increasingly autonomous systems (LEIAS) by integrating multi-sensor reliability assessment with pilot preference learning inside a Soar-based cognitive architecture. It proposes LEIAS, a learning-aware HMI and team architecture that transparently communicates sensor states and learned behaviors to pilots while adaptively escalating autonomy based on need. The approach combines formal verification (AGREE, AMASE, AADL) with reinforcement learning to tailor alerting for GPS, IMU, and LIDAR data, enabling personalized, context-driven decisions. Validation in the XPlane simulation demonstrates LEIAS’s ability to manage sensor anomalies and maintain effective human-machine collaboration, suggesting meaningful safety benefits for aviation and other safety-critical domains.

Abstract

With the rapid advancements in Artificial Intelligence (AI), autonomous agents are increasingly expected to manage complex situations where learning-enabled algorithms are vital. However, the integration of these advanced algorithms poses significant challenges, especially concerning safety and reliability. This research emphasizes the importance of incorporating human-machine collaboration into the systems engineering process to design learning-enabled increasingly autonomous systems (LEIAS). Our proposed LEIAS architecture emphasizes communication representation and pilot preference learning to boost operational safety. Leveraging the Soar cognitive architecture, the system merges symbolic decision logic with numeric decision preferences enhanced through reinforcement learning. A core aspect of this approach is transparency; the LEIAS provides pilots with a comprehensive, interpretable view of the system's state, encompassing detailed evaluations of sensor reliability, including GPS, IMU, and LIDAR data. This multi-sensor assessment is critical for diagnosing discrepancies and maintaining trust. Additionally, the system learns and adapts to pilot preferences, enabling responsive, context-driven decision-making. Autonomy is incrementally escalated based on necessity, ensuring pilots retain control in standard scenarios and receive assistance only when required. Simulation studies conducted in Microsoft's XPlane simulation environment to validate this architecture's efficacy, showcasing its performance in managing sensor anomalies and enhancing human-machine collaboration, ultimately advancing safety in complex operational environments.

Figures (7)

• Figure 1: Proposed methodology for LEIAS
• Figure 2: Learning HMI
• Figure 3: Pilot's lack of response - counterexample
• Figure 4: Learning aware HMI
• Figure 5: The decision-making process of the LEIAS agent for the GPS sensor, showing the comparison between warning (in blue) and non-warning (in orange) actions. The reinforcement learning scores reflect the alignment of these decisions with the pilot's alerting preferences.