Telematics box (T-Box) chip-level Global Navigation Satellite System (GNSS) receiver\nmodules usually suffer from GNSS information failure or noise in urban environments. In order to\nresolve this issue, this paper presents a real-time positioning method for Extended Kalman Filter\n(EKF) and Back Propagation Neural Network (BPNN) algorithms based on Antilock Brake System\n(ABS) sensor and GNSS information. Experiments were performed using an assembly in the vehicle\nwith a T-Box. The T-Box firstly use automotive kinematical Pre-EKF to fuse the four wheel speed,\nyaw rate and steering wheel angle data from the ABS sensor to obtain a more accurate vehicle\nspeed and heading angle velocity. In order to reduce the noise of the GNSS information, After-EKF\nfusion vehicle speed, heading angle velocity and GNSS data were used and low-noise positioning\ndata were obtained. The heading angle speed error is extracted as target and part of low-noise\npositioning data were used as input for training a BPNN model. When the positioning is invalid,\nthe well-trained BPNN corrected heading angle velocity output and vehicle speed add the synthesized\nrelative displacement to the previous absolute position to realize a new position. With the data of\nhigh-precision real-time kinematic differential positioning equipment as the reference, the use of the\ndual EKF can reduce the noise range of GNSS information and concentrate good-positioning signals\nof the road within 5 m (i.e. the positioning status is valid). When the GNSS information was shielded\n(making the positioning status invalid), and the previous data was regarded as a training sample, it is\nfound that the vehicle achieved 15 minutes position without GNSS information on the recycling line.\nThe results indicated this new position method can reduce the vehicle positioning noise when GNSS\ninformation is valid and determine the position during long periods of invalid GNSS information
Loading....