Dynamics-based control offers a promising approach to exploring the motion potential of soft robots. However, inherently infinite degrees of freedom of these systems pose significant challenges for dynamics modeling, closely followed by the pressing robustness concerns arising from finite-dimensional approximations. This paper addresses these issues by proposing a physics-informed dynamics learning neural network and an adaptive fractional-order control for continuum soft robots. Specifically, a deep Lagrangian neural network is first developed with an embedded self-attention mechanism to enhance learning efficiency, accuracy, and data sensitivity. Subsequently, an adaptive fractional-order sliding mode controller is designed, leveraging the inherent historical memory properties of fractional calculus. This controller not only ensures robust shape control but also improves response speed and tracking accuracy. To further handle model discrepancies in the learned dynamics and external disturbances, a nonlinear disturbance observer is introduced to effectively estimate and compensate for lumped uncertainties, thereby ensuring reliable performance. Theoretical analysis confirms the closed-loop stability, while both simulation and experiment results validate the high dynamics fitting accuracy of the proposed network, as well as the robust and precise tracking capability of the fractional-order controller.

The problem of learning-based control for robots has been extensively studied, whereas the security issue under malicious adversaries has not been paid much attention to. Malicious adversaries can invade intelligent devices and communication networks used in robots, causing incidents, achieving illegal objectives, and even injuring people. This article first investigates the problems of optimal false data injection attack scheduling and countermeasure design for car-like robots in the framework of deep reinforcement learning. Using a state-of-the-art deep reinforcement learning approach, an optimal false data injection attack scheme is proposed to deteriorate the tracking performance of a robot, guaranteeing the tradeoff between the attack efficiency and the limited attack energy. Then, an optimal tracking control strategy is learned to mitigate attacks and recover the tracking performance. More importantly, a theoretical stability guarantee of a robot using the learning-based secure control scheme is achieved. Both simulated and real-world experiments are conducted to show the effectiveness of the proposed schemes.

This letter investigates the direct trajectory optimization of the free-floating space manipulator (FFSM). The main purpose is to plan the joint space trajectories to reduce the spacecraft motion due to the joint rotation during the FFSM performing tasks. To improve the calculation efficiency, the adaptive Radau pseudospectral method (A-RPM) is applied to discretize the system dynamics and transform the formulated optimal problem into a nonlinear programming problem (NLP). By adaptively subdividing the current segment and assigning collocation points according to the solution error, high-degree interpolation polynomials are avoided. To verify the effectiveness of the proposed method, a ground micro-gravity platform of the FFSM system is designed by using the air-bearing technique, on which experiments are carried out. The results show that the variation of the base spacecraft is dramatically reduced if the joints rotate along the optimized trajectories.

Urban rail development can increase land value, reduce commute time, and increase accessibility, as reported in the literature. However, little is known about the impact of opening urban rail transit stations on people's sentiment, particularly in the context of large metropolises where population density is significantly high. This paper investigates such impact by studying six new transit stations opened in Hong Kong. People's sentiment and activity in station nearby areas are estimated by tweet sentiment and tweet activity. We use the difference-in-difference model to study the impact of opening new transit stations. Tweet sentiment, tweet activity, tweet content, and footprints of people who visit the station-influenced area ‘before and after’ the opening of transit stations are analyzed. The results suggest that, in general, the introduction of transit stations causes a positive change in tweet activity, and the change is statistically significant after six months. Regarding tweet sentiment, new transit stations tend to pose a mixed effect in a short-term, a positive influence on areas with high-density residential places, yet a negative influence on areas with a large proportion of nature reserve areas. These short-term effects, positive or negative, become not significant in the long term (after twelve months). Our analysis also confirmed that the introduction of new transit stations increased accessibility from (to) other parts of the city to(from) the station's nearby area, which was shown by the expanded locations sustaining users visited. These findings indicate that the urban rail transit system in Hong Kong promotes more active neighborhoods yet does not always promotes positive influence on people's sentiment. Further studies are needed to make future urban rail transit systems promoting active and happy neighborhoods. The study is relevant to the Belt and Road Initiative (BRI) in methodologies, data, and findings. The social media analysis method used in this study, including text mining and sentiment analysis, can be easily extended to multiple language analysis for Singapore, Malaysia, as well as other regions in the belt and road plan. The developed tools could contribute to analyzing the influence of cross-country projects on local neighborhoods in the belt and road plan.

This article investigates the secure control problem for cyber-physical systems when the malicious data are injected into the cyber realm, which directly connects to the actuators. Based on moving target defense (MTD) and reinforcement learning, we propose a novel proactive and reactive defense control scheme. First, the system (A,B) is modeled as a switching system consisting of several controllable pairs (A,Bl) to facilitate the construction of the MTD control scheme. The controllable pairs (A,Bl) can be altered to update system dynamics under certain unpredictable switching probabilities for each subsystem, which can prevent the adversaries from effective attacks. Second, both attack detection and isolation schemes are designed to accurately locate and exclude the compromised actuators from a switching sequence. Third, a reinforcement learning algorithm based on the zero-sum game theory is proposed to design the defense control scheme when there exist no controllable subsystems to switch. To demonstrate the effectiveness of the defense control scheme, a three-tank system under unknown cyber attacks is illustrated.

A novel data-driven framework to monitor the health status of high-speed rail suspension system by measuring train vibrations is proposed herein. Unlike existing methods, this framework does not rely on sophisticated dynamic models or high-fidelity simulations; it combines the power of data and domain knowledge to generate a model that can be trained quickly and adapted easily to different rail systems. In addition, the framework includes a module to generate a training dataset, tackling a typical challenge in real-world system monitoring, namely, the lack of labeled data due to practical limits. Based on the multi-output support vector regression (MSVR), the proposed framework can monitor the stiffness and damping coefficients of the suspension system using vibration signals measured on trains in real time. The framework comprises three modules. First, a simple suspension system dynamics model is built to generate a training dataset. Furthermore, key features are extracted from frequency response curves to reflect the impact of spring and damper degradation. Subsequently, a supervised learning model based on the MSVR is built to predict the stiffness and damping coefficients of suspension systems from features extracted in the second module. Once the model is built, real-time monitoring can be achieved by feeding the vibration signals as they are collected during operations. The proposed framework was evaluated on simulation data for its accuracy and tested on real-world operational data for its practicability.