Current Pose Research Articles

Graphene Composite Modified Manganese Dioxide Cathode Materials for Thermal Batteries

Abstract Limitations on rated voltage and discharge current density pose challenges to battery miniaturisation, affecting their application in missiles and other weapon systems. A modification method of graphene composite manganese dioxide (MnO2) cathode material has been proposed. This method enhances the performance of lithium manganese dioxide thermal batteries (heat activated reserve batteries) by achieving a continuous discharge time from milliseconds to seconds, with a single-cell voltage exceeding 2.6V and a cathode output of 160 mA/cm2. Experimental results indicate that graphene-composite modification improves the output performance of individual lithium manganese dioxide thermal cells and facilitates the reduction of thermal battery design volume. However, further research is necessary to address the relatively low output current density of this thermal battery system.

Unsupervised Active Visual Search With Monte Carlo Planning Under Uncertain Detections.

We propose a solution for Active Visual Search of objects in an environment, whose 2D floor map is the only known information. Our solution has three key features that make it more plausible and robust to detector failures compared to state-of-the-art methods: i) it is unsupervised as it does not need any training sessions. ii) During the exploration, a probability distribution on the 2D floor map is updated according to an intuitive mechanism, while an improved belief update increases the effectiveness of the agent's exploration. iii) We incorporate the awareness that an object detector may fail into the aforementioned probability modelling by exploiting the success statistics of a specific detector. Our solution is dubbed POMP-BE-PD (Pomcp-based Online Motion Planning with Belief by Exploration and Probabilistic Detection). It uses the current pose of an agent and an RGB-D observation to learn an optimal search policy, exploiting a POMDP solved by a Monte-Carlo planning approach. On the Active Vision Dataset Benchmark, we increase the average success rate over all the environments by a significant 35 % while decreasing the average path length by 4 % with respect to competing methods. Thus, our results are state-of-the-art, even without any training procedure.

A Review of 3D Human Pose Estimation

Abstract. Visual perception and human body recognition are fundamental capabilities required for effective and safe interactions between artificial intelligence (AI), computer vision, and humans in real-world scenarios. Recent groundbreaking developments in AI and computer vision have resulted in major advancements in human body recognition technology. However, research in human body recognition is still in the early stages of the product lifecycle. Identifying the three-dimensional locations of the joints in the human body from pictures or videos is known as 3D posture estimation. Although it is widely used in areas like human motion analysis and robotics, it continues to be a difficult task due to challenges such as depth ambiguity and the scarcity of robust datasets. Over the past decade, numerous methods have been developed, many of which are based on deep learning, significantly improving the performance of existing benchmarks. A comprehensive literature review of this field is crucial for future development. However, in nowadays,more and more such research has mainly concentrated on traditional techniques, requirement for a comprehensive examination of tools based on deep learning. This paper delivers a thorough overview of current deep learning-based 3D pose estimation algorithms, outlining their advantages and limitations while providing a detailed understanding of the field. It also explores commonly used benchmark datasets and methods for analyzing human poses in unlabeled field images, providing a thorough comparative analysis. Finally, insights are provided to aid in the design of future models and algorithms.

3D Pose Nowcasting: Forecast the future to improve the present

Technologies to enable safe and effective collaboration and coexistence between humans and robots have gained significant importance in the last few years. A critical component useful for realizing this collaborative paradigm is the understanding of human and robot 3D poses using non-invasive systems. Therefore, in this paper, we propose a novel vision-based system leveraging depth data to accurately establish the 3D locations of skeleton joints. Specifically, we introduce the concept of Pose Nowcasting, denoting the capability of the proposed system to enhance its current pose estimation accuracy by jointly learning to forecast future poses. The experimental evaluation is conducted on two different datasets, providing accurate and real-time performance and confirming the validity of the proposed method on both the robotic and human scenarios.

Occlusion‐robust markerless surgical instrument pose estimation

AbstractThe estimation of the pose of surgical instruments is important in Robot‐assisted Minimally Invasive Surgery (RMIS) to assist surgical navigation and enable autonomous robotic task execution. The performance of current instrument pose estimation methods deteriorates significantly in the presence of partial tool visibility, occlusions, and changes in the surgical scene. In this work, a vision‐based framework is proposed for markerless estimation of the 6DoF pose of surgical instruments. To deal with partial instrument visibility, a keypoint object representation is used and stable and accurate instrument poses are computed using a PnP solver. To boost the learning process of the model under occlusion, a new mask‐based data augmentation approach has been proposed. To validate the model, a dataset for instrument pose estimation with highly accurate ground truth data has been generated using different surgical robotic instruments. The proposed network can achieve submillimeter accuracy and the experimental results verify its generalisability to different shapes of occlusion.

Visual inspection and grasping methods based on deep learning

Aiming at the problems of existing robot grasping systems that have high hardware requirements, are difficult to adapt to different objects, and produce large harmful torques during the grasping process, a visual detection and grasping method based on deep learning is proposed. The channel attention mechanism is used to improve YOLO-V3, enhance the network's ability to extract image features, improve the effect of target detection in complex environments, and increase the average recognition rate compared with the original . Aiming at the problem of discreteness of the current pose estimation angle, a minimum area bounding rectangle (MABR) algorithm based on the main network embedded in the Visual Geometry Group 16 (VGG-16) is proposed to perform grasping pose estimation and angle optimization. The average error between the improved grasping angle and the actual angle of the target is less than , which greatly reduces the harmful torque applied by the two-finger manipulator to the object during the grasping process. A visual grasping system was built using UR5 robotic arm, pneumatic two-finger manipulator, Realsense D435 camera and ATI-Mini45 six-dimensional force sensor. Experiments show that the proposed method can effectively grasp and classify different objects, has low hardware requirements, and reduces harmful torque by about , thereby reducing damage to objects. It has good application prospects.

Image-Based Fitness Yoga Pose Recognition: Using Ensemble Learning and Multi-head Attention

With the increasing awareness of fitness, more and more people are choosing to participate in fitness activities. Yoga, as a form of exercise that improves both physical and mental health, is becoming increasingly popular worldwide. In order to assist yoga practitioners in more effective training through automated or semi automated systems, improve training effectiveness, assist professional athletes in training through intelligent recognition systems, correct movements, and improve athletic performance. This paper proposes a method that addresses the low accuracy issue of current yoga pose recognition algorithms by integrating multi-head attention mechanism and ensemble learning. Firstly, the Mixup algorithm is used to enhance yoga movement images. Subsequently, convolutional features are extracted from the images using the ResNet101 and VGGNet19 transfer learning models. Finally, the extracted convolutional features are combined and stacked using a multi-head attention mechanism. Model training, validation, and testing are performed using the Soft target cross-entropy loss function. Experimental results demonstrate that the proposed method achieves a training accuracy of 100%, a validation accuracy of 89.94%, a testing accuracy of 93.79%, and a detection speed of 297 frames per second. Overall, this method demonstrates high stability and robustness, providing a technological foundation for intelligent recognition of yoga poses.

Progressively global–local fusion with explicit guidance for accurate and robust 3d hand pose reconstruction

Parametric and non-parametric methods are two commonly used strategies in current 3D hand pose reconstruction. Parametric methods predict low-dimensional parameters to fit a predefined hand model to the input image. Benefiting from the prior knowledge of hand models, parametric methods guarantee plausible hand poses, whereas the pose estimation accuracy is limited due to nonlinear regression and spatial information loss. Differently, non-parametric methods directly estimate the coordinates of keypoints or mesh vertices from the input image. The reconstructed 3D hand poses show high precision but may be less robust. In this paper, we integrate the advantages of two methods for accurate and robust hand pose reconstruction. Specifically, we disentangle the hand pose reconstruction into global modeling and local refinement, which is performed in a coarse-to-fine manner. Firstly, we utilize global features from the encoder to generate the initial estimation by a parametric method, which aims to provide the prior knowledge of the human hand for subsequent processes. Then, we gradually fuse multi-scale contextual features for local refinement by explicitly integrating global prior information and local visual features. In particular, we introduce a consecutive pixel-aligned feature retrieval module to extract fine-grained information from visual features, thereby achieving pixel-level alignment. Furthermore, we demonstrate that our method can be extended to weakly-supervised learning where only sparse pose annotations are needed, potentially alleviating the burden of meticulous mesh annotation. The effectiveness and robustness of our method are substantiated through both fully- and weakly-supervised experiments, demonstrating superior performance compared to state-of-the-art methods. We plan to release our code at https://github.com/Kun-Gao/P_GLFnet.

Optimization design and key-term separation identification of parallel six-dimensional pose sensor with high sensitivity and high precision

The integrated bearing-positioning parallel manipulator is an important mean for ground testing of space optical telescope before being launched into space. To ensure positioning accuracy, the manipulator requires a pose sensor for the end-effector measurement with six degrees of freedom (DOF), real-time, high-precision, and operation in a vacuum environment. However, it is challenging for the current pose sensor to simultaneously meet all these requirements. In this paper, a novel concept of six-dimensional pose sensor based on parallel mechanism is proposed. A new mechanism design approach is presented to achieve the large measurement range, real-time measurement performance, and high accuracy measurement based on performance atlas. First, the GF sets synthesis is developed to optimize the configuration of pose sensor. Next, two new design indicators are proposed to evaluate the real-time and high accuracy performance. Mechanism parameters are optimized by combining with mechanism singularity analysis. To guarantee high measurement accuracy, a key-term separation identification method with double neural networks is presented. Experiments on 6-UPS pose sensor demonstrate the effectiveness of the proposed mechanism design and key-term identification approach.

3D Character Animation and Asset Generation Using Deep Learning

Besides video content, a significant part of entertainment is represented by computer games and animations such as cartoons. Creating such entertainment is based on two fundamental steps: asset generation and character animation. The main problem stems from its repetitive nature and the needed amounts of concentration and skill. The latest advances in deep learning and generative techniques have provided a set of powerful tools which can be used to alleviate these problems by facilitating the tasks of artists and engineers and providing a better workflow. In this work we explore practical solutions for facilitating and hastening the creative process: character animation and asset generation. In character animation, the task is to either move the joints of a subject manually or to correct the noisy data coming out of motion capture. The main difficulties of these tasks are their repetitive nature and the needed amounts of concentration and skill. For the animation case, we propose two decoder-only transformer based solutions, inspired by the current success of GPT. The first, AnimGPT, targets the original animation workflow by predicting the next pose of an animation based on a set of previous poses, while the second, DenoiseAnimGPT, tackles the motion capture case by predicting the clean current pose based on all previous poses and the current noisy pose. Both models obtained good performances on the CMU motion dataset, with the generated results being imperceptible to the untrained human eye. Quantitative evaluation was performed using mean absolute error between the ground truth motion vectors and the predicted motion vector. For both networks AnimGPT and DenoiseAnimGPT errors were 0.345, respectively 0.2513 (for 50 frames) that indicates better performances compared with other solutions. For asset generation, diffusion models were used. Using image generation and outpainting, we created a method that generates good backgrounds by combining the idea of text conditioned generation and text conditioned image editing. A time coherent algorithm that creates animated effects for characters was obtained.

Research on Vehicle Pose Detection Method Based on a Roadside Unit.

Vehicle pose detection plays a vital role in modern automotive technology, which can improve driving safety, enhance vehicle stability and provide important support for the development of autonomous driving technology. The current pose estimation methods have the problems of accumulation errors, large algorithm computing power, and expensive cost, so they cannot be widely used in intelligent connected vehicles. This paper proposes a vehicle pose detection method based on an RSU (Roadside Unit). First, the on-board GPS performs the positioning of the target vehicle and transmits the positioning information to the RSU through the UDP (User Data Protocol). Next, the RSU transmits a forward command to the OBU (On-board Unit) through the UDP. The OBU sends the command to the ECU (Electronic Control Unit) to control the vehicle forward. Then, the RSU detects and tracks the vehicle. The RSU takes pictures of two images before and after the movement and obtains the coordinates of the four angle points and the center point by image processing. The vehicle heading direction is determined by the moving direction of the center point of the front and rear two images. Finally, the RSU captures the vehicle images in real time, performs the process of tracking, rectangular fitting and pose calculation to obtain the pose information and transmits the information to the OBU to complete the whole process of vehicle pose detection and information transmission. Experiments show that the method can realize accurate and efficient detection of vehicle pose, meet the real-time requirements of vehicle pose detection, and can be widely used in intelligent vehicles.

A novel high‐impedance neutral grounding method for medium‐ or large‐size hydroelectric generators

AbstractAs the capacity of medium or large hydroelectric generators increases, conventional grounding methods face challenges in effectively limiting single‐phase to earth fault current and neutral displacement voltage within acceptable range. Excessive fault current and neutral displacement voltage pose threats to the stability and safety of power generation and transmission systems. Inherent design deficiencies in conventional grounding methods lead to failures in meeting fault current and voltage requirements. To address this, this paper proposes a novel grounding method utilizing high impedance to restrict excessive fault current and neutral displacement voltage. The method minimizes both fault current and neutral displacement voltage by optimally selecting device parameters through minimal iterative trials. Additionally, a novel indicator is introduced to evaluate the effectiveness of grounding method by monitoring changes in neutral displacement voltage. The method is tested through theoretical calculation and field experiments, successfully implemented in large‐size hydroelectric generator.

Active Vibration Avoidance Method for Variable Speed Welding in Robotic Friction Stir Welding Based on Constant Heat Input.

Robotic Friction Stir Welding (RFSW) technology integrates the advantages of friction stir welding and industrial robots, finding extensive applications and research in aerospace, shipbuilding, and new energy vehicles. However, the high-speed rotational process of friction stir welding combined with the low stiffness characteristics of serial industrial robots inevitably introduces vibrations during the welding process. This paper investigates the vibration patterns and impacts during the RFSW process and proposes an active vibration avoidance control method for variable speed welding based on constant heat input. This method utilizes a vibration feedback strategy that adjusts the spindle speed actively if the end-effector's vibration exceeds a threshold, thereby avoiding the modal frequencies of the robot at its current pose. Concurrently, it calculates and adjusts the welding speed of the robot according to the thermal equilibrium equation to maintain constant heat input. A simplified dynamic model of the RFSW robot was established, and the feasibility of this method was validated through simulation experiments. This study fills the gap in vibration analysis of RFSW and provides new insights into control strategies and process optimization for robotic friction stir welding.

Prediction of Human Reaching Pose Sequences in Human–Robot Collaboration

Abstract In human–robot collaboration, robots and humans must work together in shared, overlapping, workspaces to accomplish tasks. If human and robot motion can be coordinated, then collisions between robot and human can seamlessly be avoided without requiring either of them to stop work. A key part of this coordination is anticipating humans’ future motion so robot motion can be adapted proactively. In this work, a generative neural network predicts a multi-step sequence of human poses for tabletop reaching motions. The multi-step sequence is mapped to a time-series based on a human speed versus motion distance model. The input to the network is the human’s reaching target relative to current pelvis location combined with current human pose. A dataset was generated of human motions to reach various positions on or above the table in front of the human starting from a wide variety of initial human poses. After training the network, experiments showed that the predicted sequences generated by this method matched the actual recordings of human motion within an L2 joint error of 7.6 cm and L2 link roll–pitch–yaw error of 0.301 rad on average. This method predicts motion for an entire reach motion without suffering from the exponential propagation of prediction error that limits the horizon of prior works.

Cross-Modal Supervised Human Body Pose Recognition Techniques for Through-Wall Radar.

Through-wall radar human body pose recognition technology has broad applications in both military and civilian sectors. Identifying the current pose of targets behind walls and predicting subsequent pose changes are significant challenges. Conventional methods typically utilize radar information along with machine learning algorithms such as SVM and random forests to aid in recognition. However, these approaches have limitations, particularly in complex scenarios. In response to this challenge, this paper proposes a cross-modal supervised through-wall radar human body pose recognition method. By integrating information from both cameras and radar, a cross-modal dataset was constructed, and a corresponding deep learning network architecture was designed. During training, the network effectively learned the pose features of targets obscured by walls, enabling accurate pose recognition (e.g., standing, crouching) in scenarios with unknown wall obstructions. The experimental results demonstrated the superiority of the proposed method over traditional approaches, offering an effective and innovative solution for practical through-wall radar applications. The contribution of this study lies in the integration of deep learning with cross-modal supervision, providing new perspectives for enhancing the robustness and accuracy of target pose recognition.

Cross-Constrained Progressive Inference for 3D Hand Pose Estimation with Dynamic Observer-Decision-Adjuster Networks

Generalization is very important for pose estimation, especially for 3D pose estimation where small changes in the 2D images could trigger structural changes in the 3D space. To achieve generalization, the system needs to have the capability of detecting estimation errors by double-checking the projection coherence between the 3D and 2D spaces and adapting its network inference process based on this feedback. Current pose estimation is one-time feed-forward and lacks the capability to gather feedback and adapt the inference outcome. To address this problem, we propose to explore the concept of progressive inference where the network learns an observer to continuously detect the prediction error based on constraints matching, as well as an adjuster to refine its inference outcome based on these constraints errors. Within the context of 3D hand pose estimation, we find that this observer-adjuster design is relatively unstable since the observer is operating in the 2D image domain while the adjuster is operating in the 3D domain. To address this issue, we propose to construct two sets of observers-adjusters with complementary constraints from different perspectives. They operate in a dynamic sequential manner controlled by a decision network to progressively improve the 3D pose estimation. We refer to this method as Cross-Constrained Progressive Inference (CCPI). Our extensive experimental results on FreiHAND and HO-3D benchmark datasets demonstrate that the proposed CCPI method is able to significantly improve the generalization capability and performance of 3D hand pose estimation.

Automatic assembly of prefabricated components based on vision-guided robot

On-site assembly of prefabricated components is crucial for the construction efficiency and quality of prefabricated buildings. In this process, a prefabricated component is first lifted and transported to the vicinity, where it will be installed using a crane. Subsequently, multiple workers collaborate to align the components with the target installation area. However, this manual installation method is time-consuming and unreliable in accuracy. A vision-based robot-assisted component installation system is proposed in this study. After the initial alignment using a crane, the two robots cooperate to adjust the position and orientation of the component accurately. This automated assembly method consists of the following tasks: (1) The target installation pose of the component, which can be used as a guide for the movements of robots, is extracted from the building information model (BIM) based on the industry foundation class standard. (2) An optical-marker-based method is applied to position the robots in the coordinate system of the site and identify the pose of the reserved hole in the lifting prefabricated component. Based on this pose, the robot is manipulated to thread the end effector into the reserved hole. (3) A planned working path of the end effector in Cartesian space combined with the current pose of the end effector and the target installation pose is obtained. (4) The end effector moves along a predetermined path to drive the component precisely. Finally, the accuracy, feasibility, and effectiveness of the robotic automated construction method are verified through installation tests on a precast panel.

A Dexterous Hand-Arm Teleoperation System Based on Hand Pose Estimation and Active Vision.

Markerless vision-based teleoperation that leverages innovations in computer vision offers the advantages of allowing natural and noninvasive finger motions for multifingered robot hands. However, current pose estimation methods still face inaccuracy issues due to the self-occlusion of the fingers. Herein, we develop a novel vision-based hand-arm teleoperation system that captures the human hands from the best viewpoint and at a suitable distance. This teleoperation system consists of an end-to-end hand pose regression network and a controlled active vision system. The end-to-end pose regression network (Transteleop), combined with an auxiliary reconstruction loss function, captures the human hand through a low-cost depth camera and predicts joint commands of the robot based on the image-to-image translation method. To obtain the optimal observation of the human hand, an active vision system is implemented by a robot arm at the local site that ensures the high accuracy of the proposed neural network. Human arm motions are simultaneously mapped to the slave robot arm under relative control. Quantitative network evaluation and a variety of complex manipulation tasks, for example, tower building, pouring, and multitable cup stacking, demonstrate the practicality and stability of the proposed teleoperation system.

A Method for Unseen Object Six Degrees of Freedom Pose Estimation Based on Segment Anything Model and Hybrid Distance Optimization

Six degrees of freedom pose estimation technology constitutes the cornerstone for precise robotic control and similar tasks. Addressing the limitations of current 6-DoF pose estimation methods in handling object occlusions and unknown objects, we have developed a novel two-stage 6-DoF pose estimation method that integrates RGB-D data with CAD models. Initially, targeting high-quality zero-shot object instance segmentation tasks, we innovated the CAE-SAM model based on the SAM framework. In addressing the SAM model’s boundary blur, mask voids, and over-segmentation issues, this paper introduces innovative strategies such as local spatial-feature-enhancement modules, global context markers, and a bounding box generator. Subsequently, we proposed a registration method optimized through a hybrid distance metric to diminish the dependency of point cloud registration algorithms on sensitive hyperparameters. Experimental results on the HQSeg-44K dataset substantiate the notable improvements in instance segmentation accuracy and robustness rendered by the CAE-SAM model. Moreover, the efficacy of this two-stage method is further corroborated using a 6-DoF pose dataset of workpieces constructed with CloudCompare and RealSense. For unseen targets, the ADD metric achieved 2.973 mm, and the ADD-S metric reached 1.472 mm. This paper significantly enhances pose estimation performance and streamlines the algorithm’s deployment and maintenance procedures.

CONet: Crowd and occlusion-aware network for occluded human pose estimation

Human pose estimation has numerous applications in motion recognition, virtual reality, human–computer interaction, and other related fields. However, multi-person pose estimation in crowded and occluded scenes is challenging. One major issue about the current top-down human pose estimation approaches is that they are limited to predicting the pose of a single person, even when the bounding box contains multiple individuals. To address this problem, we propose a novel Crowd and Occlusion-aware Network (CONet) using a divide-and-conquer strategy. Our approach includes a Crowd and Occlusion-aware Head (COHead) which estimates the pose of both the occluder and the occluded person using two separate branches. We also use the attention mechanism to guide the branches for differentiated learning, aiming to improve feature representation. Additionally, we propose a novel interference point loss to enhance the model’s anti-interference ability. Our CONet is simple yet effective, and it outperforms the state-of-the-art model by +1.6 AP, achieving 71.6 AP on CrowdPose. Our proposed model has achieved state-of-the-art results on the CrowdPose dataset, demonstrating its effectiveness in improving the accuracy of human pose estimation in crowded and occluded scenes. This achievement highlights the potential of our model in many real-world applications where accurate human pose estimation is crucial, such as surveillance, sports analysis, and human–computer interaction.