Pain is a stressor for intensive care unit (ICU) patients, and inadequate pain assessment has been linked to increased morbidity and mortality. Machine learning has demonstrated potential in assisting pain assessment. However, most studies on automated facial pain assessment have primarily been limited to laboratory subjects, with only a few targeting hospitalized infants. They are less practical because ICU patients are primarily older adults, and individual variations in illness and pain threshold can lead to long-term and short-term pain expressions. Furthermore, the texture of aging skin and reduced facial muscle elasticity make it challenging to capture pain expression features. To address these challenges, we present an efficient, weakly supervised approach that models video-based facial pain assessment as a multiple-instance learning problem. Specifically, we introduce a new large-scale Intensive Care Unit Pain Expression Dataset (ICUPED), which contains 714 facial videos from 152 ICU patients (mean age: 62.9 years). We propose a novel differential multiple instance pain assessment network (DMI-PAN) with a differential learning module (DLM). The network preserves the raw pain information from video snippets via uniform sampling and fine-grained instance partitioning. The DLM uses a pretrained coarse classifier to distinguish long-term from short-term pain expressions. It also models facial pain motion to capture dynamic pain information, thereby reducing individual facial variations. In comparison with other techniques, the proposed method achieved state-of-the-art (SOTA) results on both the ICUPED dataset and the publicly available UNBC-McMaster Shoulder Pain Archive dataset, improving the accuracy of the ICUPED low-level and high-level pain classification tasks by 11.1% and 5.2%, respectively. The results demonstrate the promising potential of the developed DMI-PAN model for automating the process of pain assessment in ICU settings.

Sinusoidal oscillators, as excitation sources for impedance measurements, require high signal quality for accurate measurements. However, traditional amplitude control methods, such as automatic gain control (AGC) or Zener clipping amplitude control, introduce either system complexity or additional total harmonic distortion (THD). In this paper, a sinusoidal oscillator topology based on multiple feedback band-pass filter is proposed, which employs antiparallel diode pairs that exploit diodes’ forward characteristics to efficiently generate low-THD, amplitude-tunable sinusoidal signals at low amplitudes. The proposed topology is capable of generating low-distortion sinusoidal signals with specified amplitudes across a frequency range of 10Hz to 1MHz. Within the range of 1kHz to 1MHz, the THD is less than 0.0900%, and below 1kHz, the THD is less than 0.1694%. Methods for generating low-distortion sinusoidal signals are also analyzed. In complex impedance demodulation applications, compared to DDS solution, the improved demodulation accuracy of the proposed topology highlights the indispensable role of high-precision single-frequency excitation sources.

Multiagent path finding (MAPF) is a critical problem in real-world multiagent systems, where agents reach their respective destinations without colliding with one another. Most MAPF solvers assume agents move at constant speeds with no delays and stop upon reaching their goal. However, real-world nonholonomic agents face delays like deceleration, lane changes, and acceleration, which impact efficiency. Moreover, tasks are continuously generated, making it challenging to meet production requirements. To address this issue, we propose a novel approach, the space-level path segment (SLPS) finding algorithm, which bridges the gap between traditional MAPF methods and the real-world requirements of nonholonomic agents. SLPS defines necessary and optional constraints to construct the collision detection graph (CDG) and formulates an optimization problem to minimize task completion time, resulting in the simplified CDG. It then computes a single SLPS, allowing nonholonomic agents to operate at varying speeds without synchronization. In addition, SLPS supports persistent MAPF tasks through four event-triggered methods, enabling flexible replanning in response to dynamic changes. Experimental results demonstrate that SLPS reduces average task completion time compared to the closest state-of-the-art solvers, proving its efficiency for real-world applications.

Telemedicine is promising in digital healthcare management, such as supporting the coronavirus disease 2019 (COVID-19) pandemic. Three-dimensional (3D) ultrasound reconstruction and new view image synthesis, which can assist in diagnosis and reexamine, have significant potential in teleultrasound, especially integrating robotic ultrasound systems (RUSS). Neural Radiance Field (NeRF), an impressive reconstruction method, requires long training times, limiting its practicality in ultrasound. Despite NeRF variants achieving faster optimization, their performance remains confined to natural scene reconstructions. To address this limitation, we propose HFUS-NeRF, a hybrid representation method designed for fast and accurate ultrasound reconstruction. HFUS-NeRF integrates multi-resolution hash-grid and tri-plane representations to represent each sampling point of the ultrasonic wave. A unified model for sampling points from different ultrasonic probes is presented to simulate the wave's propagation through tissues, and the final ultrasound image is rendered using volume rendering. Compared with NeRF-based ultrasound reconstruction, both the hash grid and triplane resolutions can be scaled up more efficiently, improving reconstruction speed. Experimental results demonstrate that HFUS-NeRF enhances reconstruction quality while significantly reducing reconstruction time to mere minutes. Furthermore, we validated HFUS-NeRF's adaptability by reconstruction using images from different types of ultrasound probes, and real-world experiments confirmed its feasibility and transferability, enabling fast ultrasound reconstruction on human subjects.

The multi-agent pickup and delivery problem is central to coordinating multiple agents in real-world applications such as warehouse automation, urban logistics, and robotic delivery networks, where efficient task assignment and pathfinding are vital for maximizing production efficiency. However, existing approaches often struggle to seamlessly integrate task allocation with path planning while also failing to address the demands of continuous pickup and delivery tasks, resulting in suboptimal performance and limited scalability in dynamic environments. To address these problems, we first introduce a novel task allocation approach, which constructs a cost matrix to satisfy pickup and delivery timing constraints for tasks and employs a Mixed-Integer Linear Programming (MILP) model to compute a task assignment matrix queue. Next, the CBS-TAPF framework is proposed, which constructs search forests for tasks and paths to address the joint optimization of task allocation and path planning. This framework is further extended to Continuous Multi-Agent Pickup and Delivery (CMAPD) tasks by dynamically updating the task allocation matrix queue, enhancing robustness and adaptability for real-world, sustained scenarios. Finally, through simulation and real-world experiments, we validated the effectiveness of the proposed methods. The experimental results demonstrate its superiority across diverse environments, ensuring robust performance in various operational scenarios.

Accurate 3D reconstruction in surgical scenarios is essential for visualizing dynamic tissues with complex anatomical geometries. While 3D Gaussian Splatting (3D-GS) has been explored as an efficient approach to scene modeling, occlusion-induced voids and suboptimal detail optimization have limited its application in surgery. This work introduces a Complexity-Guided 3D Gaussian Splatting (CG-3DGS) framework, in which occlusion regions are globally filled by a state-of-the-art optical flow-based video inpainting method. A frequency–spatial aware refinement (FSAR) mechanism is proposed, allowing spectral signatures and spatial gradients to be jointly analyzed to enhance critical anatomical features (e.g., blood vessels). This mechanism adaptively guides Gaussian densification based on scene-specific anatomical complexity. Experimental results demonstrate that the proposed framework achieves higher reconstruction fidelity while maintaining efficient rendering speeds.

Efficient scheduling of multi-shuttle is crucial for optimizing the performance of Automated Storage/Retrieval Systems (AS/RS). Multi-Agent Path Finding (MAPF) techniques play a pivotal role in addressing scheduling challenges by guaranteeing collision-free paths for multiple agents, however the assumptions of MAPF cannot meet the practical applications, such as 1) agents move at constant speeds and change directions instantaneously, 2) agents remain stationary at their destinations, 3) agents have different destinations. In this paper, we propose a novel lifelong multi-shuttle scheduling framework (LMSSF) to fill this gap based on the AS/RS system implemented in Hunan, China. LMSSF can perform re-planning and execution occur simultaneously, ensuring robust performance even in dynamic and uncertain environment. To apply MAPF to practical scenarios, we propose task conflict resolution, an improved single-shot MAPF and a path constraint mechanism to ensure collision-free movement of shuttles and improve the throughput performance of AS/RS system. Empirical evaluations on throughput and occupancy rate of outbound stations demonstrate the superiority of our proposed algorithm. Finally, LMSSF is applied to a real-world system and the experimental results show a 31.8% improvement in throughput compared to conventional strategies.Note to Practitioners—The motivation of this article stems from the challenges posed by the assumptions inherent in most MAPF algorithms when applied to practical AS/RS environments. Traditional MAPF algorithms typically compute discrete collision-free paths based on predefined start and goal locations. However, in real-world scenarios, tasks are continually generated, shuttles are highly dynamic, and various environmental constraints exist. To address these challenges, we propose the LMSSF as a means to adapt existing MAPF algorithms for practical AS/RS systems. This framework incorporates task conflict resolution, path planning optimization, and efficient shuttle control mechanisms. The paths obtained from the MAPF solver can be seamlessly integrated into our framework with minor format conversions. Through comprehensive testing, our algorithm demonstrates significantly improved throughput performance compared to traditional strategies.

Coverage quantification is required in many sequencing datasets within the field of genomics research. However, most existing tools fail to provide comprehensive statistical results and exhibit limited performance gains from multithreading. Here, we present PanDepth, an ultra-fast and efficient tool for calculating coverage and depth from sequencing alignments. PanDepth outperforms other tools in computation time and memory efficiency for both BAM and CRAM-format alignment files from sequencing data, regardless of read length. It employs chromosome parallel computation and optimized data structures, resulting in ultrafast computation speeds and memory efficiency. It accepts sorted or unsorted BAM and CRAM-format alignment files as well as GTF, GFF and BED-formatted interval files or a specific window size. When provided with a reference genome sequence and the option to enable GC content calculation, PanDepth includes GC content statistics, enhancing the accuracy and reliability of copy number variation analysis. Overall, PanDepth is a powerful tool that accelerates scientific discovery in genomics research.

Untreated pain in critically ill patients can lead to immunosuppression and increased metabolic activity, with severe clinical consequences such as tachypnea and delirium. Continuous pain assessment is challenging due to nursing shortages and intensive care unit (ICU) workload. Mechanical ventilation equipment obscures the facial features of many patients in the ICU, making previous facial pain detection methods based on full-face images inapplicable. This paper proposes a facial Action Units (AUs) guided pain assessment network for faces under occlusion. The network consists of an AU-guided (AUG) module, a texture feature extraction (TFE) module, and a pain assessment (PA) module. The AUG module automatically detects AUs in the non-occluded areas of the face. In contrast, the TFE module detects the facial landmarks and crops prior knowledge patches, a random exploration patch, and a global feature patch. Then these patches are fed into two convolutional networks to extract texture features. Afterward, the designed AU guidances and texture features are fused in the PA module to assess the pain state. Extensive validation is conducted on a public dataset and two datasets created in this work. The proposed network architecture achieves superior performance in binary classification, four-class classification, and intensity regression tasks. In addition, we have successfully applied the network to actual data collected in the laboratory environment with excellent results.

2D-to-3D human pose lifting is fundamental for 3D human pose estimation (HPE), for which graph convolutional networks (GCNs) have proven inherently suitable for modeling the human skeletal topology. However, the current GCN-based 3D HPE methods update the node features by aggregating their neighbors’ information without considering the interaction of joints in different joint synergies. Although some studies have proposed importing limb information to learn the movement patterns, the latent synergies among joints, such as maintaining balance are seldom investigated. We propose the Hop-wise GraphFormer with Intragroup Joint Refinement (HopFIR) architecture to tackle the 3D HPE problem. HopFIR mainly consists of a novel hop-wise GraphFormer (HGF) module and an intragroup joint refinement (IJR) module. The HGF module groups the joints by k-hop neighbors and applies a hop-wise transformer-like attention mechanism to these groups to discover latent joint synergies. The IJR module leverages the prior limb information for peripheral joint refinement. Extensive experimental results show that HopFIR outperforms the SOTA methods by a large margin, with a mean per-joint position error (MPJPE) on the Human3.6M dataset of 32.67 mm. We also demonstrate that the state-of-the-art GCN-based methods can benefit from the proposed hop-wise attention mechanism with a significant improvement in performance: SemGCN [42] and MGCN [49] are improved by 8.9% and 4.5%, respectively.

Automated guided vehicle (AGV) is widely used in transportation and distribution of materials. In the development of multi-AGV systems, how to handle deadlocks is a core issue. Most existing researches focus on open systems. Thus those results are not applicable in real-world systems. A few works have paid attention to closed systems recently, but the results are not flexible and generic enough. Therefore, an improved deadlock avoidance algorithm in closed guide-path system is proposed in this paper. The proposed algorithm is divided into an offline stage and an online stage. At the offline stage, the guide-path graph is processed to obtain useful information for the online stage. At the online stage, the algorithm assesses the safety of each resource allocation to ensure a deadlock-free operation. The computational complexity of the algorithm is shown to be$O(|E|)$, where$E$is the set of the edges in the guide-path graph. Based on the algorithm, an overall control strategy is also developed, and then implemented and tested in real systems. It is also compared with Banker’s algorithm and its variants, the results of which show that the proposed algorithm has a better performance.Note to Practitioners—Deadlock is a core issue in guide-path based multi-AGV systems. Once deadlock occurs, the whole system will collapse. This problem is more serious in closed systems, which is paid less attention to in literature. Current deadlock solutions are either too restrictive, resulting in inefficient resource utilization and poor flexibility, or computationally intensive and thus are unable to scale to large systems. To solve this problem, an improved deadlock avoidance algorithm with polynomial computational complexity is proposed in this paper, and it is more flexible than the Banker’s algorithm and its variants. Furthermore, an overall control framework (i.e., including task assignment, path planning and real-time scheduling) is developed based on the deadlock avoidance algorithm, which keeps persistent operation of the considered system while still guaranteeing deadlock-free. However, in this overall control framework, the choice of path is not optimized with respect to travel distance and makespan, which is the direction of future research.

3D perception of objects is critical for many real-world applications, such as autonomous cars and robots. Among them, most state-of-the-art (SOTA) 3D perception systems are based on deep learning models. Recently, the research community found that 3D object classifiers on point cloud based on deep learning are easily fooled by adversarial point cloud craft by attackers. To overcome this, adversarial defenses are considered the most effective ways to improve the robustness of deep learning models, and most adversarial defenses on point cloud are focused on input transformation. However, all previous defense methods decrease the natural accuracy, and the nature of the point cloud classifiers itself has been overlooked. To this end, in this paper, we propose a novel adversarial defense for 3D point cloud classifiers that makes full use of the nature of the point cloud classifiers. Due to the disorder of point cloud, all point cloud classifiers have the property of permutation invariant to the input point cloud. Based on this nature, we design invariant transformations defense (IT-Defense). We show that, even after accounting for obfuscated gradients, our IT-Defense is a resilient defense against SOTA 3D attacks. Moreover, IT-Defense does not hurt clean accuracy compared to previous SOTA 3D defenses. Our code will be available at: https://github.com/cuge1995/IT-Defense.

Abstract The application of traditional 3D reconstruction methods such as structure-from-motion and simultaneous localization and mapping are typically limited by illumination conditions, surface textures, and wide baseline viewpoints in the field of robotics. To solve this problem, many researchers have applied learning-based methods with convolutional neural network architectures. However, simply utilizing convolutional neural networks without taking other measures into account is computationally intensive, and the results are not satisfying. In this study, to obtain the most informative images for reconstruction, we introduce a residual block to a 2D encoder for improved feature extraction, and propose an attentive latent unit that makes it possible to select the most informative image being fed into the network rather than choosing one at random. The recurrent visual attentive network is injected into the auto-encoder network using reinforcement learning. The recurrent visual attentive network pays more attention to useful images, and the agent will quickly predict the 3D volume. This model is evaluated based on both single- and multi-view reconstructions. The experiment results show that the recurrent visual attentive network increases prediction performance in a way that is superior to other alternative methods, and our model has desirable capacity for generalization.

This study investigates the use of a tendon-driven continuum robot to deform a soft object, whereas the robot body is deformed into an arbitrary shape to adapt to a constrained environment. A dynamic estimator (DE) is developed to approximate the Jacobian matrix that associates the actuator input with the deformed output of the soft object. This helps solve the singularity problem and reduce the effects of noise. Then a visual predictive controller (VPC) with a reference trajectory is developed to ensure a smooth operation. A linear extended-state observer (ESO) is further designed to measure the robot states, such that the controller can compensate for the estimation error. Simulations and experiments are performed to verify the proposed control approach.Note to Practitioners—The motivation of this article is to solve the problem of automatic deformation control of soft objects in restricted environments. The existing soft object deformation control is achieved using rigid robots in an open environment, but rigid robots are difficult to use in specific applications where the environment is restricted (e.g., natural orifice surgery). Flexible continuum robots with mechanical compliance can manipulate soft objects in narrow spaces. However, due to environmental constraints, the robot body may be deformed into any shape regardless of the input of the actuator. To solve the problem, this research provides a new visual servo control strategy that deforms soft objects using a continuum robot in a restricted environment. The proposed method can control a flexible robot to manipulate soft objects while taking into account the change in the robot configuration in a restricted environment.

Inherent compliance plays an enabling role in soft robots, which rely on it to mechanically conform to the environment. However, it also limits the payload of the robots. Various variable stiffness approaches have been adopted to limit compliance and provide structural stability, but most of them can only achieve stiffening of discrete fixed regions which means compliance cannot be precisely adjusted for different needs. This paper offers an approach to enhance the payload with finely adjusted compliance for different needs. We have developed a manipulator that incorporates a novel variable stiffness mechanism and a sliding layer mechanism. The variable stiffness mechanism can achieve a 6.4 stiffness changing ratio with a miniaturized size (10 mm diameter for the testing prototype) through interlocking jamming layers with a honeycomb core. The sliding layer mechanism can actively shift the position of the stiffening regions through sliding of jamming layers. A model to predict the robot shape is derived with verifications via an experiment. The stiffening capacity of the variable stiffness mechanism is also empirically evaluated. A case study of a potential application in laparoscopic surgeries is showcased. The payload of the manipulator is investigated, and the prototype shows up to 57.8 percentage decrease of the vertical deflection due to an external load after reconfigurations.

Advanced motor skills are essential for robots to physically coexist with humans. Much research on robot dynamics and control has achieved success on hyper robot motor capabilities, but mostly through heavily case-specific engineering. Meanwhile, in terms of robot acquiring skills in a ubiquitous manner, robot learning from human demonstration (LfD) has achieved great progress, but still has limitations handling dynamic skills and compound actions. We present a composite learning scheme which goes beyond LfD and integrates robot learning from human definition, demonstration, and evaluation. The method tackles advanced motor skills that require dynamic time-critical maneuver, complex contact control, and handling partly soft partly rigid objects. We also introduce the “nunchaku flipping challenge”, an extreme test that puts hard requirements to all these three aspects. Continued from our previous presentations, this paper introduces the latest update of the composite learning scheme and the physical success of the nunchaku flipping challenge.

Flexible continuum robots have exhibited unique advantages in working in an unstructured environment. Many applications require robots to actively control the deformation of soft objects, such as soft tissues in surgery. Thus, this study presents a robust model-predictive deformation control of a soft object using a flexible continuum robot. A linear approximation model for mapping from actuation space of a continuum robot to deformation space of a soft object is established. Jacobian matrix is estimated online by using a robust Geman-McClure estimator. Then, the deformation of the soft object is regulated by using a prediction horizon-based controller with exponential weighting for model uncertainty. The proposed control approach is effective in manipulating a soft object with a flexible continuum robot that is in contact with obstacles.

Electromagnetically actuated microparticles can be widely applied in the field of biomedicine, for its advantages of minimally invasive feature and approachability to complex microenvironments. In this paper, we propose a robust feedback control approach for precise 3D manipulation of a microparticle actuated by a self-constructed electromagnetic coil system. Model uncertainties, environmental disturbances as well as actuator energy loss problem are all taken into account in the controller design. It is shown that this proposed control scheme can enable the entire system to maintain the input-to-state stability in presence of various perturbations. Experimental results have demonstrated the effectiveness of the proposed control approach. Success of the current study will benefit the precise motion control with high throughput in applications of the targeted material delivery.