Reproduce “Safe Autonomy for Uncrewed Surface Vehicles Using Adaptive Control and Reachability Analysis” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Karan Mahesh, Tyler M. Paine, Max L. Greene, Nicholas Rober, Steven Lee, Sildomar T. Monteiro, Anuradha Annaswamy, Michael R. Benjamin and 1 more
Researchers developed and validated an autonomy pipeline for Uncrewed Surface Vehicles (USVs) that combines Model Reference Adaptive Control (MRAC) with real-time, data-driven reachability analysis. This pipeline achieved 45-81% reduction in position error compared to PID controllers and provided dynamic safety certification, enabling successful navigation in challenging, disturbed marine environments.
Key insights
- Adaptive control significantly enhances USV robustness and trajectory tracking accuracy by dynamically compensating for unmodeled dynamics and time-varying disturbances in real-time.
- Combining online disturbance estimation via MHE with efficient reachable set computation using CGs enables practical, real-time, and less conservative safety certification for autonomous systems.
- Comprehensive field validation with induced disturbances is crucial for demonstrating the practical efficacy and reliability of advanced control and safety methodologies in bridging the gap between theory and real-world deployment.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.