|
A global path planning algorithm based on the feature map
收藏
Gongchang Ren, Peng Liu, Zhou He
IET Cyber-Systems and Robotics. 2022 (1): 15-24.
DOI: https://doi.org/10.1049/csy2.12040
The feature map is a characteristic of high computational efficiency,
but it is seldom used in path planning due to its lack of expression of
environmental details. To solve this problem, a global path planning
algorithm based on the feature map is proposed based on the
directionality of line segment features. First, the robot searches the
path along the direction of the target position but turns to search in
the direction parallel to the obstacle, which it approaches until the
line between the robot and the target position does not intersect with
obstacles. Then it turns to the target position, keep searching the
path. Meanwhile, the problems of the direction selection of turning
point, corner point and obstacle circumvention in the searching process
are analysed and corresponding solutions are put forth. Finally, a path
optimisation algorithm with variable parameters is proposed, making the
optimised path shorter and smoother. Simulation experiments demonstrate
that the proposed algorithm is superior to A* algorithm in terms of
computation time and path length, especially of the computation
efficiency.
|
|
Long-time target tracking algorithm based on re-detection multi-feature fusion
收藏
Junsuo Qu, Chenxue Tang, Yuan Zhang, Kai Zhou, Abolfazl Razi
IET Cyber-Systems and Robotics. 2022 (1): 38-50.
DOI: https://doi.org/10.1049/csy2.12042
This paper considers the problem of long-term target tracking in complex scenes when tracking failures are unavoidable due to illumination change, target deformation, scale change, motion blur, and other factors. More specifically, a target tracking algorithm, called re-detection multi-feature fusion, is proposed based on the fusion of scale-adaptive kernel correlation filtering and re-detection. The target tracking algorithm trains three kernel correlation filters based on the histogram of oriented gradients, colour name, and local binary pattern features and then obtains the fusion weight of response graphs corresponding to different features based on average peak correlation energy criterion and uses weighted average to complete the position estimation of the tracked target. In order to deal with the problem that the target is occluded and disappears in the tracking process, a random fern classifier is trained to perform re-detection when the target is occluded. After comparing the OTB-50 target tracking dataset, the experimental results show that the proposed tracker can track the target well in the occlusion attribute video sequence in the OTB-100 test dataset and has a certain improvement in tracking accuracy and success rate compared with the traditional correlation filter tracker.
|
|
A mixed target estimation fusion algorithm based on Gibbs-GLMB and federated filter
收藏
Yu Liu, Zhangming Peng, Shibo Gao, Jiangning Li
IET Cyber-Systems and Robotics. 2022 (1): 61-75.
DOI: https://doi.org/10.1049/csy2.12044
Mixed targets are composed of point targets, extended targets, and group targets. The point target can produce one measurement at most, the extended target and the group target can produce multiple measurements, but the sub-goals of the group target have a certain dependency relationship. At this time, the estimated fusion of the group target is converted to the estimated fusion of sub-targets with formation motion structure, and the distance among the sub-targets is very close, which brings difficulties to the estimated fusion of mixed targets. This paper combines the adjacency matrix in graph theory to dynamically model the discernible group target and introduces the concept of deformation. Also, it uses the finite mixture model method to dynamically model the extended target. Then the Gibbs-GLMB algorithm is used to estimate the state and number of the mixed targets. A dynamic detection federated filter fusion algorithm is proposed to fuse the mixed targets state estimates. The effectiveness of the algorithm is verified in the final simulation.
|
|