Due to safety concerns of integrating small unmanned aircraft systems (UAS) into non-segregated airspace, aviation authorities have required a set of detect and avoid (DAA) systems to be equipped on small UAS for beyond-visual-line-of-sight (BVLOS) flight operations in civil airspace. However, the development of small UAS DAA systems also requires BVLOS flights for testing and validation. To mitigate operational risks for small UAS BVLOS flight operations, this paper proposes to initially test small UAS DAA systems in BVLOS flights in a restricted airspace with additional safety features. Later, this paper further discusses the operating procedures and emergency action plans for small UAS BVLOS flight operations. The testing results show that these safety systems developed can help improve operational safety for small UAS BVLOS flight operations.
Artificial Intelligence (AI) is becoming more ubiquitous throughout our lives. As our reliance on this technology increases, ensuring human operators maintain an adequate level of trust is integral to their safe and effective operations. To facilitate the appropriate level of operator trust in AI, a mechanism to continuously evaluate and calibrate human–AI trust is required. Such a Trust Management System (TMS) will be integral to developing trustworthy AI systems and thus enabling collaborative and effective Human–AI Teaming (HAT) in future operations. This article starts a review of the current state-of-the-art in trust research applicable to HAT, then summarizes the development and presents the IMPACTS (Intention, Measurability, Performance, Adaptivity, Communication, Transparency, Security) homeostasis TMS. It is based on a dynamic and transactional trust framework and allows for continuous trust monitoring, managing, and behaviour adjustment to ensure operator trust is calibrated.
1 September 2018 in Journal of Aerospace Information Systems
To achieve a level of safety equivalent to manned aircraft in the national airspace system, the pilot in command of small unmanned aircraft systems should be able to maintain situational awareness and make necessary maneuvers to avoid potential conflicts with nearby air traffic during midair encounters. However, due to ever-changing flight environments, the pilot in command often misestimates conflict risks and cannot engage the appropriate maneuvers to prevent midair traffic from violating the safety boundaries of small unmanned aircraft systems. To fix this problem, a Monte-Carlo-simulation-based method is therefore introduced and designed to quantitatively determine the alerting threshold boundaries in various wind conditions for detect-and-avoid systems to help the pilot in command identify hazards and trigger avoidance maneuvers before a safety boundary violation occurs.