Reproduce “RISC-V Functional Safety for Autonomous Automotive Systems: An Analytical Framework and Research Roadmap for ML-Assisted Certification” 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
Nick Andreasyan, Mikhail Struve, Alexey Popov, Maksim Nikolaev, Vadim Vashkelis
This paper presents an analytical framework and a research roadmap aimed at achieving economically efficient certification for RISC-V platforms in autonomous automotive systems. It proposes leveraging machine learning techniques to automate and optimize functional safety processes, alongside a certification economics framework and a maturity model tailored for RISC-V safety.
Key insights
- The central challenge for RISC-V adoption in automotive safety has shifted from technical feasibility to achieving economic superiority in the certification process itself.
- RISC-V offers inherent structural advantages, such as an open ISA, enhanced formal verifiability, and better toolchain qualification reuse, which can fundamentally reduce certification costs compared to proprietary solutions.
- Machine learning techniques can be systematically applied to automate and optimize traditionally manual and expensive certification activities, streamlining workflows and reducing uncertainty.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.