In intelligent transportation system (ITS) applications, vehicles require robust and accurate positioning where global navigation satellite system signals are not available. However, despite extensive research, vehicle positioning with lane-level accuracy in a confined tunnel environment remains a challenging task. In this study, a positioning system based on a synchronized pseudolite system is proposed to enable low-latency and high-accuracy vehicle localization in tunnels. The pseudolites with cascading synchronization are deployed one-dimensionally. The effect of the cascading synchronization is analyzed; and a base station selection strategy is proposed to solve this problem. Fusion mechanization of the vehicle positioning system, digital elevation model, and laser ranging are adopted to provide three-dimensional positioning. Furthermore, deep integration is implemented using a low-cost inertial measurement unit to improve positioning accuracy and stability. The proposed localization solution is experimentally verified using a 4.6 km highway tunnel environment. The results of seven repeated experiments show that the positioning error is better than 11.55 cm.

Accurate context awareness of land vehicles can assist integrated navigation systems. Motion behavior recognition is one context awareness of vehicles, based on which constraint information helps reduce the impact of short-term blockage of navigation signals on radio-frequency-based positioning systems. To improve the reliability of behavior recognition, we proposed a machine learning-based vehicle motion behavior recognition and constraint method (MLMRC). The machine learning-based recognition process is directly driven by raw data from low-cost MEMS-IMU, while the traditional threshold-based method relies on previous experience. Four categories of constraint information—sensor error calibration, velocity constraint, angle constraint, and position constraint—were constructed from the recognition results. Both the simulated vehicle experiment and real vehicle experiment demonstrate the performance of the MLMRC method. When there is a short-term blockage, the MLMRC method can reduce the positioning error from 17.2% to 38.3% compared with the traditional method, which effectively improves positioning accuracy and provides support for autonomous vehicles in complex urban environments.

Ground-based positioning systems have some limitations such as low vertical accuracy, blockage, and multipath effect. Compared with ground-based positioning systems, joint airborne, and ground-based positioning systems can provide better observation geometry and reduce the influence of terrain occlusion on navigation signals received by user receivers. A synchronized joint airborne and ground-based regional positioning system is proposed, which is composed of ground-based stations (GS) and airborne nodes (AN). The ANs relay the signals broadcast by GSs in the way of frequency division multiple access and synchronize the time and frequency between the ANs and GBs as well as the invisible GSs by using the relayed navigation signals, which effectively solves the signal conflict problem and the frequency drift problem of the AN. The prototype system of synchronized joint airborne and ground-based regional positioning system was built and verified by two tests. The test results of time and frequency synchronization performance based on a moving platform show that the maximum deviation of time synchronization error is 974.5 ps, and the frequency stability is 4.49e-11@1s. The comprehensive positioning test results (root mean square) show that the positioning accuracy is 2.36 m and the velocity accuracy is 0.02 m/s.