A novel path planning method for biomimetic robot based on deep learning

Abstract

Purpose This paper aims to design a multi-layer convolutional neural network (CNN) to solve biomimetic robot path planning problem. Design/methodology/approach At first, the convolution kernel with different scales can be obtained by using the sparse auto encoder training algorithm; the parameter of the hidden layer is a series of convolutional kernel, and the authors use these kernels to extract first-layer features. Then, the authors get the second-layer features through the max-pooling operators, which improve the invariance of the features. Finally, the authors use fully connected layers of neural networks to accomplish the path planning task. Findings The NAO biomimetic robot respond quickly and correctly to the dynamic environment. The simulation experiments show that the deep neural network outperforms in dynamic and static environment than the conventional method. Originality/value A new method of deep learning based biomimetic robot path planning is proposed. The authors designed a multi-layer CNN which includes max-pooling layer and convolutional kernel. Then, the first and second layers features can be extracted by these kernels. Finally, the authors use the sparse auto encoder training algorithm to train the CNN so as to accomplish the path planning task of NAO robot.

A Path Planning Method Based on Multi- Objective Cauchy Mutation Cat Swarm Optimization Algorithm for Navigation System of Intelligent Patrol Car

“…In autonomous navigation of mobile robots, global path planning is the process of planning a collision-free optimal path from a starting point to a target point based on known information about the operating environment [23]. The global path is composed of line segments between the sub target point and path discontinuity point.…”

Meta-heuristic techniques for path planning: recent trends and advancements

“…The results obtained from the proposed optimisation model are compared with the artificial bee colony (ABC) optimisation results which evince that the proposed algorithm is effective than ABC for 2D path planning. Recently, Lu et al (2016) have used the deep convolutional NN for the path planning for NAO bio-mimetic robot in static and dynamic environments. The obtained results in terms of various evaluation parameters indicates the dominance of deep convolutional NN in comparison with back propagation NN, support vector machine and PSO.…”

TDPP-Net: Achieving three-dimensional path planning via a deep neural network architecture

“…In recent years, CNNs have achieved extraordinary success due to their impressive performance in various applications such as object recognition [8] and detection [9], image classification [10], semantic segmentation [11], and action recognition [12]. Moreover, CNNs nowadays have also been utilized to address a variety of planning problems [13][14][15][16], where a policy is characterized using a neural network. While performing these tasks, CNNs are typically adopted to extract features either during reinforcement learning [17,18] or imitation learning [19].…”