Autonomous execution of long-horizon, contact-rich manipulation tasks traditionally requires extensive real-world data and expert engineering, posing significant cost and scalability challenges. This paper proposes a novel framework integrating hierarchical semantic decomposition, reinforcement learning (RL), visual language models (VLMs), and knowledge distillation to overcome these limitations. Complex tasks are decomposed into atomic skills, with RL-trained policies for each primitive exclusively in simulation. Crucially, our RL formulation incorporates explicit force constraints to prevent object damage during delicate interactions. VLMs perform high-level task decomposition and skill planning, generating diverse expert demonstrations. These are distilled into a unified policy via Visual-Tactile Diffusion Policy for end-to-end execution. We conduct comprehensive ablation studies exploring different VLM-based task planners to identify optimal demonstration generation pipelines, and systematically compare imitation learning algorithms for skill distillation. Extensive simulation experiments and physical deployment validate that our approach achieves policy learning for long-horizon manipulation without costly human demonstrations, while the VLM-guided atomic skill framework enables scalable generalization to diverse tasks.

In this paper, we consider a practical integrated sensing and communication (ISAC) scenario in industrial Internet of Things (IIoT). In this scenario, a robot acted as a mobile base station (BS) performing sensing to locate a logistics transport robot (LTR) while also communicating with multiple production lines (PL). We predict the motion parameters of LTR in each time slot and derive the Cramér-Rao bound (CRB) of angle and distance estimation. Afterward, we formulate a joint CRB minimization problem by optimizing the transmit beamforming for communication and sensing. We convert the formulated problem into a two-tier alternating optimization approach by constructing precise surrogates for the non-convex objective functions and constraints. A closed-form expression is derived for solving the outer layer problem. In addition, we employ a convex framework to address the inner layer problem. Numerical results validate the superiority of the proposed algorithm, especially when the BS is far away from the sensing target.

Quadruped manipulators require precise detection of external impact forces to ensure safe and compliant responses during environmental interactions. However, these systems often lack tactile sensors on their body surfaces or force/torque sensors at critical joints. This study introduces a whole-body admittance control framework for quadruped manipulators, utilizing a novel external impact force observer that estimates impact forces acting on the manipulator or the quadruped’s base without relying on dedicated force sensors. The observer leverages the robustness of a super-twisting algorithm (STA) based on the momentum model of quadruped manipulators. Model uncertainties are mitigated using a low-pass filter (LPF) and compensated by ground reaction forces, significantly reducing estimation oscillations during dynamic gaits. By integrating these estimated impact forces, the whole-body admittance control framework enables compliant interactions with the environment and mitigates unsafe behaviors caused by torque saturation through a set-valued feedback loop that constrains command torques within actuation limits, including joint torque boundaries and friction cone constraints of the ground reaction force. Experimental validation across diverse scenarios confirms the effectiveness of this approach in facilitating safe and adaptive interactions between quadruped manipulators and external forces.

To solve the time-optimal problem of velocity planning, various optimization-based methods were proposed in the literature, but these existing methods typically have limitations on completeness and real-time performance. For the scenario of single-axis multipoint (SAMP) motion, this article proposes a global dynamic programming algorithm with local greedy strategies to solve the time-optimal velocity planning problem, which is important for the multiaxis synchronous velocity planning problem. The proposed method, which is called SAMP algorithm, transfers the problem into the splicing problem of interval endpoints and acceleration. Then, based on the assumptions of continuity and monotonicity of piecewise polynomial functions, it derives the optimal motion mapping in these different intervals. Finally, the SAMP algorithm obtains the global time-optimal solution by employing the global dynamic programming with a backtracking algorithm. Simulation and experiments demonstrate that the SAMP algorithm not only has time optimization but also shows good numerical efficiency.

Understanding the environment is crucial for the autonomous navigation of vehicles. Accurately identifying and removing dynamic objects that cause occlusions and noisy pose issues is crucial to the task. The casualty collection point (CCP) is a designated location for treating casualties during disasters. These sites are commonly located in open fields to ensure that the injured receive timely and appropriate care. Therefore, the construction of a 3D map in CCP may encounter additional challenges. In this paper, we introduces a novel algorithm that integrates a learning-based multi-object detection network with a Kalman Filter tracking framework to remove dynamic object traces from the 3D map building, particularly in CCP scenarios, and it redirects attention on the velocity attribute of dynamic objects at the object-level scale. Additionally, we contribute a new dataset specifically designed for the CCP scenario. Comparative experiments conducted on the SemanticKITTI dataset and CCP dataset show that our proposed method achieves the state-of-the-art performance in removing traces of dynamic objects on 3D Map. Dataset is available at https://github.com/haidongwang96/ccp_dataset.

Quadruped robots are being widely deployed in various scenarios with uneven terrains, such as rescue and supervision, due to their ability to climb obstacles and carry heavy loads. However, these robots struggle when faced with complex tasks that require reaching time-varying multiple target locations or landmarks. The visiting order of the landmarks and the total travel cost can significantly impact their overall work efficiency. The situation is worsened by limited on-board computing resources, restricted battery storage, and real-time computing demand for navigation systems. To address this issue, we propose a novel approach of multi-goal path planning specifically designed for quadruped robots. Our system extends the conventional Rapidly-Exploring Random Tree (RRT) algorithm to optimize the visiting order of multi-goal while taking into account the kinematics and safety-distance of quadruped robots. Simulation and experimental results demonstrate that our proposed multi-goal path planning system is more efficient than traditional methods in navigating complex tasks while reaching each sub-target position.

Traditional trajectory planning methods are challenged by high-dimensional robot navigation, particularly in handling high-velocity obstacles and computation efficiency. This paper introduces a novel approach leveraging Dynamic Control Barrier Functions (DCBF) to address these issues. The proposed method ensures safety and precise obstacle avoidance in dynamic environments, demonstrated through superior performance in mobile manipulator experiments. Key contributions include the design of efficient DCBF functions, real-time trajectory planning under dynamic conditions, and validation of the algorithm's effectiveness, offering a significant advancement for mobile manipulators in complex work settings.

This paper addresses the critical objective of achieving rapid state transfer in quantum systems. Increasing control gain to achieve fast convergence can result in poor convergence. To circumvent this, a novel continuous, nonsmooth control is devised, exploiting Lyapunov conditions for quantum systems described by von Neumann equations. This approach ensures swift convergence to the target eigenstate while minimizing control effort and enhancing fidelity compared to prevalent techniques such as bang-bang control, approximate bang-bang control, and standard Lyapunov control. Several illustrative examples are provided to corroborate and validate the efficacy of the proposed methodology.

An increasing number of robotic manipulation tasks now use optical tactile sensors to provide tactile feedback, making tactile servo control a crucial aspect of robotic operations. This paper presents a rapid tactile transfer framework (RTTF) that achieves optical-tactile image sim2real transfer and robust tactile servo control using limited paired data. The sim2real aspect of RTTF employs a semi-supervised approach, beginning with pretraining the latent space representations of tactile images and subsequently mapping different tactile image domains to a shared latent space within a simulated tactile image domain. This latent space, combined with the proprioceptive information of the robotic arm, is then integrated into a privileged learning framework for policy training, which results in a deployable tactile control policy. Our results demonstrate the robustness of the proposed framework in achieving task objectives across different tactile sensors with varying physical parameters. Furthermore, manipulators equipped with tactile sensors, allow for rapid training and deployment for diverse contact-rich tasks, including object pushing and surface following.

In normal operations, when quadruped manipulators with impedance control experience external disturbances, they may become unstable and lose balance due to actuation saturation, affecting their stability, safety, and compliance with the environment. To address this issue, we propose a whole-body compliance controller to prevent unstable behaviors like slip, oscillation, and overshoot, which arise from actuation saturation. The controller includes an admittance scheme with a set-valued operator as the internal feedback, to constrain joint torques within actuators’ limits and ground reaction forces within friction cones to ensure stability against disturbances. Then, it formulates a hierarchical optimization problem using the Hierarchical Quadratic Programming (HQP) to impose the output of the admittance scheme while ensuring physical consistency to maintain compliance behaviors. Unlike traditional compliance control with one-dimensional torque limitations, our approach considers both joints torque limits of manipulator joints and friction cones of quadruped ground reaction as actuation saturation. This ensures overall compliance and stability for the quadruped manipulators, even under significant external forces, regardless of where they are exerted on the robot. We demonstrate through experiments involving variable stiffness environments and external forces during normal operations how effective our approach is in enhancing the safety of quadruped manipulators.

Ensuring product quality while reducing costs is critical in manufacturing scenarios. However, real-world operational factories, particularly in the hydrogen storage industries, pose several challenges, including strict quality control standards and limited but extremely biased data available for model development. To address these challenges, we propose an augmented hybrid learning method for visual defect inspection that leverages the strengths of deep learning and unsupervised learning. The proposed method is developed using only one-class OK samples and then validated on a real-world operational manufacturing line. The experiment results demonstrate that our method achieves a recall rate of nearly 90% with an overkill rate of only 0.6%. This method outperforms several benchmark methods that often struggle to balance high recall and low overkill rates. Experiments with industrial setups show that our method provides a promising solution for visual defect inspection in real-world manufacturing scenarios.

This study presents the development and implementation of an advanced hybrid neural network (HNN) model for predicting nitrogen oxide (NO$_{x}$) emissions and controlling ammonia (NH$_{3}$) injection in a 1-GW generator within a 2-GW operational coal-fired power plant. The HNN model, which integrates both endogenous and exogenous input features to effectively analyze complex relationships, shows significant improvement in accuracy with a forecast skill of 22% compared to multiple benchmark models. The real-world application of the HNN-based control strategy resulted in a slight increase in average outlet NO$_{x}$concentration but remained well within the regulated limit of 50 ppm, while reducing the standard deviation from 9.7 to 4.9 ppm, indicating a more stable and controlled outlet NO$_{x}$concentration. The successful deployment of the HNN model in an operational power plant demonstrates its practical applicability and effectiveness in large-scale industrial settings, ultimately supporting the transition toward a sustainable energy future.

Supporting wireless transmission of large-scale control systems is a challenging task due to the scarcity of wireless resources in the industrial internet of things (IIOT). To reduce wireless resource consumption while maintaining control stability, this paper investigates the wireless networked predictive control system, where only part of the control devices is permitted to transmit their state information to the centralized controller in each control cycle. For the rest unscheduled control devices, the centralized controller predicts their state information via the Gaussian process regression method. To evaluate the control performance and the wireless resources consumption, we formulate a joint optimization problem of control device scheduling, power allocation, and bandwidth allocation. The joint predictive control and communication optimization (JPCCO) scheduling algorithm is proposed to minimize both the control cost and communication cost. As for control device scheduling, we proposed a fuzzy logic based scheduling ranking (FL-SR) method, where control devices are ranked in descending order according to the fuzzy output. Numerical results show that the proposed JPCCO scheduling method with FL-SR outperforms the previous scheduling methods without predictive control, enabling a more stable wireless networked control system with less wireless resources.

Exactly estimating and tracking the motion of surrounding dynamic objects is one of important tasks for the autonomy of a quadruped manipulator. However, with only an onboard RGB camera, it is still a challenging work for a quadruped manipulator to track the motion of a dynamic object moving with unknown and changing velocities. To address this problem, this manuscript proposes a novel image-based visual servoing (IBVS) approach consisting of three elements: a spherical projection model, a robust super-twisting observer, and a model predictive controller (MPC). The spherical projection model decouples the visual error of the dynamic target into linear and angular ones. Then, with the presence of the visual error, the robustness of the observer is exploited to estimate the unknown and changing velocities of the dynamic target without depth estimation. Finally, the estimated velocity is fed into the model predictive controller (MPC) to generate joint torques for the quadruped manipulator to track the motion of the dynamical target. The proposed approach is validated through hardware experiments and the experimental results illustrate the approach's effectiveness in improving the autonomy of the quadruped manipulator.

Age of information (AoI) is an effective performance metric for time-critical industrial Internet of things (IIoT) applications. We investigate status prediction and data aggregation with prediction error awareness, to enhance the AoI performance for short-packet transmission (SPT) in time-critical IIoT. A predict-compare (PredComp) transmission scheme is proposed, where proactive transmission termination is employed in case of prediction error, by comparing the predicted and real updates at source. It is proved to achieve a significant average AoI performance gain over the case without prediction, even under high prediction error probability. In addition, a predict-aggregate-compare (PredAggComp) transmission scheme is proposed, where two status updates are predicted with different prediction horizons and aggregated by utilizing their time correlation. That allows a good tradeoff between the prediction accuracy and the transmission error probability. A closed-form threshold that the PredAggComp scheme outperforms the PredComp scheme is derived. Moreover, prediction horizon adaptation is conducted to minimize the average AoI of the proposed transmission schemes. Simulation results verify the analytical results and show the superiority of the proposed PredComp and PredAggComp schemes, with an average AoI reduction of up to 64% over the case without prediction.

In this paper, a beamforming scheme that aims to support user-wise asymmetric uplink-downlink (UL-DL) traffic in a more energy-efficient manner is proposed for time-division duplex (TDD) millimeter-wave massive multiple-input-multiple-output (MIMO) systems. Assuming that proper data links have been established during the initial access stage for DL or UL traffic, we consider the beamforming problem for UL or DL whose payload traffic is much lighter than the other link. Such asymmetric traffic allows part of the massive MIMO array to be deactivated in order to achieve a higher energy efficiency (EE) while still meeting the spectrum efficiency (SE) requirements for UL or DL. To deal with such a problem, we propose the corresponding phase shifter (PS) deactivation strategies based on different SE constraints for individual mobile stations or users independently, which select the PSs to be deactivated accordingly with low computational complexity. We then propose a novel codebook design method, which relies on the iteratively updated average main beam gain, in order to pursue a flatter beam under asymmetric DL-UL traffic that interacts with the corresponding PS deactivation strategy. The proposed codebook not only offers flexible beam width and flat main beam gain, but also can generate some good candidate codewords to account for the need of beam refinements, after some of the PSs have been deactivated. Simulation results demonstrated the superiority of the proposed energy efficient PS deactivation approach and the corresponding codebook design.

In this paper, a beamforming scheme that aims to support user-wise asymmetric uplink-downlink (UL-DL) traffic in a more energy-efficient manner is proposed for time-division duplex (TDD) millimeter-wave massive multiple-input-multiple-output (MIMO) systems. Assuming that proper data links have been established during the initial access stage for DL or UL traffic, we consider the beamforming problem for UL or DL whose payload traffic is much lighter than the other link. Such asymmetric traffic allows part of the massive MIMO array to be deactivated in order to achieve a higher energy efficiency while still meeting the spectral efficiency (SE) requirements for UL or DL. To deal with such a problem, we propose the corresponding phase shifter (PS) deactivation strategies based on different SE constraints for each mobile stations or user independently, which select the PSs to be deactivated accordingly with low computational complexity. Simulation results demonstrated the superiority of the proposed energy efficient PS deactivation approach and the corresponding codebook design.

In complex urban environments, the Inertial Navigation System (INS) is important for navigating unmanned ground vehicles (UAVs) for its environment-independency and reliability of real-time localization. It is usually employed as the baseline in the case of other sensors failures, such as the GPS, Lidar, or Cameras. However, one problem for the INS is that its estimation error of localization accumulates over time, and thus the estimated trajectories of the UAVs continue to drift away from their ground truths. To solve this problem, this paper proposes an improved algorithm based on the Invariant Extended Kalman Filter (IEKF) for dead-reckoning of autonomous vehicles, which dynamically adjusts the process noise and the observation noise covariance matrixes through Attention mechanism and Recurrent Neural Network (RNN). The algorithm achieves more robust and accurate dead-reckoning localization in the experiments conducted on the KITTI dataset, reducing the translational error by about 45%compared to the baseline.

Grant-free (GF) access is expected to support low-latency services in fifth-generation (5G) systems, while non-orthogonal multiple access (NOMA) has been proposed to enable massive connectivity in cellular networks. However, the performance analysis for the GF access mode based on NOMA is not trivial, especially for large-scale multi-cell networks due to the inherent random near-far phenomenon. In this paper, we exploit tools from stochastic geometry to develop a tractable framework for analysing uplink performance in large-scale multi-cell networks under GF NOMA and short packet transmission. To make the framework tractable, we further transform the intra- and inter-cell interference to an equivalent interference model. The URLLC performance of GF NOMA networks is derived under the assumption of perfect successive interference cancellation (SIC) and short packet transmission. Numerical results obtained from theoretical calculations and Monte Carlo simulations verify the correctness of our analysis.

In this paper, we investigate unmanned aerial vehicle (UAV) assisted communication systems that require quasi-balanced data rates in uplink (UL) and downlink (DL), as well as users’ heterogeneous traffic. To the best of our knowledge, this is the first work to explicitly investigate joint UL-DL optimization for UAV assisted systems under heterogeneous requirements. A hybrid-mode multiple access (HMMA) scheme is proposed toward heterogeneous traffic, where non-orthogonal multiple access (NOMA) targets high average data rate, while orthogonal multiple access (OMA) aims to meet users’ instantaneous rate demands by compensating for their rates. HMMA enables a higher degree of freedom in multiple access and achieves a superior minimum average rate among users than the UAV assisted NOMA or OMA schemes. Under HMMA, a joint UL-DL resource allocation algorithm is proposed with a closed-form optimal solution for UL/DL power allocation to achieve quasi-balanced average rates for UL and DL. Furthermore, considering the error propagation in successive interference cancellation (SIC) of NOMA, an enhanced-HMMA scheme is proposed, which demonstrates high robustness against SIC error and a higher minimum average rate than the HMMA scheme.

In this article, the free-will arbitrary time consensus is formulated for multiagent systems. This consensus protocol is independent of initial conditions and any other system parameters. With such a protocol, the multiagent system is shown to attain consensus as well as average consensus within the prespecified arbitrary time. Agents rendezvous can also be accomplished with the given protocol. Communication imperfections are easily handled with the designed protocol. Robust free-will arbitrary time consensus protocol is also designed. The stability of such nonlinear nonautonomous protocols is established using suitable Lyapunov functions. Simulation examples confirm the theoretical findings.

To suffice the requirement of FCV, a DC-DC converter must have continuous high voltage gain, continuous input current, common grounding between input and output, low electromagnetic interference issues. Besides these, DC-DC converter should be compact with lower voltage stress across different components. A new DCDC converter is proposed which is structured by combining quasi switched boost network and switched capacitor network in this paper to fulfill above requirements. The proposed converter steady state analysis, stress analysis, comparative analysis is presented in this paper. A 200 W power rating converter is validated in experiment.

In motion control systems, feedback signals are often corrupted by noise because of environmental disturbances and measurement errors. Thus, filters are necessary to remove noise to obtain reliable signals. This paper proposes a new sliding mode filter that possesses a parabolic-shaped sliding surface. The proposed filter is an extension of a Jin et al.'s parabolic sliding mode filter by including feed-forward compensating terms for accelerating the tracking speed between the output and the input. Its discrete-time algorithm is developed by using the backward Euler discretization, and its discrete-time implementation does not produce chattering. A numerical example is executed for validating the effectiveness and advantage of the proposed filter.