Real-Time Path Planning With Virtual Magnetic Fields

Moussa, Majda; Beltrame, Giovanni

doi:10.1109/lra.2021.3063992

Cited by 3 publications

(1 citation statement)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although Kalman filtering provides a solution for filtering nonlinear systems, it also has the following shortcomings: Extended Kalman filtering assumes that the noise and state distributions obey Gaussian distributions, an assumption that is poorly approximated in practical applications, unless the nonlinear system is continuously close to linearity, the results of extended Kalman filtering will be close to the true value. In the process of local linearization of the nonlinear system using Taylor's formula after expansion only the first-order term is retained, which will introduce errors [21]. The extended Kalman filter may prevent the filtering results from converging when the error in the given initial state and initial covariance is large.…”

Section: B Motion Model Of Mobile Unmanned Vehiclesmentioning

confidence: 99%

An Intelligent Navigation Control Approach for Autonomous Unmanned Vehicles via Deep Learning-Enhanced Visual SLAM Framework

Chen,

Liu,

Dong

et al. 2023

IEEE Access

View full text Add to dashboard Cite

For autonomous unmanned vehicles (AUVs), navigation control is an essential concern in academia. Conventionally, existing research works dealt with this issue by resorting to the "Simultaneous Localization and Mapping" (SLAM) technology. Although many SLAM-based approaches had been proposed in recent years, they could not mostly perceive semantic characteristics from dynamic visual scenarios. To deal with this challenge, this paper proposes a navigation control approach for AUVs via a deep learning-enhanced visual SLAM framework. Firstly, the commonly used coordinate system in the motion of AUVs is analyzed, and a mathematical description of the circular arc motion of AUVs is formulated. Then, an up-convex curve model is adopted to realize high-accuracy detection of the bilateral lane lines. On the foundation, a yaw angle guidance-based imitation learning framework is utilized to realize navigation control. This well facilitates the analyzing the causal relationship between scenarios and decisions. Some experiments are conducted by simulating real-world urban road scenes, to testify the efficiency of the navigation control for AUVs. The results show that navigation accuracy can be improved by about 5%.INDEX TERMS autonomous unmanned vehicles; navigation control; deep learning; visual SLAM

show abstract

Section: B Motion Model Of Mobile Unmanned Vehiclesmentioning

confidence: 99%