Search Results

A Distance Control Assist System (DCA) aiming at facilitating the driver maintaining a following distance to a lead vehicle in congested traffic was developed. The DCA imposes active force to the driver’s foot to urge him or her to release the accelerator pedal as well as decelerates automatically when the host vehicle comes too close to a lead vehicle. This paper introduces the system description and a field test conducted to evaluate effectiveness of the DCA. As a result of the field test, comparison of the driver performances between with and without the DCA showed that numbers of braking by the drivers were decreased, and comparison of NASA-TLX scores showed subjective workload was reduced by the DCA. These results suggested that the DCA can contribute to mitigation of the driver’s workload while following situations.

This paper describes a novel prototype driver support system aimed at improving drivers' awareness of changing situations ahead as well as at reducing the frequency of approaching a preceding car closely. The control algorithm is based on the idea of a virtual repulsive force that increases as the host vehicle draws closer to a car ahead. The virtual repulsive force is utilized to determine the accelerator pedal reaction force and to control the effective driving and braking force. A build-up of accelerator pedal reaction force helps drivers recognize that the situation ahead is changing towards a more critical state so that they can appropriately release their accelerator pedal and be ready to operate the brake pedal. The driving and braking force control, which is used in parallel to the control of the accelerator pedal reaction force, is designed to actively reduce the frequency where the host vehicle driver closes in on a preceding car without driver's intention.

A method for detecting drivers' intentions is essential to facilitate operating mode transitions between driver and driver assistance systems. We propose a driver behavior recognition method using Hidden Markov Models (HMMs) to characterize and detect driving maneuvers and place it in the framework of a cognitive model of human behavior. HMM-based steering behavior models for emergency and normal lane changes as well as for lane keeping were developed using a moving base driving simulator. Analysis of these models after training and recognition tests showed that driver behavior modeling and recognition of different types of lane changes is possible using HMMs.