Knowledge distillation (KD) aims to enhance the performance of lightweight student networks through the guidance of teacher models. However, the existing methods have deficiencies in two key aspects: First, these methods rely heavily on static representation alignment, failing to account for optimization sensitivity in different directions within the distillation subspace; second, they lack a fine-grained mechanism to align critical directional features. To address these issues, we propose Direction Sensitivity–based Knowledge Distillation method (DSKD), which can quantitatively measure the sensitivity of each direction to the loss function at different training stages and dynamically select the optimization direction accordingly. Meanwhile, we designed a directional sensitivities weighted distillation loss. By aligning the parameter matrices of the teacher and student models in the key directions, we can more effectively transfer knowledge and improve the distillation effect. We combined DSKD with multiple advanced distillation strategies and conducted an empirical evaluation in the GLUE benchmark and CIFAR-100. The results showed that this method could significantly improve the performance of existing distillation techniques.

In cluttered environments, a human-following mobile robot must predict the motion intention of the followed human and take environmental obstacles into consideration. Consequently, it brings several challenges, such as the human’s detour direction prediction problem and the visibility maintenance problem for route planning. To overcome these problems, this paper proposes an integrated follow-ahead framework, in which the human’s detour behavior is predicted by the Leg Motion Model-based EKF (LMM-EKF) and the iterative human route search algorithm, followed by the Safe Corridor-based Model Predictive Controller (SCMPC) used to obtain the optimal control solution. Also, a new perspective about visibility is provided in this paper that, via placing multiple obstacle-free safe regions along the human’s intended direction without any complex preprocessing for the point cloud, SCMPC prevents the robot from collision and occlusion simultaneously based on the basic properties of the convex set. The validity of the proposed method is comprehensively verified through real-world experiments.

In this work, we conducted research on deformable object manipulation by robots based on demonstration-enhanced reinforcement learning (RL). We present FADERL (Fuzzy-Augmented Demonstration-Embedded Reinforcement Learning), a novel framework for robotic manipulation of deformable objects that significantly improves reinforcement learning efficiency through synergistic unification of High-Dimensional Takagi-Sugeno-Kang (HTSK) fuzzy systems, Generative Adversarial Behavior Cloning (GABC), and Conditional Policy Learning (CPL). Compared to the Rainbow-DDPG baseline, FADERL achieves 2.01× higher global average reward and reduces standard deviation to 45% while requiring fewer computational resources. To address the high cost of human demonstration collection, we introduce a Nonlinear Model Predictive Control (NMPC)-based data augmentation method that generates high-quality demonstrations at minimal cost. Simulation results demonstrate that NMPC-generated demonstrations enable FADERL to achieve performance comparable to human demonstrations. Physical experiments on fabric manipulation tasks—diagonal folding, central-axis folding, and flattening—achieve success rates of 83.3%, 80.0%, and 96.7% respectively, validating our approach’s effectiveness in real-world scenarios. Unlike computationally intensive large-model approaches, FADERL provides a lightweight, task-specific solution with efficient adaptability, making it suitable for practical robotic applications in manufacturing, medical surgery, and service robotics.

Wearable devices are currently being used to reduce metabolism and assist people with disabilities for daily walking. For the elderly and disabled people, improving the walking stability of wearable devices is a crucial and unsolved research. In particular, the center of mass (CoM) trajectory can reflect the walking state as well as the stability of a person. For this reason, realizing the prediction of CoM trajectory under daily walking is promising to improve the wearable devices. In this article, a method for estimation and prediction of CoM during daily walking was proposed. A visual-inertial-odometry algorithm was used to obtain history CoM trajectories during walking, and the depth information from camera data was extracted by sequential distance embedding method and encode the information into terrain vectors. The trajectory vectors were patched with the corresponding terrain vectors and then realized the fusion of multi-modal data, which were then fed into a well-trained temporal convolution network to output the prediction results. With data from two outdoor datasets, the method in this paper was verified to be able to be used for CoM trajectory prediction for a variety of walking tasks and consume low computational cost. This method has the potential to be extensible in improving the stability of wearable devices, such as exoskeleton, powered prosthetic, and so on.

Current research on grasping state analysis in soft manipulators is limited and lacks broad applicability. In this article, we introduce a novel method that leverages multimodal data from flexible sensors and Inertial Measurement Units (IMUs) to develop a comprehensive grasping state analysis system for multidegree-of-freedom (multi-DOF) pneumatic soft manipulators. A Deep Spiking High-Dimensional Fuzzy Network (DSHTFN) algorithm is specifically designed to analyze the “3S” grasping states of soft manipulators—shaking, stable, and slipping—with greater depth and precision. A novel membership function, the BernoulliArctangent (B-Atan) function, has been designed to accommodate the unique characteristics of spiking input signals and support backpropagation capabilities. Experimental results demonstrate that our proposed method achieves accuracies of 95.66% and 96.05% in opposing-finger and three-fingered soft manipulator operations, respectively. Through comparative analysis with other algorithms, the superior performance of the B-Atan membership function and the DSHTFN approach in analyzing the grasping states of soft manipulators has been validated.

Environment awareness is crucial for enhancing walking safety and stability of amputee wearing powered prosthesis when crossing uneven terrains such as stairs and obstacles. However, existing environmental perception systems for prosthesis only provide terrain types and corresponding parameters, which fail to prevent potential collisions when crossing uneven terrains and may lead to falls and other severe consequences. In this paper, a visual-inertial motion estimation approach is proposed for prosthesis to perceive its movement and the changes of spatial relationship between the prosthesis and uneven terrain when traversing them. To achieve this, we estimate the knee motion by utilizing a depth camera to perceive the environment and align feature points extracted from uneven terrains. Subsequently, an error-state Kalman filter is incorporated to fuse the inertial data into visual estimations to obtain a more robust and accurate estimation, which is then utilized to derive the motion of the whole prosthesis for our prosthetic control scheme. Experiments conducted on our collected dataset and stair walking trials with powered prosthesis show that the proposed method can accurately track the motion of human leg and the prosthesis with the average root-mean-square error of toe trajectory less than 5 cm. The proposed method is expected to enable the environmental adaptive control for prosthesis, thereby enhancing amputee’s safety and mobility in uneven terrains.

Seismic noise suppression refers to a data processing technique utilized to bolster the signal-to-noise ratio of recorded seismic signals. This enhancement in clarity can significantly amplify the efficacy of subsequent analysis and processing endeavors. With the advancement of deep learning, neural networks have significantly outperformed traditional denoising methods in seismic noise reduction tasks. They can process more data in less time and achieve better denoising results, moreover, they do not require limiting assumptions. In this article, we design an end-to-end seismic noise separation model based on the Wave-Unet, which is an adaptation of Unet for the 1-D time domain. Our designed model introduces the selective Kernel convolution into the Wave-Unet to enhance its performance and incorporates an attention-enhanced skip connection to bridge the semantic gap caused by the concatenation of features computed by networks of varying depths. Meanwhile, a joint loss function is used to enhance the model’s ability to learn signal frequency information. We tested our network using synthetic noisy signals and real seismic records from the STEAD dataset and compared the results with the wavelet threshold denoising method and the advanced omni-dimensional dynamic convolution (ODConv network) modules. The results demonstrate that our network performance surpasses the other two methods and can restore clean signals with high resolution without damaging the effective signal.

The quality of breast ultrasound imaging is greatly affected by the contact force of the probe, which largely requires experienced sonographers to complete the clinical examination. We propose a flexible and fully autonomous ultrasound scanning system for breast ultrasound imaging. It consists of an ultrasound machine, a dual robotic arms system, a multi-structured light system, a human–computer interaction system, and a flexible ultrasound probe clamping device (FUPCD). First, the dynamics model of the FUPCD was analyzed, and a closed-loop force control strategy was established. We then implemented an automatic scanning system. The hysteresis characteristics of the FUPCD and transient response of the force controller were experimentally verified. The system could keep the steady-state error less than ± 5% within 0.5 s. Second, the performance of the control system to maintain constant contact force at different scanning speeds (Note to Practitioners—The motivation of this study is to solve the problem of poor image reproducibility in breast ultrasound scanning, but the proposed system can also be applied to ultrasound scanning of other parts of the body. The position, direction, and contact force of the ultrasound probe affects the image quality and repeatability of the ultrasound, thereby affecting the diagnostic ability. Therefore, we propose and develop a flexible and fully autonomous breast ultrasound scanning system. We aimed to improve the autonomy and stability of the scanning process by designing end-to-end automated scanning strategies, flexible clamping devices, and closed-loop force control strategies. Among them, the fully automatic three-dimensional perception and trajectory planning can provide global fitting capabilities to different forms of breast surfaces and control the probe to maintain the best contact posture. At the same time, the fully automatic workflow reduces additional interference and reduces the complexity of the workflow. The flexible ultrasound probe clamping device improves the passive applicability to flexible tissues and reduces the resistance in the scanning process. The closed-loop force control strategy can adjust the contact force in real time. Experiments verified that the repeatability could be evaluated by contact force. A series of human–machine comparison experiments verified the advancement and effectiveness of the system. In future research, we will further solve the problem of abnormalities and repeatability of ultrasound images acquired during the scanning process by combining the multi-modal feedback of images and forces.

Objective:While neuroscience research has established a link between vision and intention, studies on gaze data features for intention recognition are absent. The majority of existing gaze-based intention recognition approaches are based on deliberate long-term fixation and suffer from insufficient accuracy. In order to address the lack of features and insufficient accuracy in previous studies, the primary objective of this study is to suppress noise from human gaze data and extract useful features for recognizing grasp intention.Methods:We conduct gaze movement evaluation experiments to investigate the characteristics of gaze motion. The target-attracted gaze movement model (TAGMM) is proposed as a quantitative description of gaze movement based on the findings. A Kalman filter (KF) is used to reduce the noise in the gaze data based on TAGMM. We conduct gaze-based natural grasp intention recognition evaluation experiments to collect the subject's gaze data. Four types of features describing gaze point dispersion ($f_{var}$), gaze point movement ($f_{gm}$), head movement ($f_{hm}$), and distance from the gaze points to objects ($f_{d_{j}}$) are then proposed to recognize the subject's grasp intentions. With the proposed features, we perform intention recognition experiments, employing various classifiers, and the results are compared with different methods.Results:The statistical analysis reveals that the proposed features differ significantly across intentions, offering the possibility of employing these features to recognize grasp intentions. We demonstrated the intention recognition performance utilizing the TAGMM and the proposed features in within-subject and cross-subject experiments. The results indicate that the proposed method can recognize the intention with accuracy improvements of 44.26% (within-subject) and 30.67% (cross-subject) over the fixation-based method. The proposed method also consumes less time (34.87 ms) to recognize the intention than the fixation-based method (about 1 s).Conclusion:This work introduces a novel TAGMM for modeling gaze movement and a variety of practical features for recognizing grasp intentions. Experiments confirm the effectiveness of our approach.Significance:The proposed TAGMM is capable of modeling gaze movements and can be utilized to process gaze data, and the proposed features can reveal the user's intentions. These results contribute to the development of gaze-based human-robot interaction.

Feature selection is an important preprocessing step in data mining and pattern recognition. The neighborhood rough set (NRS) model is a widely-used rough set model for feature selection on continuous data. All currently known NRS models are defined on a distance metric — mostly the euclidean distance metric — which invalidates the NRS models in scenarios wherein the euclidean distance is ineffective, for example, while considering differing attribute weights. We first introduce the concept of space division of granular-rectangular, and then construct the neighborhood radius in our method by describing the relationship between child and parent spaces, which avoids the use of a distance metric and reduces the search space for the neighborhood radius. This greatly improves both the accuracy and efficiency of NRS. In addition, the upper and lower approximations of the granular-rectangular rough sets (GRRSs) comprise equivalence classes; this results in better performance of GRRS in knowledge representation compared with the traditional NRS. Experimental results on public benchmark datasets reveal that our method, GRRS, achieves higher accuracy than ten popular and state-of-the-art feature-selection methods, including two NRS algorithms. Moreover, GRRS outperforms the established NRS algorithms regarding efficiency, including the state-of-the-art NRS algorithm, GBNRS. All code has been released as an open libary called GRRS:https://github.com/syxiaa/GRRS.

The mechanical work performed by the individual legs affects the metabolic cost of locomotion. The effects of an elastically suspended backpack (ESB) on the mechanical work performed by the individual legs have not yet been quantified. This article explores the impact of variables, such as the stiffness and damper of an ESB, walking speed, and load mass, on the leg mechanical work (LMW). A model integrating an improved bipedal walking submodel and a spring−mass−damper submodel is proposed to estimate the mechanical work performed by the individual legs (LMW model). Experimental data were collected to estimate the accuracy of the proposed model. Seven subjects walked with a loaded ESB prototype at speeds ranging from 3.6 to 6.0 km/h with the suspension engaged and with the suspension locked out. The measured mechanical work performed by the individual legs was compared to the LMW model estimates. The proposed model estimates corresponded well with the empirical results (averageR2= 0.909; estimated average error 3.6%). The LMW model was then used to simulate the effects of variables. The ESB produces positive or negative effects under different variables. With increasing ESB stiffness, the ESB first produces positive effects, then negative effects, and finally approaches the rigid backpack effect. The ESB damper also affects the magnitude of the effect. The smaller the damping, the larger the effect. These results could assist engineers trying to design ESB to minimize the mechanical work performed by the legs which may also minimize the metabolic energy cost.

In this work, we study a novel query type, called top-k,m queries. Suppose we are given a set of groups and each group contains a set of attributes, each of which is associated with a ranked list of tuples, with ID and score. All lists are ranked in decreasing order of the scores of tuples. We are interested in finding the best combinations of attributes, each combination involving one attribute from each group. More specifically, we want the top-k combinations of attributes according to the corresponding top-m tuples with matching IDs. This problem has a wide range of applications from databases to search engines on traditional and non-traditional types of data (relational data, XML, text, etc.). We show that a straightforward extension of an optimal top-k algorithm, the Threshold Algorithm (TA), has shortcomings in solving the km problem, as it needs to compute a large number of intermediate results for each combination and reads moreinputs than needed. To overcome this weakness, we provide here, for the first time, a provably instance-optimal algorithm and further develop optimizations for efficient query evaluation to reduce computational and memory costs and the number of accesses. We demonstrate experimentally the scalability and efficiency of our algorithms over three real applications.