Gait recognition is one of the key technologies for exoskeleton robot control. The existing gait recognition methods cannot meet the needs of real-time control well in terms of recognition accuracy and robustness. In this paper, a gait recognition method based on the recurrent neural network and fully convolutional network (RNN-FCN) algorithm is proposed. In this paper, a human lower limb gait information acquisition device is developed, ten types of human lower limb gait data are collected, and a human gait recognition model is constructed using the RNN-FCN algorithm. The experimental results demonstrate that the RNN-FCN algorithm achieves an average recognition classification accuracy of 94.43% in the experiments, outperforming the other four algorithms.

Aiming at mimicking the jumping locomotion of water striders, a new continuous jumping robot on water is proposed. Compared with the horizontal rowing motion, the jumping capability of water striders is challengeable to imitate, since the impact force on water is easy to cause the sinking of the robot. In this paper, a jumping mechanism based on springs is designed to produce a large thrust for the robot to jump. The shape of supporting legs and center of gravity of the robot are carefully designed so that the robot can jump on the surface continuously and smoothly. Influences of several critical factors, including the area of supporting legs, spring stiffness and jumping angle, on jump performance are analyzed by means of dynamic simulation and experiments. The fabricated robot weighs about 10.2 g and can continuously jump on water with the maximum leap height and length of 120 mm and 410 mm, respectively.

Aiming at mimicking water strider's water-surface locomotion, this study proposes a new miniature surface tension-driven robot. A key feature of this robot is that its actuating legs possess ellipse-like spatial trajectories like water strider by using a cam-link mechanism, and never pierces water surface when rowing. A set of simple models and equations are proposed to analyze the interaction forces between leg and water as well as the critical condition for a leg penetrating a water surface. The final fabricated robot weights about 3.9 g with a load capacity of 5.6 g. By controlling the motions of actuating legs, the robot can freely and stably walk on water with different gaits. The maximum forward and turning speeds of the robot are measured as 16 cm/s and 23 °/s, respectively. Moreover, a similarity analysis with Bond Number and Weber Number reveals that the locomotion of this robot is quite analogous to that of a water strider: surface tension force dominates the lifting force and plays a major role in the propulsion.