The integrated navigation system of Inertial Navigation System (INS) and Global Navigation Satellite System (GNSS) is a standard solution in land vehicle navigation applications. Considering a low-cost solution, the reduced inertial sensor system (RISS) is adopted in place of INS to provide better navigation performance for land vehicles with fewer inertial sensors and lower computations. However, low-cost sensors can quickly deteriorate the navigation solution during GNSS outage. Hence, a novel RISS/GNSS method with the assistance of the long short-term memory (LSTM) neural network, which has the ability of adaptive memorizing, is proposed to bridge GNSS outage by means of data fusion. Additionally, zero-velocity detection is applied to advance the navigation performance provided by LSTM algorithm during GNSS outage. We examined the performance of this method by using real road test experiments in a land vehicle equipped with GNSS receivers and inertial sensors in addition to a high end GNSS/INS to provide the reference solution. During 300 second GNSS outage, the experimental results illustrate that this hybrid method based on the LSTM algorithm can enhance the navigation accuracy by 50% when compared to the standalone RISS algorithm, and provide 30% improvements in comparison to NARX algorithm.

Modern parking lots have gradually developed into underground garages to improve the efficient use of space. However, the complex design of parking lots also increases the demands on vehicle navigation. The traditional method of navigation switching only uses satellite signals. After the Position Dilution Of Precision (PDOP) of satellite signals is over the limit, vehicle navigation will enter indoor mode. It is not suitable for vehicles in underground garages to switch modes with a fast-response system. Therefore, this paper chooses satellite navigation, inertial navigation, and the car system to combine navigation. With the condition that the vehicle can freely travel through indoor and outdoor environments, high-precision outdoor environment navigation is used to provide the initial state of underground navigation. The position of the vehicle underground is calculated by the Dead Reckoning (DR) navigation system. This paper takes advantage of the Extended Kalman Filter (EKF) algorithm to provide two freely switchable navigation modes for vehicles in ground and underground garages. The continuity, robustness, fast response, and low cost of the indoor and outdoor switching navigation methods are verified in real-time systems.

Vehicles have to rely on satellite navigation in an open environment. However, satellite navigation cannot obtain accurate positioning information for vehicles in the interior of underground parking lots, as they comprise a semi-enclosed navigation space. Therefore, vehicular navigation needs to take into consideration both outdoor and indoor environments. Actually, outdoor navigation and indoor navigation require different positioning methods, and it is of great importance to choose a reasonable navigation and positioning algorithm solution for vehicles. Fortunately, the integrated navigation of the Global Positioning System (GPS) and the Micro-Electro-Mechanical System (MEMS) inertial navigation system could solve the problem of switching navigation algorithms in the entrance and exit of underground parking lots. This paper proposes a low cost vehicular seamless navigation technology based on the reduced inertial sensor system (RISS)/GPS between the outdoors and an underground garage. Specifically, the enhanced RISS is a positioning algorithm based on three inertial sensors and one odometer, which could achieve a similar location effect as the full model integrated navigation, reduce the costs greatly, and improve the efficiency of each sensor.

In robotics, obstacle avoidance is an essential ability for distance sensor-based robots. This type of robot has axisymmetrically distributed distance sensors to acquire obstacle distance, so the state is symmetrical. Training the control policy with a reinforcement learning method is a trend. Considering the complexity of environments, such as narrow paths and right-angle turns, robots will have a better ability if the control policy can control the steering direction and speed simultaneously. This paper proposes the multi-dimensional action control (MDAC) approach based on a reinforcement learning technique, which can be used in multiple continuous action space tasks. It adopts a hierarchical structure, which has high and low-level modules. Low-level policies output concrete actions and the high-level policy determines when to invoke low-level modules according to the environment’s features. We design robot navigation experiments with continuous action spaces to test the method’s performance. It is an end-to-end approach and can solve complex obstacle avoidance tasks in navigation.

Continuous navigation information for dynamic road vehicles is commonly provided through integrated Inertial Navigation System (INS)/Global Navigation Satellite System (GNSS) solutions. By using fewer inertial sensors and reducing computational requirements, the Reduced Inertial Sensor System (RISS) is a highly suitable alternative to INS for vehicular navigation applications. This article proposes a CNN–Transformer-enhanced GNSS/RISS integrated navigation algorithm based on the RISS Recomputed Method (RRM). Specifically, the RISS Recomputed Method is first used to mitigate RISS errors. Moreover, the CNN and Transformer models are adopted to further estimate the RISS error model, thereby improving observation accuracy and reducing navigation errors during GNSS outages. Finally, the feasibility and effectiveness of the proposed approach are evaluated through land-vehicle navigation experiments. The experimental results demonstrate that the proposed CNN–Transformer algorithm based on RRM can improve positioning accuracy and robustness in complex land-vehicle environments.