Using light-weight architectures or reasoning on low-resolution images, recent methods realize very fast scene parsing, even running at more than 100 FPS on a single GPU. However, there is still a significant gap in performance between these real-time methods and the models based on dilation backbones. To this end, we proposed a family of deep dual-resolution networks (DDRNets) for real-time and accurate semantic segmentation, which consist of deep dual-resolution backbones and enhanced low-resolution contextual information extractors. The two deep branches and multiple bilateral fusions of backbones generate higher quality details compared to existing two-pathway methods. The enhanced contextual information extractor named Deep Aggregation Pyramid Pooling Module (DAPPM) enlarges effective receptive fields and fuses multi-scale context based on low-resolution feature maps with little time cost. Our method achieves a new state-of-the-art trade-off between accuracy and speed on both Cityscapes and CamVid dataset. For the input of full resolution, on a single 2080Ti GPU without hardware acceleration, DDRNet-23-slim yields 77.4 $\%$ mIoU at 102 FPS on Cityscapes test set and 74.7 $\%$ mIoU at 230 FPS on CamVid test set. With widely used test augmentation, our method is superior to most state-of-the-art models and requires much less computation. Codes and trained models are available at https://github.com/ydhongHIT/DDRNet.

Bilateral teleoperation system has raised expansive concern as it's excellent behaviors in executing the tasks in the remote, unstructured and dangerous areas via the cooperative operation systems. In this paper, an RBF-neural-network-based adaptive robust control design is proposed for nonlinear bilateral teleoperation manipulators to cope with the main issues including the communication time delay, various nonlinearities and uncertainties. Specifically, the slave environmental dynamics is modeled by a general RBF neural network, and its parameters are estimated and then transmitted for the environmental torque reconstruction in the master side. Since the parameters of neural network (which are non-power signals) are transmitted instead of the traditional environmental torque in the communication channel, the previous existing passivity problem under time delay is avoided. In both of master and slave sides, the trajectory creators are applied to generate the desired trajectories, and the RBF-neural-network-based adaptive robust controllers are designed subsequently to handle the nonlinearities and uncertainties. Theoretically, the proposed control algorithm can guarantee the global stability of bilateral teleoperation manipulators under time delay, and the good transparency performance with both position tracking and force feedback is also achieved simultaneously. The real platform comparative experiments are carried out, and the results show the good position tracking to execute precise operation and the good force feedback to detect the sudden disturbance in the environment dynamics.

In this paper, an output feedback finite-time control method is investigated for stabilizing the perturbed vehicle active suspension system to improve the suspension performance. Since the physical suspension systems always exist the phenomenon of uncertainty or external disturbance, a novel disturbance compensator with finite-time convergence performance is proposed for efficiently compensating the unknown external disturbance. Moreover, the presented compensator is advantageous over the existing ones since it is continuous and can completely remove the matched disturbance. And from the viewpoint of practical implementation, continuous control law will not lead to chattering, which is desirable for electrical and mechanical systems. For the nominal suspension system without disturbance, a homogeneous controller with a simple filter is constructed to achieve a finite-time convergence property, where the filter is applied to obtain the unknown velocity signal. Thus, the nominal controller combines a disturbance compensator into an overall continuous control law, which provides two independent parts with a separate design unite and a highly flexibility for selecting the control gains. According to the geometric homogeneity and finite-time separation principle, it can be shown that the active suspension is finite-time stabilized. A designed example is given to illustrate the effectiveness of the presented controller for improving the vehicle ride performance.

This paper focuses on developing an advanced nonlinear controller for hydraulic system to achieve asymptotic tracking with various disturbances. To accomplish this study, a multilayer neural-networks (NNs) estimator is first developed to improve the compensation accuracy of model-based feed-forward control terms, which can greatly reduce the uncompensated disturbance, then a continuous robust integral of the sign of the error (RISE) control approach is effectively integrated with the multilayer neural-networks (NNs) estimator to deal with the residual mismatched disturbance, in which the RISE feedback gain is adapted online to further decrease the high-gain feedback. At last, by considering the inwardness of matched disturbance in hydraulic systems, it is estimated by another multilayer NNs fully with the residual functional reconstruction inaccuracies handled by a novel adaptive term. As a result, theoretical analysis reveals that the proposed controller guarantees a semi-global asymptotic stability. Extensively comparative experimental results verify the priority of the proposed control strategy, and a 0.2% dynamic tracking accuracy is achieved.

This paper investigates the energy-efficiency design of adaptive control for active suspension systems with a bioinspired nonlinearity approach. To this aim, a bioinspired dynamics-based adaptive tracking control is proposed for nonlinear suspension systems. In many existing techniques, one important effort is used for canceling vibration energy transmitted by suspension inherent nonlinearity to improve ride comfort. Unlike existing methods, the proposed approach takes full advantage of beneficial nonlinear stiffness and damping characteristics inspired by the limb motion dynamics of biological systems to achieve advantageous nonlinear suspension properties with potentially less energy consumption. The stability analysis of the desired bioinspired nonlinear dynamics is conducted within the Lyapunov framework. Theoretical analysis and simulation results reveal that the proposed bioinspired nonlinear dynamics-based adaptive controller has a significant impact on the amount of energy consumption, considering the same basic control method and random excitation of road irregularity for a similar ride comfort performance.

Multilateral tele-robotic system have potential applications in the industry environments with the advantages of cooperative manipulation for the remote and hazardous tasks, and its control design is quite challenging due to several coupling issues such as stability, position tracking, force feedback and cooperative manipulation under time delays, various uncertainties and external disturbance. In this paper, a novel RBFNN ( $Radial\ Basis\ Function\ Neural\ Network$ )-based adaptive sliding mode control design is proposed for nonlinear multilateral tele-robotic system with $n$ -master- $n$ -slave manipulators. The environment force is modeled with a general form via the RBFNN-based environment parameters estimation in the slave side. The estimated environment parameters (non-power signals) are transmitted to rebuild the environment dynamics in the master side and provide the good force feedback for the human operators. The RBFNN-based adaptive sliding mode controllers are designed separately for master and slave manipulators to achieve good position tracking under parameter variations and external disturbance. The coordinated force distribution algorithm is designed to achieve cooperative manipulation with the balance of force acting on the target object. The theoretical analysis is given and the comparative experiment for a nonlinear multilateral tele-robotic system with 2-master-2-slave manipulators is implemented. The results show the good performance of our design.