IET Cybersystems and Robotics最新文献

This study presents the overall architecture of HeterBot, a heterogeneous mobile manipulation robot developed in our lab, which is designed for versatile operation in hazardous environments. The most significant feature of HeterBot is the heterogeneous design created by adopting the idea of ‘big arm + small arm’ and ‘big car + mini car’. This combination has the advantage of functional complementation, which achieves performance promotion in both locomotion and manipulation capabilities, making HeterBot distinguished from other mobile manipulation robots. Besides, multiple novel technologies are integrated into HeterBot to expand its versatility and ease of use, including Virtual Robot Experimentation Platform-based teleoperation, reconfigurable end effectors, laser-aided grasping, and manipulation with customised tools. Experimental results validate the effectiveness of HeterBot in various locomotion and manipulation tasks. HeterBot displays huge potential in future applications, such as searching and rescue.

Recurrent Neural Network, Long Short-Term Memory, and Transformer have made great progress in predicting the trajectories of moving objects. Although the trajectory element with the surrounding scene features has been merged to improve performance, there still exist some problems to be solved. One is that the time series processing models will increase the inference time with the increase of the number of prediction sequences. Another problem is that the features cannot be extracted from the scene's image and point cloud in some situations. Therefore, an Obstacle-Transformer is proposed to predict trajectory in a constant inference time. An ‘obstacle’ is designed by the surrounding trajectory rather than images or point clouds, making Obstacle-Transformer more applicable in a wider range of scenarios. Experiments are conducted on ETH and UCY datasets to verify the performance of our model.

The bionic joints composed of pneumatic muscles (PMs) can simulate the motion of biological joints. However, the PMs themselves have non-linear characteristics such as hysteresis and creep, which make it difficult to achieve high-precision trajectory tracking control of PM-driven robots. In order to effectively suppress the adverse effects of non-linearity on control performance and improve the dynamic performance of PM-driven legged robot, this study designs a double closed-loop control structure based on neural network. First, according to the motion model of the bionic joint, a mapping model between PM contraction force and joint torque is proposed. Second, a control strategy is designed for the inner loop of PM contraction force and the outer loop of bionic joint angle. In the inner control loop, a feedforward neuron Proportional-Integral-Derivative controller is designed based on the PM three-element model. In the control outer loop, a sliding mode robust controller with local model approximation is designed by using the radial basis function neural network approximation capability. Finally, it is verified by simulation and physical experiments that the designed control strategy is suitable for humanoid motion control of antagonistic PM joints, and it can satisfy the requirements of reliability, flexibility, and bionics during human–robot collaboration.

The realisation of a model-based controller for a robot with a higher degree of freedom requires a substantial amount of computational power. A high-speed CPU is required to maintain a higher sampling rate. Multicore processors cannot boost the performance or reduce the execution time as the programs are sequentially structured. The neural network is a great tool to convert a sequentially structured program to an equivalent parallel architecture program. In this study, a radial basis function (RBF) neural network is developed for controlling 7 degrees of freedom of the human lower extremity exoskeleton robot. A realistic friction model is used for modelling joint friction. High trajectory tracking accuracies have been obtained. Evidence of computational efficiency has been observed. The stability analysis of the developed controller is presented. Analysis of variance is used to assess the controller's resilience to parameter variation. To show the effectiveness of the developed controller, a comparative study was performe between the developed RBF network-based controller and Sliding Mode Controller, Computed Torque Controller, Adaptive controller, Linear Quadratic Regulator and Model Reference Computed Torque Controller.

Bounding is one of the important gaits in quadrupedal locomotion for negotiating obstacles. The authors proposed an effective approach that can learn robust bounding gaits more efficiently despite its large variation in dynamic body movements. The authors first pretrained the neural network (NN) based on data from a robot operated by conventional model-based controllers, and then further optimised the pretrained NN via deep reinforcement learning (DRL). In particular, the authors designed a reward function considering contact points and phases to enforce the gait symmetry and periodicity, which improved the bounding performance. The NN-based feedback controller was learned in the simulation and directly deployed on the real quadruped robot Jueying Mini successfully. A variety of environments are presented both indoors and outdoors with the authors’ approach. The authors’ approach shows efficient computing and good locomotion results by the Jueying Mini quadrupedal robot bounding over uneven terrain.

The cover image is based on the Research Article Efficient learning of robust quadruped bounding using pretrained neural networks by Zhicheng Wang et al., https://doi.org/10.1049/csy2.12062.

The semantic representation of the trajectory is conducive to enrich the content of trajectory data mining. A trajectory summarisation generation method based on the mobile robot behaviour analysis was proposed to realize the abstract expression and semantic representation of the spatio-temporal motion features of the robot and its environmental interaction state. First, the behavioural semantic modelling and representation of the mobile robot are completed by modelling the sub-trajectory and calculating the topological behaviour (TOP). Second, Chinese word segmentation and semantic slot filling methods are used to combine with hierarchical clustering to perform basic word extraction and classification for describing trajectory sentences. Then, the description language frame is extracted based on the TOP, and the final trajectory summarisation is generated. The result shows that the proposed method can semantically represent robot behaviours with different motion features and topological features, extract two verb-frameworks for describing the sentences according to their topological features, and dynamically adjust the syntactic structure for the different topological behaviours between the target and the environment. The proposed  method can generate semantic information of relatively high quality for spatio-temporal data and help to understand the higher-order semantics of moving robot behaviour.

Asynchronous advantage actor-critic (A3C) algorithm is a commonly used policy optimization algorithm in reinforcement learning, in which asynchronous is parallel interactive sampling and training, and advantage is a sampling multi-step reward estimation method for computing weights. In order to address the problem of low efficiency and insufficient convergence caused by the traditional heuristic exploration of A3C algorithm in reinforcement learning, an improved A3C algorithm is proposed in this paper. In this algorithm, a noise network function, which updates the noise tensor in an explicit way is constructed to train the agent. Generalised advantage estimation (GAE) is also adopted to describe the dominance function. Finally, a new mean gradient parallelisation method is designed to update the parameters in both the primary and secondary networks by summing and averaging the gradients passed from all the sub-processes to the main process. Simulation experiments were conducted in a gym environment using the PyTorch Agent Net (PTAN) advanced reinforcement learning library, and the results show that the method enables the agent to complete the learning training faster and its convergence during the training process is better. The improved A3C algorithm has a better performance than the original algorithm, which can provide new ideas for subsequent research on reinforcement learning algorithms.

The large and heavy-duty hexapod robot has strong motion stability and load capacity, which promises to have a wide range of application prospects in rescue and disaster relief. Multi-mode gait and static stability during walking make the hexapod robot adapt to more diverse terrains, while little research has been conducted on the motion control methods of heavy-duty hexapod robots in complex environments. A novel heuristic whole-body motion control framework for the heavy-duty hexapod robot to traverse complex terrain is presented. By splitting the legged locomotion into a single task, the whole-body motion could be planned in a reasonable time. The terrain adaptation strategy is designed to improve the complex terrain passability. Ground reaction forces are then optimised based on single rigid-body dynamics with heuristics. This framework utilised simple but powerful heuristics to approximate complex dynamics and allows for a single set of parameters for all task conditions. Simulation results demonstrate the robustness and adaptability of the proposed framework.

Particle image velocimetry (PIV) is an essential method in experimental fluid dynamics. In recent years, the development of deep learning-based methods has inspired new approaches to tackle the PIV problem, which considerably improves the accuracy of PIV. However, the supervised learning of PIV is driven by large volumes of data with ground truth information. Therefore, the authors consider unsupervised PIV methods. There has been some work on unsupervised PIV, but they are not nearly as effective as supervised learning PIV. The authors try to improve the effectiveness and accuracy of unsupervised PIV by adding classical PIV methods and physical constraints. In this paper, the authors propose an unsupervised PIV method combined with the cross-correlation method and divergence-free constraint, which obtains better performance than other unsupervised PIV methods. The authors compare some classical PIV methods and some deep learning methods, such as LiteFlowNet, LiteFlowNet-en, and UnLiteFlowNet with the authors’ model on the synthetic dataset. Besides, the authors contrast the results of LiteFlowNet, UnLiteFlowNet and the authors’ model on experimental particle images. As a result, the authors’ model shows comparable performance with classical PIV methods as well as supervised PIV methods and outperforms the previous unsupervised PIV method in most flow cases.

This paper studies a distributed formation problem for non-holonomic mobile robots. Consideration of the leader dynamics of the robots as non-ideal, that is, subject to disturbances/unmodelled variables, is the distinguishing feature of this work. The issue is resolved by a distributed combined disturbance-and-leader estimator, allowing for the distributed reconstruction of the leader's signals. The estimator needs to detect the leader's information and disturbance. In order to reject such disturbance and achieve the formation asymptotically, the control law incorporates the smooth estimator's estimate of the leader disturbance. Furthermore, the stability of the total distributed formation control algorithm is also examined using the Lyapunov technique. Finally, to show the viability of the proposed theoretical results, simulations and actual experiments are carried out.