Bayesian Localization in Real-Time using Probabilistic Maps and Unscented-Kalman-Filters

Abstract

In this paper, based on the fusion of Lidar and Radar measurement data, high-definition probabilistic maps, and a tailored particle filter, a Real-Time Monte Carlo Localization (RT_MCL) method for autonomous cars is proposed. The lidar and radar devices are installed on the ego car, and a customized Unscented Kalman Filter (UKF) is used for their data fusion. Lidars are accurate in determining objects' positions and have a much higher spatial resolution. On the other hand, Radars are more accurate in measuring objects velocities and perform well in extreme weather conditions. Therefore, the merits of both sensors are combined using the UKF to provide pole-like static-objects pose estimations that are well suited to serve as landmarks for vehicle localization in urban environments. These pose estimations are then clustered using the Grid-Based Density-Based Spatial Clustering of Applications with Noise (GB-DBSCAN) algorithm to represent each pole landmarks in the form of a source-point model to reduce computational cost and memory requirements. A reference map that includes pole landmarks is generated off-line and extracted from a 3-D lidar to be used by a carefully designed Particle Filter (PF) for accurate ego-car localization. The particle filter is initialized by the combined GPS+IMU reading and used an ego-car motion model to predict the states of the particles. The data association between the estimated landmarks by the UKF and that in the reference map is performed using Iterative Closest Point (ICP) algorithm. The proposed pipeline is implemented using the high-performance language C++ and utilizes highly optimized math and optimization libraries for best real-time performance. Extensive simulation studies have been carried out to evaluate the performance of the RT_MCL in both longitudinal and lateral localization.

An Innovation in the Development of a Mobile Radio Model for a Dual-Band Transceiver in Wireless Cellular Communication

“…Also, one of the weaknesses of such systems is that they aren't always accurate; for example, if the instructor makes a mistake while taking attendance and places the student as "present" when he isn't, there is no way to know where the student might be in school or even outside of school [3]. Some students can take advantage of these systems because they cannot ensure the student is in his class because he can simply leave class [4] without the instructor noticing and leave the school where he is at risk [5].…”

Walking Trajectory Estimation Using Multi-Sensor Fusion and a Probabilistic Step Model

“…Other sensor fusion combinations for human localization include fusing IMU data with visual odometry [ 15 ], cellular long-term evolution (LTE) data [ 16 ], and UWB data [ 17 ]. Outside of human localization, other techniques combine traditional GPS/IMU fusion with other sensors and models for ground vehicle localization [ 18 , 19 , 20 ]. Other Bayesian approaches combine algorithms with GPS/IMU fusion for UAV localization [ 21 ].…”

Low-Cost Active Monitoring of Attendance using Passive RFID Technology

“…Also, one of the weaknesses of such systems is that it isn't accurate all the time, for example, if the instructor makes a mistake while taking attendance and places the student as "present" while he isn't, there is no way to know where the student might be in school or even outside of school [3]. Some students can take advantage of these kinds of systems as they can't ensure the student is in his class as he can simply leave class [4] without the instructor noticing and leaves the school where he is prone to danger [5]. The appropriate solution will be making a system to take attendance automatically using passive RFID technology.…”