Lane Departure Assist: A Formal Approach

نویسندگان

  • Daniel Hoehener
  • Geng Huang
  • Domitilla Del Vecchio
چکیده

We use a controlled invariance approach to design a semi-autonomous lane departure assist system that is guaranteed to keep the vehicle in the lane. The controlled invariant safe set is the set of system states from which an input exists that can keep the vehicle in the lane. First we provide theoretical conditions under which the controlled invariant safe set has a simple characterization that can be quickly computed in real-time. We then use this characterization to derive a feedback strategy that keeps the vehicle in the lane and overrides the driver only if he/she could otherwise force a future lane departure. We also provide a detailed description of the above mentioned conditions, including algorithmic approaches that allow to verify whether these conditions are satisfied.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Design of a lane departure driver-assist system under safety specifications: Theorems and Proofs

This note contains full proofs of all the results provided in the submission “On a semi-autonomous lane departure assist system” to the 2016 Conference on Decision and Control by the same authors, [2].

متن کامل

Computer Vision based Intelligent Lane Detection and Warning System: A Design Approach

In Intelligent Transport System (ITS), prevention from accident is one of prominent area of research in which various approaches are implemented and proposed to assist and warn driver from accidents. As a part of warning system lane departure technique is widely considered, that monitor vehicle’s movement , and warn driver before lane departure which will prevent driver from head on collision. ...

متن کامل

Volvo and Infiniti drivers' experiences with select crash avoidance technologies.

OBJECTIVES Vehicle-based crash avoidance systems can potentially reduce crashes, but success depends on driver acceptance and understanding. This study gauged driver use, experience, and acceptance among early adopters of select technologies. METHODS Telephone interviews were conducted in early 2009 with 380 owners of Volvo vehicles equipped with forward collision warning with autobrake, lane...

متن کامل

Evaluation of Lane Departure Correction Systems Using a Stochastic Driver Model

Evaluating the effectiveness and benefits of driver assistance systems is crucial for improving the system performance. In this paper, we propose a novel framework for testing and evaluating lane departure correction systems at a low cost by using lane departure events reproduced from naturalistic driving data. First, 529,096 lane departure events were extracted from the Safety Pilot Model Depl...

متن کامل

A Learning-Based Approach for Lane Departure Warning Systems with a Personalized Driver Model

Misunderstanding of driver correction behaviors (DCB) is the primary reason for false warnings of lane-departureprediction systems. We propose a learning-based approach to predicting unintended lane-departure behaviors (LDB) and the chance for drivers to bring the vehicle back to the lane. First, in this approach, a personalized driver model for lanedeparture and lane-keeping behavior is establ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2015