Wei Pan

Bio: Wei Pan is an academic researcher from Northwestern Polytechnical University. The author has contributed to research in topics: Visual servoing & Feature extraction. The author has an hindex of 6, co-authored 6 publications receiving 120 citations.

Decoupled Visual Servoing With Fuzzy Q -Learning

Abstract: The objective of visual servoing aims to control an object's motion with visual feedbacks and becomes popular recently. Problems of complex modeling and instability always exist in visual servoing methods. Moreover, there are few research works on selection of the servoing gain in image-based visual servoing (IBVS) methods. This paper proposes an IBVS method with Q -Learning, where the learning rate is adjusted by a fuzzy system. Meanwhile, a synthetic preprocess is introduced to perform feature extraction. The extraction method is actually a combination of a color-based recognition algorithm and an improved contour-based recognition algorithm. For dealing with underactuated dynamics of the unmanned aerial vehicles (UAVs), a decoupled controller is designed, where the velocity and attitude are decoupled through attenuating the effects of underactuation in roll and pitch and two independent servoing gains, for linear and angular motion servoing, respectively, are designed in place of single servoing gain in traditional methods. For further improvement in convergence and stability, a reinforcement learning method, Q -Learning, is taken for adaptive servoing gain adjustment. The Q -Learning is composed of two independent learning agents for adjusting two serving gains, respectively. In order to improve the performance of the Q -Learning, a fuzzy-based method is proposed for tuning the learning rate. The results of simulations and experiments on control of UAVs demonstrate that the proposed method has better properties in stability and convergence than the competing methods.

A Neuro-Fuzzy Visual Servoing Controller for an Articulated Manipulator

Abstract: The challenges of selecting appropriate image features, optimizing complex nonlinear computations, and minimizing the approximation errors always exist in visual servoing. A fuzzy neural network controller is developed for a six-degrees-of-freedom robot manipulator to perform visual servoing is proposed to tackle these problems. To increase the accuracy of the image preprocesses, a synthetic image process performs feature extraction for the controller. The method combines a support vector machine contour recognition algorithm and a color-based feature recognition algorithm. For visual servoing, a control method based on the fuzzy cerebellar model articulation controller with the Takagi–Sugeno framework is proposed to directly map an image feature error vector to a desired robot end-effector velocity. This approach achieves visual servoing control without the need of computing the inverse interaction matrix. The control variables are learned and updated by the T–S fuzzy inference. This simplifies the implementation of visual servoing in real-time applications. The proposed control method is used to control an articulated manipulator with an eye-in-hand configuration. The results of simulations and experiments demonstrate that the proposed visual servoing controller has good performance, in terms of stability and convergence.

Collision Avoidance for Redundant Robots in Position-Based Visual Servoing

Abstract: To tackle the problem on trajectory planning or the design of control law, this paper introduces a visual servoing system for a manipulator with redundant joints that the trajectory of the manipulator approaching the target is determined spontaneously by the visual control law. The proposed method resolves joint solution for visual servoing and obstacle avoidance. The work comprises of two procedures, feature extraction for position-based visual servoing (PBVS) and collision avoidance within the working envelope. In the PBVS control, the target pose must be reconstructed with respect to the robot and this results in a Cartesian motion-planning problem. Once the geometric relationship between the target and the end effector is determined, a secure inverse kinematics method incorporating trajectory planning is used to solve the solution of the redundant manipulator by the virtual repulsive torque method. Therefore, the links of the manipulator can always maintain a safe distance from obstacles while approaching the target smoothly. The proposed method is verified with its applicability in experiments using an eye-in-hand manipulator with seven joints. For reusability and extensibility, the system has been coded and constructed in the framework of the Robot Operating System so as that the developed algorithms can be disseminated to different platforms.

An ensemble method for inverse reinforcement learning

Abstract: In inverse reinforcement learning (IRL), a reward function is learnt to generalize experts’ behavior. This paper proposes a model-free IRL algorithm based on an ensemble method , where the reward function is regarded as a parametric function of expected features. In other words, the parameters are updated based on a weak classification method. The IRL is formulated as a problem of a boosting classifier , akin to the renowned Adaboost algorithm for classification, feature expectations from experts’ demonstration, and the trajectory induced by an agent's current policy. The proposed approach takes individual feature expectation as attractor or expeller, depending on the sign of the residuals of the state trajectories between expert's demonstration and the one induced by RL with the currently approximated reward function, so as to tackle its central challenges of accurate inference, generalizability , and correctness of prior knowledge. Then, the proposed method is applied further to approximate an abstract reward function from observations of more complex behavior composed of several basic actions. The results of the simulations in a labyrinth are shown to validate the proposed algorithm. Furthermore, behaviors composed of a set of primitive actions on a soccer robot field are examined for the applicability of the proposed method.

A novel fuzzy three-dimensional grid navigation method for mobile robots:

Abstract: The objective of the autonomous navigation aims to achieve the self-motion control for a robot with the environmental feedbacks and becomes popular recently. Problems of complex modeling, large amo...

Generative Neural Networks for Anomaly Detection in Crowded Scenes

Abstract: Security surveillance is critical to social harmony and people’s peaceful life. It has a great impact on strengthening social stability and life safeguarding. Detecting anomaly timely, effectively and efficiently in video surveillance remains challenging. This paper proposes a new approach, called $S^{2}$ -VAE, for anomaly detection from video data. The $S^{2}$ -VAE consists of two proposed neural networks: a Stacked Fully Connected Variational AutoEncoder ( $S_{F}$ -VAE) and a Skip Convolutional VAE ( $S_{C}$ -VAE). The $S_{F}$ -VAE is a shallow generative network to obtain a model like Gaussian mixture to fit the distribution of the actual data. The $S_{C}$ -VAE, as a key component of $S^{2}$ -VAE, is a deep generative network to take advantages of CNN, VAE and skip connections. Both $S_{F}$ -VAE and $S_{C}$ -VAE are efficient and effective generative networks and they can achieve better performance for detecting both local abnormal events and global abnormal events. The proposed $S^{2}$ -VAE is evaluated using four public datasets. The experimental results show that the $S^{2}$ -VAE outperforms the state-of-the-art algorithms. The code is available publicly at https://github.com/tianwangbuaa/ .

A Review of Physics Simulators for Robotic Applications

Abstract: The use of simulators in robotics research is widespread, underpinning the majority of recent advances in the field. There are now more options available to researchers than ever before, however navigating through the plethora of choices in search of the right simulator is often non-trivial. Depending on the field of research and the scenario to be simulated there will often be a range of suitable physics simulators from which it is difficult to ascertain the most relevant one. We have compiled a broad review of physics simulators for use within the major fields of robotics research. More specifically, we navigate through key sub-domains and discuss the features, benefits, applications and use-cases of the different simulators categorised by the respective research communities. Our review provides an extensive index of the leading physics simulators applicable to robotics researchers and aims to assist them in choosing the best simulator for their use case.

End-to-End Navigation Strategy With Deep Reinforcement Learning for Mobile Robots

Abstract: In this article, we develop a navigation strategy based on deep reinforcement learning (DRL) for mobile robots. Because of the large difference between simulation and reality, most of the trained DRL models cannot be directly migrated into real robots. Moreover, how to explore in a sparsely rewarded environment is also a long-standing problem of DRL. This article proposes an end-to-end navigation planner that translates sparse laser ranging results into movement actions. Using this highly abstract data as input, agents trained by simulation can be extended to the real scene for practical application. For map-less navigation across obstacles and traps, it is difficult to reach the target via random exploration. Curiosity is used to encourage agents to explore the state of an environment that has not been visited and as an additional reward for exploring behavior. The agent relies on the self-supervised model to predict the next state, based on the current state and the executed action. The prediction error is used as a measure of curiosity. The experimental results demonstrate that without any manual design features and previous demonstrations, the proposed method accomplishes map-less navigation in complex environments. Through a reward signal that is enhanced by intrinsic motivation, the agent explores more efficiently, and the learned strategy is more reliable.

Deep GRU Neural Network Prediction and Feedforward Compensation for Precision Multiaxis Motion Control Systems

Abstract: This article proposes a gated recurrent unit (GRU) neural network prediction and compensation (NNC) strategy for precision multiaxis motion control systems with contouring performance orientation. First, some characteristic contouring tasks are carried out on a multiaxis linear-motor-driven motion system, and the true contouring error values obtained by the Newton numerical calculation method are used as the training data of a developed artificial GRU neural network. Essentially, the proposed GRU neural network structure can be viewed as a data-based black-box error model, which can capture the dynamic characteristics of contouring motion rather accurately. The well-trained GRU network can predict the contouring error precisely even under the tasks those have not been conducted during the training session. Moreover, the predicted contouring error is compensated into the reference contour as feedforward compensation to improve the final contouring performance. Comparison between the predicted contouring error and the actual contouring error practically proves the effective prediction ability of the proposed GRU neural network. Furthermore, comparative experiments among proportional–integral–differential, iterative learning control (ILC), and the proposed NNC controller are conducted. The results consistently validate that NNC can basically achieve excellent contouring motion performance as ILC, significantly without need of motion repetition and iteration. Due to the implementation convenience and excellent prediction/compensation ability, the proposed NNC would have good potential in industrial mechatronic applications.

Development of simulation software for mobile robot path planning within multilayer map system based on metric and topological maps

Abstract: This article deals with methods of navigation and mapping of mobile robots in an indoor environment, for example, laboratories, building corridors, and so on. It explains the proposed solution of g...