Reproduce “Haptic Shared Control in Steering Operation Based on Cooperative Status Between a Driver and a Driver Assistance System” 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
Ryota Nishimura, Takahiro Wada, Seiji Sugiyama
Ritsumeikan University researchers developed a methodology to quantify the cooperative status between a human driver and a steering assistance system, employing "pseudo-power" and "pseudo-work" metrics to adapt haptic feedback. The resulting lane-keeping assist system improves lane-keeping performance and facilitates driver-initiated lane changes with comparable driver effort to manual driving.
Key insights
- The cooperative status between human and automation in shared control can be effectively quantified by analyzing the energy contributions (pseudo-power/work) of each agent.
- Dynamically reducing the DAS's haptic assistance gain when driver intent conflicts with the system (e.g., during a lane change) leads to smoother and more intuitive interaction.
- Adapting the target lane based on detected driver intent, combined with gain-tuning, allows an LKAS to assist lane-keeping while seamlessly supporting driver-initiated maneuvers.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.