A Novel Self-Positioning Based on Feature Map Creation and Laser Location Method for RBPF-SLAM

Aiming at the high computational complexity of the traditional Rao-Blackwellized Particle Filtering (RBPF) method for simultaneous localization and Mapping (SLAM), an optimization method of RBPF-SLAM system is proposed, which is based on lidar and least square line segment feature extraction as well as raster, reliability mapping continuity. Validation test results show that less storage in constructing a map with this method is occupied, and the computational complexity is significantly reduced. The effect of noise data on feature data extraction results is effectively avoided. It also solves the problem of error accumulation caused by noninteger grid size movement of unmanned vehicle in time update stage based on Markov positioning scheme. The improved RBPF-SLAM method can enable the unmanned vehicle to construct raster map in real time, and the efficiency and accuracy of map construction are significantly improved.

Beacon-Based Hybrid Routing Protocol for Large-Scale Unmanned Vehicle Ad Hoc Network

In this paper, we designed a beacon-based hybrid routing protocol to adapt to the new forms of intelligent warfare, accelerate the application of unmanned vehicles in the military field, and solve the problems such as high maintenance cost, path failure, and repeated routing pathfinding in large-scale unmanned vehicle network communications for new battlefields. This protocol used the periodic broadcast pulses initiated by the beacon nodes to provide synchronization and routing to the network and established a spanning tree through which the nodes communicated with each other. An NS3 platform was used to build a dynamic simulation environment of service data to evaluate the network performance. The results showed that when it was used in a range of 5 ~ 35 communication links, the beacon-based routing protocol’s PDR was approximately 10% higher than that of AODV routing protocol. At 5 ~ 50 communication links, the result was approximately 20% higher than the DSDV routing protocol. The routing load was not related to the number of nodes and communication link data and the protocol had better performance than traditional AODV and DSDV routing protocol, which reduced the cost of the routing protocol and effectively improved the stability and reliability of the network. The protocol we designed is more suitable for the scenarios of large-scale unmanned vehicle network communication in the future AI battlefield.

Acceleration Anomaly Detection Method for Sensor Axle Box of Unmanned Vehicle

Detecting the anomaly acceleration of the sensor’s axle box of unmanned vehicles is very important for judging the wear condition of vehicle track and evaluating the state of the track. A capacitive accelerometer is connected with acquisition equipment to collect the information of train axle box’s acceleration change when the vehicle is running; instrument amplifier AD8250 with a digitally programmable gain is selected as system signal conversion chip to realize acceleration signal conversion; sliding variance of axle box’s acceleration of the unmanned vehicle is calculated based on sliding variance statistical analysis method, which is confirmed by time window and distance window. Fixing the width of a sliding window according to the response statistics caused by the line excitation link, the acceleration sliding variance is compared with the standard one to determine whether the acceleration is in an anomaly state. The test results show that the anomaly acceleration of the sensor axle box of the unmanned vehicle detected by the proposed method is consistent with the actual results, which provides a reliable basis for vehicle track condition assessment.

Intelligent Detection Method for Roll Stability of Unmanned Vehicle based on Fuzzy Control

When the unmanned vehicle is disturbed by the outside world or carries out dangerous actions such as steering and continuous lane changing, the yaw stability of the unmanned vehicle decreases and the dangerous situation such as rollover is easy to occur. In this paper, the intelligent detection method for roll stability of unmanned vehicles based on fuzzy control is studied. The roll control system of the unmanned vehicle based on a double-layer control strategy is designed. The roll stability of the unmanned vehicle is controlled by an upper-layer fuzzy controller and lower-layer differential braking control. The dynamic model and tire model are built in MATLAB/Simulink to restore the running characteristics of unmanned vehicles. Based on the operation characteristics, the roll stability of the unmanned vehicle’s roll control system based on fuzzy control is tested from three aspects: steady-state response, roll stability and dynamic stability coefficient. The experimental results show that the transverse load’s transfer rate of the proposed method is reduced by more than 0.2% compared with the contrast method, the yaw angular velocity, centroid’s roll angle and roll angle measured under the two working conditions are closer to the actual values, which shows that the method has better control effect and detection accuracy.

Adaptive Preview based Control System for Unmanned Vehicle Path Tracking

The unmanned vehicle control technology is constantly updated. How to accurately track the path has become a key issue. For this reason, a path tracking control system for an unmanned vehicle is designed. The system control module solves the lateral and longitudinal control problems of the unmanned vehicle. The preview compensation controller corrects the deviation of the vehicle approaching the normal track. The steering control module changes the direction of the vehicle based on the motor command signal. In the software part, the kinematics model of the unmanned vehicle in the plane rectangular coordinate system is built. In this model, the steering geometric track is constructed based on the Stanley algorithm. Track tracking preview model can adjust the preview adaptively according to the lateral deviation and heading angle deviation of the vehicle and gets the adaptive preview point. The simulation results show that the maximum absolute value of preview deviation angle, the root mean square of preview deviation angle and the root mean square of tracking error are lower. The effect of path tracking control is better. The effect of path tracking control is less affected by vehicle speed and road environment.

Intelligent Collision Avoidance Method for Motion Obstacles of Unmanned Vehicles

At present, the active technology of automobiles is becoming more and more mature and the emergence of driverless vehicles makes it a hotspot in the field of road safety. A new intelligent collision avoidance method for unmanned vehicle motion obstacles is proposed. The kinematics model of unmanned vehicles is established and linearized to obtain the kinematics linear tracking error model of unmanned vehicles and predict the future behavior of unmanned vehicles. The intelligent collision avoidance can be achieved by improving the artificial potential field model of the unmanned vehicle after understanding the future behavior and obstacle information of the unmanned vehicle. The experimental results show that the method has a high detection rate and success rate of obstacle avoidance and low total time-consuming in the process of behavior selection and path planning. It can quickly make collision avoidance responses and reduce the possibility of collision.

DeepLabV3+/Efficientnet Hybrid Network-Based Scene Area Judgment for the Mars Unmanned Vehicle System

Due to the complexity and danger of Mars’s environment, traditional Mars unmanned ground vehicles cannot efficiently perform Mars exploration missions. To solve this problem, the DeepLabV3+/Efficientnet hybrid network is proposed and applied to the scene area judgment for the Mars unmanned vehicle system. Firstly, DeepLabV3+ is used to extract the feature information of the Mars image due to its high accuracy. Then, the feature information is used as the input for Efficientnet, and the categories of scene areas are obtained, including safe area, report area, and dangerous area. Finally, according to three categories, the Mars unmanned vehicle system performs three operations: pass, report, and send. Experimental results show the effectiveness of the DeepLabV3+/Efficientnet hybrid network in the scene area judgment. Compared with the Efficientnet network, the accuracy of the DeepLabV3+/Efficientnet hybrid network is improved by approximately 18% and reaches 99.84%, which ensures the safety of the exploration mission for the Mars unmanned vehicle system.

Safety Management for Unmanned Aviation

In Air Traffic Management (ATM), Safety Management Systems (SMS) provide the principal vehicle for implementing safety policies, practices and procedures in accordance with internationally agreed Standards. In a constantly changing operating environment, it is essential to maintain SMS effectiveness to maintain and enhance levels of ATM safety. Research at the University Politehnica of Bucharest (UPB) has analysed the major, fast-rising threats to ATM safety emerging in the field of unmanned aviation. After considering the operating environment in terms of control arrangements and unmanned vehicle types, the relationship between ATM and Unmanned Traffic Management (UTM) is examined. It is concluded that the SMS supporting ATM requires enhancement to address the risks arising from the emergence of unmanned aviation and relevant enhancement measures are therefore proposed. Further, research shows that detailed safety management arrangements to support UTM are not yet defined. Indicative SMS requirements for UTM are therefore derived and presented.