Unmanned Vehicles: Towards Heterogeneous Hardware Approaches

Author(s):  
Fernando G. Tinetti ◽  
Oscar C. Valderrama Riveros
2012 ◽  
Author(s):  
Andrew S. Clare ◽  
Jason C. Ryan ◽  
Kimberly F. Jackson ◽  
M. L. Cummings

2020 ◽  
Vol 1 (3) ◽  
pp. 55-62
Author(s):  
N. А. LEBEDEV ◽  

The article analyzes the structural guidelines for the modernization of the domestic agricultural machinery industry, which are formed in the aspect of a new development model; some types of machine-building products that are innovative in nature. Separate tasks of digitalization for the development of production of unmanned vehicles are considered. It is concluded that in order to seriously promote the structural modernization of agricultural machinery enterprises, it is necessary to give priority to the development strategy of enterprises, which should be based on clear development guidelines for the long-term period.


2000 ◽  
Author(s):  
Dennis Perzanowski ◽  
Alan C. Schultz ◽  
William Adams ◽  
Elaine Marsh

2021 ◽  
Vol 11 (13) ◽  
pp. 5963
Author(s):  
Phuc Thanh-Thien Nguyen ◽  
Shao-Wei Yan ◽  
Jia-Fu Liao ◽  
Chung-Hsien Kuo

In the industrial environment, Autonomous Guided Vehicles (AGVs) generally run on a planned route. Among trajectory-tracking algorithms for unmanned vehicles, the Pure Pursuit (PP) algorithm is prevalent in many real-world applications because of its simple and easy implementation. However, it is challenging to decelerate the AGV’s moving speed when turning on a large curve path. Moreover, this paper addresses the kidnapped-robot problem occurring in spare LiDAR environments. This paper proposes an improved Pure Pursuit algorithm so that the AGV can predict the trajectory and decelerate for turning, thus increasing the accuracy of the path tracking. To solve the kidnapped-robot problem, we use a learning-based classifier to detect the repetitive pattern scenario (e.g., long corridor) regarding 2D LiDAR features for switching the localization system between Simultaneous Localization And Mapping (SLAM) method and Odometer method. As experimental results in practice, the improved Pure Pursuit algorithm can reduce the tracking error while performing more efficiently. Moreover, the learning-based localization selection strategy helps the robot navigation task achieve stable performance, with 36.25% in completion rate more than only using SLAM. The results demonstrate that the proposed method is feasible and reliable in actual conditions.


IEEE Network ◽  
2021 ◽  
Vol 35 (1) ◽  
pp. 101-107
Author(s):  
Bimal Ghimire ◽  
Danda B. Rawat ◽  
Chunmei Liu ◽  
Jiang Li
Keyword(s):  

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Debo Qi ◽  
Chengchun Zhang ◽  
Jingwei He ◽  
Yongli Yue ◽  
Jing Wang ◽  
...  

AbstractThe fast swimming speed, flexible cornering, and high propulsion efficiency of diving beetles are primarily achieved by their two powerful hind legs. Unlike other aquatic organisms, such as turtle, jellyfish, fish and frog et al., the diving beetle could complete retreating motion without turning around, and the turning radius is small for this kind of propulsion mode. However, most bionic vehicles have not contained these advantages, the study about this propulsion method is useful for the design of bionic robots. In this paper, the swimming videos of the diving beetle, including forwarding, turning and retreating, were captured by two synchronized high-speed cameras, and were analyzed via SIMI Motion. The analysis results revealed that the swimming speed initially increased quickly to a maximum at 60% of the power stroke, and then decreased. During the power stroke, the diving beetle stretched its tibias and tarsi, the bristles on both sides of which were shaped like paddles, to maximize the cross-sectional areas against the water to achieve the maximum thrust. During the recovery stroke, the diving beetle rotated its tarsi and folded the bristles to minimize the cross-sectional areas to reduce the drag force. For one turning motion (turn right about 90 degrees), it takes only one motion cycle for the diving beetle to complete it. During the retreating motion, the average acceleration was close to 9.8 m/s2 in the first 25 ms. Finally, based on the diving beetle's hind-leg movement pattern, a kinematic model was constructed, and according to this model and the motion data of the joint angles, the motion trajectories of the hind legs were obtained by using MATLAB. Since the advantages of this propulsion method, it may become a new bionic propulsion method, and the motion data and kinematic model of the hind legs will be helpful in the design of bionic underwater unmanned vehicles.


Sign in / Sign up

Export Citation Format

Share Document