The desired rhythmic signals for adaptive walking of humanoid robots should have proper frequencies, phases, and shapes. Matsuoka's central pattern generator (CPG) is able to generate rhythmic signals with reasonable frequencies and phases, and thus has been widely applied to control the movements of legged robots, such as walking of humanoid robots. However, it is difficult for this kind of CPG to generate rhythmic signals with desired shapes, which limits the adaptability of walking of humanoid robots in various environments. To address this issue, a new framework that can generate desired rhythmic signals for Matsuoka's CPG is presented. The proposed framework includes three main parts. First, feature processing is conducted to transform the Matsuoka's CPG outputs into a normalized limit cycle. Second, by combining the normalized limit cycle with robot feedback as the feature inputs and setting the required learning objective, the neural network (NN) learns to generate desired rhythmic signals. Finally, in order to ensure the continuity of the desired rhythmic signals, signal filtering is applied to the outputs of NN, with the aim of smoothing the discontinuous parts. Numerical experiments on the proposed framework suggest that it can not only generate a variety of rhythmic signals with desired shapes but also preserve the frequency and phase properties of Matsuoka's CPG. In addition, the proposed framework is embedded into a control system for adaptive omnidirectional walking of humanoid robot NAO. Extensive simulation and real experiments on this control system demonstrate that the proposed framework is able to generate desired rhythmic signals for adaptive walking of NAO on fixed and changing inclined surfaces. Furthermore, the comparison studies verify that the proposed framework can significantly improve the adaptability of NAO's walking compared with the other methods.

No abstract

Currently, since the model of a driverless bus is not clear, it is difficult for most traditional path tracking methods to achieve a trade-off between accuracy and stability, especially in the case of driverless buses. In terms of solving this problem, a path-tracking controller based on a Fuzzy Pure Pursuit Control with a Front Axle Reference (FPPC-FAR) is proposed in this paper. Firstly, the reference point of Pure Pursuit is moved from the rear axle to the front axle. It relieves the influence caused by the ignorance of the bus’s lateral dynamic characteristics and improves the stability of Pure Pursuit. Secondly, a fuzzy parameter self-tuning method is applied to improve the accuracy and robustness of the path-tracking controller. Thirdly, a feedback-feedforward control algorithm is devised for velocity control, which enhances the velocity tracking efficiency. The proportional-integral (PI) controller is indicated for feedback control, and the gravity acceleration component in the car’s forward direction is used in feedforward control. Finally, a series of experiments is conducted to illustrate the excellent performances of proposed methods.

Loop closure detection plays a very important role in the mobile robot navigation field. It is useful in achieving accurate navigation in complex environments and reducing the cumulative error of the robot’s pose estimation. The current mainstream methods are based on the visual bag of word model, but traditional image features are sensitive to illumination changes. This paper proposes a loop closure detection algorithm based on multi-scale deep feature fusion, which uses a Convolutional Neural Network (CNN) to extract more advanced and more abstract features. In order to deal with the different sizes of input images and enrich receptive fields of the feature extractor, this paper uses the spatial pyramid pooling (SPP) of multi-scale to fuse the features. In addition, considering the different contributions of each feature to loop closure detection, the paper defines the distinguishability weight of features and uses it in similarity measurement. It reduces the probability of false positives in loop closure detection. The experimental results show that the loop closure detection algorithm based on multi-scale deep feature fusion has higher precision and recall rates and is more robust to illumination changes than the mainstream methods.

No abstract