In modern day, from planetary exploration, disaster response to antiterrorism mission multiped robot has become the major tool. Smart robot with effective gait plan may play a significant role in such missions. But if a leg is injured, it is not possible to repair in this kind of mission. Then robot needs some alternative strategies to complete its mission. This paper proposes a removable sliding leg approach to solve this problem. A fault leg can be detaches and other legs can be slide to better position by the command of operator to get optimum alternative gait configuration. Based on leg sequence, stride length, longitudinal stability and efficiency, alternative gaits are evaluated. This paper recommends tables for different gait sequence with progressive efficiency. These tables can provide options for alternative gait and information about certain damaged leg. Moreover, a procedure for a multi-legged robot to complete its mission after serious leg failure is included. By taking the recommended tables and procedure, the multiped Robot can overcome any fault event and maintain stability and efficiency.

No abstract

No abstract

The maize field environment is complex. Weeds and maize have similar colors and may overlap, and lighting and weather conditions vary. Thus, many methods for the automated differentiation of maize and weeds achieve poor segmentation or cannot be used in real time. In this paper, a weed recognition model based on improved Swin-Unet is proposed. The model first performs semantic segmentation of maize seedlings and uses the resulting mask to identify weeds. U-Net acts as the semantic segmentation framework, and a Swin transformer module is introduced to improve performance. DropBlock regularization, which randomly hides some blocks in crop feature maps, is applied to enhance the generalization ability of the model. Finally, weed areas are identified and segmented with the aid of an improved morphological processing algorithm. The DeepLabv3+, PSANet, Mask R-CNN, original Swin-Unet, and proposed models are trained on a dataset of maize seedling images. The proposed Swin-Unet model outperforms the others, achieving a mean intersection over union of 92.75%, mean pixel accuracy of 95.57%, and inference speed of 15.1 FPS. Our model could be used for accurate, real-time segmentation of crops and weeds and as a reference for the development of intelligent agricultural equipment.

Generally, it is claimed that hexapod walking robots are superior to others. However, in some conditions hexapod suffers from stability problems. To solve the problem of stability, this paper proposes a new gait model of hexapod robot named offset model and also investigates the effects of morphological factor of hexapod robots on their locomotion. A comparison between the offset model and general model of hexapod robot is also included. The stability margin and error margin are used to indicate the stability of a hexapod robot, as it walks with different gaits in arbitrary directions. Two hexapod gaits are compared, which are the diametrical gait and the paired metachronal gait. The former is an artificial gait and the latter is a natural gait. The authors conclude that that the stability of a hexapod robot with the diametrical gait can be enhanced by increasing the offset parameter.