SBIR Phase I: Collision Regulations (COLREG) Aware Autonomy for Safe Interactions of Crewed and Uncrewed Vessels

点击翻译按钮获取中文摘要

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase I project is to advance the productivity and safety of operations across the entire $1.3 trillion Blue Economy. Maritime operations routinely involve significant risks to human life and property and consequently bear extraordinarily high operating costs. Autonomous ocean vehicles (falling under the Robotics technology area) are being rapidly adopted by science, commercial, and defense organizations due to their potential to dramatically reduce cost and risk. The success of the proposed project will advance the state of the art for commercial autonomous vehicle compliance with international laws regulating interactions between maritime vessels at sea. Giving autonomous ocean vehicles the ability to interact with crewed vessels safely and predictably will accelerate the adoption of these tools and the missions they enable. Several specific market segments stand to benefit immediately from the proposed technology, including the $31B offshore wind market, the $2B port automation market, the $233B aquaculture market, and dozens of others. Beyond market impacts, humanity needs ocean data to understand the critical dangers of overfishing and climate change.This Small Business Innovation Research (SBIR) Phase I project is focused on the design of systems and software needed for autonomous ocean vehicles to comply with the international collision regulations (COLREGS) for maritime vehicles. The difficulty the industry has faced in creating COLREGS compliant autonomy is the fact that the rules were developed with the expectation that experienced mariners would be able to make qualitative interpretations in unique situations. That led to a descriptive rather than prescriptive set of rules that is good for human mariners, but difficult to implement in software. The objectives of this Phase I project include the design and simulation of autonomous systems able to operate in compliance with the COLREGS. In addition to simulations, the software may be deployed to small autonomous surface vehicles for preliminary on-water testing. Anticipated results include a system able to maintain COLREGS compliance within a documented envelope of conditions. The effective implementation of safe system design, optimized control, and machine learning techniques can combine to produce the first autonomous ocean vehicles that can be trusted in congested waterway settings.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.