In this paper, a hybrid method based on deep learning is proposed to visually classify terrains encountered by mobile robots. Considering the limited computing resource on mobile robots and the requirement for high classification accuracy, the proposed hybrid method combines a convolutional neural network with a support vector machine to keep a high classification accuracy while improve work efficiency. The key idea is that the convolutional neural network is used to finish a multi-class classification and simultaneously the support vector machine is used to make a two-class classification. The two-class classification performed by the support vector machine is aimed at one kind of terrain that users are mostly concerned with. Results of the two classifications will be consolidated to get the final classification result. The convolutional neural network used in this method is modified for the on-board usage of mobile robots. In order to enhance efficiency, the convolutional neural network has a simple architecture. The convolutional neural network and the support vector machine are trained and tested by using RGB images of six kinds of common terrains. Experimental results demonstrate that this method can help robots classify terrains accurately and efficiently. Therefore, the proposed method has a significant potential for being applied to the on-board usage of mobile robots.

No abstract

The cable-driven soft arm is mostly made of soft material; it is difficult to control because of the material characteristics, so the traditional robot arm modeling and control methods cannot be directly applied to the soft robot arm. In this paper, we combine the data-driven modeling method with the reinforcement learning control method to realize the position control task of robotic soft arm, the method of control strategy based on deep Q learning. In order to solve slow convergence and unstable effect in the process of simulation and migration when deep reinforcement learning is applied to the actual robot control task, a control strategy learning method is designed, which is based on the experimental data, to establish a simulation environment for control strategy training, and then applied to the real environment. Finally, it is proved by experiment that the method can effectively complete the control of the soft robot arm, which has better robustness than the traditional method.

In order to increase the compatibility between underwater robots and the underwater environment and inspired by the coconut octopus’s underwater bipedal walking, a method was proposed for bipedal walking for an underwater soft robot based on a spring-loaded inverted pendulum (SLIP) model. Using the characteristics of octopus tentacles rolling on the ground, a wrist arm was designed using the cable-driven method, and an underwater SLIP bipedal walking model was established, which makes an underwater soft robot more suitable for moving on uneven ground. An underwater bipedal walking soft robot based on coconut octopus was then designed, and a machine vision algorithm was used to extract the motion information for analysis. Experimental analysis shows that the underwater bipedal walking robot can achieve an average speed of 6.48 cm s−1, and the maximum instantaneous speed can reach 8.14 cm s−1.

No abstract