Sharing Driving Between a Vehicle Driver and a Sensor System Using Trust-Factors to Set Control Gains

Abstract

A system is presented that shares control between a driver and sensors to maneuver a vehicle. The vehicle can be driven by a driver, or by the sensors, or they can share control between them. In some circumstances, sharing control can allow a human driver to drive more efficiently and safely. The gains in the controller are automatically set for the human driver and sensors by calculating a trust-factor for the vehicle driver. The sensors can assist a human driver in driving the vehicle to offset for any detected shortcomings; for example, the driver may not be able to see a vehicle ahead or the human driver may be tired. In emergencies, efficient interaction between the vehicle and a human driver can make all the differences. This research explores that collaboration and interfacing. The proposed methods are validated with initial testing.

Simple Expert System for Intelligent Control and HCI for a Wheelchair fitted with Ultrasonic Sensors

“…Ultrasonics [4] are used to identify dangerous circumstances and suggest safer directions and speeds. Systems used at the moment [5][6][7][8] are likely to rely greatly on vision and the experience of the drivers. This paper describes methods to make the driving task easier using an expert system to interpret sensor and joystick signals.…”

“…The way that the wheelchair interacts with a human operator might reduce effectiveness [5][6][7][8][9][10]. Improvements to the interaction are investigated.…”

“…Powered-wheelchairs have often been guided with a joystick [5][6][7][8][9][10][11][12][13] although there are other devices: switches [14], pointers [15,16] or virtual reality transducers [17]. And poweredwheelchairs need to avoid objects, wheelchairs, vehicles and/or people [18,19].…”

“…And poweredwheelchairs need to avoid objects, wheelchairs, vehicles and/or people [18,19]. Various local sensors have been used with wheelchairs: light or laser [20], ultrasonics [5][6][7][8][9][10][11][12][13] or infra-red [21]. Positioning has used tilt, gyro, odometry or acoustic [22].…”

Analysis of Reaction Times and Time-Delays Introduced into an Intelligent HCI for a Smart Wheelchair

“…Wheelchairs are often controlled with manual input transducers, for example joysticks [15] although other input transducers have been used, such as pointers [16,17], switches [18,19], or a custom built Human Computer Interaction (HCI) in the form of a virtual reality interface [20]. The controllers usually interface between a lower current input device with a higher current actuator that typically drives a motor(s) connected to a wheel(s).…”