TRANSCEND: Trustworthy Resilient Autonomous agents for Safe City transportation in the Evolving New Decade

Trustworthy Resilient Autonomous ageNts for Safe City transportation in the Evolving New Decade (TRANSCEND), aims to establish a trust framework for engineers and human operators to determine the trustworthiness of machine-learning-enabled autonomous aviation systems.

This project focuses on integrating key pillars of trust for autonomous intelligent systems (AIS) across multiple technical disciplines, including human factors, formal methods, autonomy, and artificial intelligence. The team will create innovative technologies as part of the TRANSCEND framework for the verification and validation of the trustworthiness of increasingly autonomous systems, such as those that could potentially employ artificial intelligence and machine learning.  The goal is to convey assumptions for trust, from design time to operation, as the intelligent systems are being deployed, so that operators know when to trust and when not to trust the AIS. This goal is accomplished through four interrelated technical challenges (TCs). TC1 focuses on the development of a conceptual model of trust through the integration of trust definitions across interdisciplinary boundaries; TC2 emphasizes the design and implementation of approaches to assure trust in AIS; TC3 integrates the methodologies developed in TC2,  that transcend existing technical gaps across disciplines; TC4 provides a structured framework for the development of safety case arguments for AIS. TRANSCEND supports industry and FAA in identifying critical pathways for the certification of learning enabled systems

The technologies being developed are

1. Verification and validation of Learning enabled systems with formal methods, machine learning and human factors
2. Explainability of learning enabled systems
3. Identification of failures with vision language models
4. Safety case toolkit for assurance argument for learning enables systems

• Near (till 2035): A cross disciplinary TRANSCEND framework to develop trust in Learning-Enabled Autonomous Systems for handling In-time System-wide Safety Assurance (ISSA) to provide alerts, strategies and mitigation of safety risks.
• Mid (2035-2045): Integration of new operational concepts and applications with extensions to the TRANSCEND framework for the inclusion of intelligent ISSA functions for In-time Aviation Safety Management System (IASMS).
• Far(beyond 2045): A framework to integrate and trust artificial intelligence and machine learning (ML) based system for handling emerging safety risks throughout aviation systems and operations. A trusted approach to demonstrate the safety of intelligent systems applied within IASMS, appropriate for certification and operational approval.

This is early/mid-stage (TRL 1) — the most realistic path in is NASA SBIR/STTR, which funds small businesses and research institutions to develop technology aligned with NASA's needs (equity-free, phased funding). Check whether a current SBIR/STTR solicitation topic overlaps with this project's technology area, or contact the project directly (above) to ask.

None of these are guaranteed paths for this specific project — TechPort itself doesn't have an "apply" button. Reaching out to the contact(s) above with a specific question is usually the fastest way to find out what's actually open.