Three-dimensional Pose Research Articles

Development of a Gait Analysis Application for Assessing Upper and Lower Limb Movements to Detect Pathological Gait.

Pathological gait in patients with Hakim's disease (HD, synonymous with idiopathic normal-pressure hydrocephalus; iNPH), Parkinson's disease (PD), and cervical myelopathy (CM) has been subjectively evaluated in this study. We quantified the characteristics of upper and lower limb movements in patients with pathological gait. We analyzed 1491 measurements of 1 m diameter circular walking from 122, 12, and 93 patients with HD, PD, and CM, respectively, and 200 healthy volunteers using the Three-Dimensional Pose Tracker for Gait Test. Upper and lower limb movements of 2D coordinates projected onto body axis sections were derived from estimated 3D relative coordinates. The hip and knee joint angle ranges on the sagittal plane were significantly smaller in the following order: healthy > CM > PD > HD, whereas the shoulder and elbow joint angle ranges were significantly smaller, as follows: healthy > CM > HD > PD. The outward shift of the leg on the axial plane was significantly greater, as follows: healthy < CM < PD < HD, whereas the outward shift of the upper limb followed the order of healthy > CM > HD > PD. The strongest correlation between the upper and lower limb movements was identified in the angle ranges of the hip and elbow joints on the sagittal plane. The lower and upper limb movements during circular walking were correlated. Patients with HD and PD exhibited reduced back-and-forth swings of the upper and lower limbs.

Visual guidance technology of flying cars based on multilevel markers and depth

Split-type flying car will play an important role in the future transportation. This paper adopts a guidance method that couples visual information and depth information, and improves the docking accuracy through the mutual cooperation of the drone and the vehicle. Firstly, a multilevel docking marker is designed to achieve adaptive target matching within different distances during the docking process. The marker has strong robustness and can adapt to complex scenes such as occlusion, strong light, and large angle tilting, providing the redundant corner points required for machine vision detection pose information accurately. Secondly, a three-dimensional pose estimation algorithm is proposed, which can introduce depth information to correct the homography matrix. The algorithm combines the advantages of strong robustness to multilevel marker detection and high accuracy of depth information, and can output millimeter-level precision pose information in different environments, different inclination angles, and different occlusions. Finally, a flying car model experiment was carried out, and the results showed that the guidance technology can obtain millimeter-level precise pose information during the entire process of long distance-near distance-completion of docking, thus realizing precise docking.

Monocular Pose Estimation Method for Automatic Citrus Harvesting Using Semantic Segmentation and Rotating Target Detection.

The lack of spatial pose information and the low positioning accuracy of the picking target are the key factors affecting the picking function of citrus-picking robots. In this paper, a new method for automatic citrus fruit harvest is proposed, which uses semantic segmentation and rotating target detection to estimate the pose of a single culture. First, Faster R-CNN is used for grab detection to identify candidate grab frames. At the same time, the semantic segmentation network extracts the contour information of the citrus fruit to be harvested. Then, the capture frame with the highest confidence is selected for each target fruit using the semantic segmentation results, and the rough angle is estimated. The network uses image-processing technology and a camera-imaging model to further segment the mask image of the fruit and its epiphyllous branches and realize the fitting of contour, fruit centroid, and fruit minimum outer rectangular frame and three-dimensional boundary frame. The positional relationship of the citrus fruit to its epiphytic branches was used to estimate the three-dimensional pose of the citrus fruit. The effectiveness of the method was verified through citrus-planting experiments, and then field picking experiments were carried out in the natural environment of orchards. The results showed that the success rate of citrus fruit recognition and positioning was 93.6%, the average attitude estimation angle error was 7.9°, and the success rate of picking was 85.1%. The average picking time is 5.6 s, indicating that the robot can effectively perform intelligent picking operations.

Deciphering social traits and pathophysiological conditions from natural behaviors in common marmosets

Nonhuman primates (NHPs) are indispensable animal models by virtue of the continuity of behavioral repertoires across primates, including humans. However, behavioral assessment at the laboratory level has so far been limited. Employing the application of three-dimensional (3D) pose estimation and the optimal integration of subsequent analytic methodologies, we demonstrate that our artificial intelligence (AI)-based approach has successfully deciphered the ethological, cognitive, and pathological traits of common marmosets from their natural behaviors. By applying multiple deep neural networks trained with large-scale datasets, we established an evaluation system that could reconstruct and estimate the 3D poses of the marmosets, a small NHP that is suitable for analyzing complex natural behaviors in laboratory setups. We further developed downstream analytic methodologies to quantify a variety of behavioral parameters beyond motion kinematics. We revealed the distinct parental roles of male and female marmosets through automated detections of food-sharing behaviors using a spatial-temporal filter on 3D poses. Employing a recurrent neural network to analyze 3D pose time series data during social interactions, we additionally discovered that marmosets adjusted their behaviors based on others' internal state, which is not directly observable but can be inferred from the sequence of others' actions. Moreover, a fully unsupervised approach enabled us to detect progressively appearing symptomatic behaviors over a year in a Parkinson's disease model. The high-throughput and versatile nature of an AI-driven approach to analyze natural behaviors will open a new avenuefor neuroscience research dealing with big-data analyses of social and pathophysiological behaviors in NHPs.

Human Joint Angle Estimation Using Deep Learning-Based Three-Dimensional Human Pose Estimation for Application in a Real Environment.

Human pose estimation (HPE) is a technique used in computer vision and artificial intelligence to detect and track human body parts and poses using images or videos. Widely used in augmented reality, animation, fitness applications, and surveillance, HPE methods that employ monocular cameras are highly versatile and applicable to standard videos and CCTV footage. These methods have evolved from two-dimensional (2D) to three-dimensional (3D) pose estimation. However, in real-world environments, current 3D HPE methods trained on laboratory-based motion capture data encounter challenges, such as limited training data, depth ambiguity, left/right switching, and issues with occlusions. In this study, four 3D HPE methods were compared based on their strengths and weaknesses using real-world videos. Joint position correction techniques were proposed to eliminate and correct anomalies such as left/right inversion and false detections of joint positions in daily life motions. Joint angle trajectories were obtained for intuitive and informative human activity recognition using an optimization method based on a 3D humanoid simulator, with the joint position corrected by the proposed technique as the input. The efficacy of the proposed method was verified by applying it to three types of freehand gymnastic exercises and comparing the joint angle trajectories during motion.

Natural scenes reveal diverse representations of 2D and 3D body pose in the human brain

Human pose, defined as the spatial relationships between body parts, carries instrumental information supporting the understanding of motion and action of a person. A substantial body of previous work has identified cortical areas responsive to images of bodies and different body parts. However, the neural basis underlying the visual perception of body part relationships has received less attention. To broaden our understanding of body perception, we analyzed high-resolution fMRI responses to a wide range of poses from over 4,000 complex natural scenes. Using ground-truth annotations and an application of three-dimensional (3D) pose reconstruction algorithms, we compared similarity patterns of cortical activity with similarity patterns built from human pose models with different levels of depth availability and viewpoint dependency. Targeting the challenge of explaining variance in complex natural image responses with interpretable models, we achieved statistically significant correlations between pose models and cortical activity patterns (though performance levels are substantially lower than the noise ceiling). We found that the 3D view-independent pose model, compared with two-dimensional models, better captures the activation from distinct cortical areas, including the right posterior superior temporal sulcus (pSTS). These areas, together with other pose-selective regions in the LOTC, form a broader, distributed cortical network with greater view-tolerance in more anterior patches. We interpret these findings in light of the computational complexity of natural body images, the wide range of visual tasks supported by pose structures, and possible shared principles for view-invariant processing between articulated objects and ordinary, rigid objects.

Automatic planning of maxillary anterior dental implant based on prosthetically guided and pose evaluation indicator.

Preoperative planning of maxillary anterior dental implant is a prerequisite to ensuring that the implant achieves the proper three-dimensional (3D) pose, which is essential for its long-term stability. However, the current planning process is labor-intensive and subjective, relying heavily on the surgeon's experience. Consequently, this paper proposes an automatic method for computing the optimal pose of the dental implant. The method adopts the principle of prosthetically guided dental implant placement. Initially, the prosthesis coordinate system is established to determine the implant candidate orientations. Subsequently, virtual slices of the maxilla in the buccal-palatal direction are generated according to the prosthesis position. By extracting feature points from the virtual slices, the implant candidate starting points are acquired. Then, a candidate pose set is obtained by combining these candidate starting points and orientations. Finally, a pose evaluation indicator is introduced to determine the optimal implant pose from this set. Twenty-two cases were utilized to validate the method. The results show that the method could determine an ideal pose for the dental implant, with the average minimum distance between the implant and the left tooth root, the right tooth root, the palatal side, and the buccal side being mm, mm, mm, mm, respectively. The planning time was less than 9s. Unlike manual planning, the proposed method can efficiently and accurately complete maxillary anterior dental implant planning, providing a theoretical analysis of the success rate of the implant. Thus, it has great potential for future clinical application.

A visual servo reinforcement learning control of uncalibrated manipulators with multi-channel gain decision

A technology based on Kalman filtering method combined with multi-channel gain training reinforcement learning for uncalibrated camera visual servo tasks is proposed in this paper. First, a dynamic system with state variables formed from the elements of the image Jacobian matrix is constructed to describe the mapping relationship between two-dimensional images and three-dimensional poses. Kalman filter is used to estimate the state variables of the constructed system online. Next, the Jacobian matrix estimation and depth determination strategy gradient (DDPG) methods are combined to jointly train multi-channel gains by setting a reasonable segmented reward and punishment mechanism. Through training, a more effective gain decision can be obtained. The robustness of Kalman filtering to interference to a certain extent reduces the precise dependence of reinforcement learning models, thereby achieving higher robustness in intelligent visual servo control. Finally, the effectiveness and advantages of the Kalman-DDPG method have been demonstrated through simulation comparison and six-degree-of-freedom (DOF) uncalibrated manipulator physical experiments.

Homography-Based Visual Servoing of Eye-in-Hand Robots With Exact Depth Estimation

Visual servoing can effectively control robots using visual feedback to improve their intelligence and reliability. For a feature point detected by a monocular camera, the time-varying depth appearing nonlinearly in the Jacobian matrix is difficult to be measured without the prior geometry knowledge of the observed object. Hence, the depth of the feature point is one of the major uncertain parameters in visual servoing. Considering unknown Cartesian feature positions, this study presents a dynamics-based homography-based visual servoing (HBVS) controller for the three-dimensional (3-D) pose regulation of eye-in-hand robot arms with monocular cameras. The uncertain depth is represented as a linear form of its Cartesian feature position, and a composite learning law is applied to estimate position parameters accurately, resulting in exact depth estimation. Compared to existing adaptive HBVS methods, the distinctive feature of the proposed method is that it is a dynamics-based design and guarantees exact depth estimation under a much weaker condition termed interval excitation than persistent excitation. Simulations and experiments on a collaborative robot with 7 degrees of freedom named Franka Emika Panda have verified the effectiveness of the proposed method.

A-SOiD, an active-learning platform for expert-guided, data-efficient discovery of behavior.

To identify and extract naturalistic behavior, two methods have become popular: supervised and unsupervised. Each approach carries its own strengths and weaknesses (for example, user bias, training cost, complexity and action discovery), which the user must consider in their decision. Here, an active-learning platform, A-SOiD, blends these strengths, and in doing so, overcomes several of their inherent drawbacks. A-SOiD iteratively learns user-defined groups with a fraction of the usual training data, while attaining expansive classification through directed unsupervised classification. In socially interacting mice, A-SOiD outperformed standard methods despite requiring 85% less training data. Additionally, it isolated ethologically distinct mouse interactions via unsupervised classification. We observed similar performance and efficiency using nonhuman primate and human three-dimensional pose data. In both cases, the transparency in A-SOiD's cluster definitions revealed the defining features of the supervised classification through a game-theoretic approach. To facilitate use, A-SOiD comes as an intuitive, open-source interface for efficient segmentation of user-defined behaviors and discovered sub-actions.

DCSPose: A Dual-Channel Siamese Framework for Unseen Textureless Object Pose Estimation

The demand for object pose estimation is steadily increasing, and deep learning has propelled the advancement of this field. However, the majority of research endeavors face challenges in their applicability to industrial production. This is primarily due to the high cost of annotating 3D data, which places higher demands on the generalization capabilities of neural network models. Additionally, existing methods struggle to handle the abundance of textureless objects commonly found in industrial settings. Finally, there is a strong demand for real-time processing capabilities in industrial production processes. Therefore, in this study, we introduced a dual-channel Siamese framework to address these challenges in industrial applications. The architecture employs a Siamese structure for template matching, enabling it to learn the matching capability between the templates constructed from high-fidelity simulated data and real-world scenes. This capacity satisfies the requirements for generalization to unseen objects. Building upon this, we utilized two feature extraction channels to separately process RGB and depth information, addressing the limited feature issue associated with textureless objects. Through our experiments, we demonstrated that this architecture effectively estimates the three-dimensional pose of objects, achieving a 6.0% to 10.9% improvement compared to the state-of-the-art methods, while exhibiting robust generalization and real-time processing capabilities.

Lightweight Three-Dimensional Pose and Joint Center Estimation Model for Rehabilitation Therapy

In this study, we proposed a novel transformer-based model with independent tokens for estimating three-dimensional (3D) human pose and shape from monocular videos, specifically focusing on its application in rehabilitation therapy. The main objective is to recover pixel-aligned rehabilitation-customized 3D human poses and body shapes directly from monocular images or videos, which is a challenging task owing to inherent ambiguity. Existing human pose estimation methods heavily rely on the initialized mean pose and shape as prior estimates and employ parameter regression with iterative error feedback. However, video-based approaches face difficulties capturing joint-level rotational motion and ensuring local temporal consistency despite enhancing single-frame features by modeling the overall changes in the image-level features. To address these limitations, we introduce two types of characterization tokens specifically designed for rehabilitation therapy: joint rotation and camera tokens. These tokens progressively interact with the image features through the transformer layers and encode prior knowledge of human 3D joint rotations (i.e., position information derived from large-scale data). By updating these tokens, we can estimate the SMPL parameters for a given image. Furthermore, we incorporate a temporal model that effectively captures the rotational temporal information of each joint, thereby reducing jitters in local parts. The performance of our method is comparable with those of the current best-performing models. In addition, we present the structural differences among the models to create a pose classification model for rehabilitation. We leveraged ResNet-50 and transformer architectures to achieve a remarkable PA-MPJPE of 49.0 mm for the 3DPW dataset.

Fall-portent detection for construction sites based on computer vision and machine learning

PurposeFall accidents can cause casualties and economic losses in the construction industry. Fall portents, such as loss of balance (LOB) and sudden sways, can result in fatal, nonfatal or attempted fall accidents. All of them are worthy of studying to take measures to prevent future accidents. Detecting fall portents can proactively and comprehensively help managers assess the risk to workers as well as in the construction environment and further prevent fall accidents.Design/methodology/approachThis study focused on the postures of workers and aimed to directly detect fall portents using a computer vision (CV)-based noncontact approach. Firstly, a joint coordinate matrix generated from a three-dimensional pose estimation model is employed, and then the matrix is preprocessed by principal component analysis, K-means and pre-experiments. Finally, a modified fusion K-nearest neighbor-based machine learning model is built to fuse information from the x, y and z axes and output the worker's pose status into three stages.FindingsThe proposed model can output the worker's pose status into three stages (steady–unsteady–fallen) and provide corresponding confidence probabilities for each category. Experiments conducted to evaluate the approach show that the model accuracy reaches 85.02% with threshold-based postprocessing. The proposed fall-portent detection approach can extract the fall risk of workers in the both pre- and post-event phases based on noncontact approach.Research limitations/implicationsFirst, three-dimensional (3D) pose estimation needs sufficient information, which means it may not perform well when applied in complicated environments or when the shooting distance is extremely large. Second, solely focusing on fall-related factors may not be comprehensive enough. Future studies can incorporate the results of this research as an indicator into the risk assessment system to achieve a more comprehensive and accurate evaluation of worker and site risk.Practical implicationsThe proposed machine learning model determines whether the worker is in a status of steady, unsteady or fallen using a CV-based approach. From the perspective of construction management, when detecting fall-related actions on construction sites, the noncontact approach based on CV has irreplaceable advantages of no interruption to workers and low cost. It can make use of the surveillance cameras on construction sites to recognize both preceding events and happened accidents. The detection of fall portents can help worker risk assessment and safety management.Originality/valueExisting studies using sensor-based approaches are high-cost and invasive for construction workers, and others using CV-based approaches either oversimplify by binary classification of the non-entire fall process or indirectly achieve fall-portent detection. Instead, this study aims to detect fall portents directly by worker's posture and divide the entire fall process into three stages using a CV-based noncontact approach. It can help managers carry out more comprehensive risk assessment and develop preventive measures.

Human–robot collaborative interaction with human perception and action recognition

This paper presents a human–robot interaction system (HRIS) that utilizes human perception and action recognition to enable the robot to understand human intentions and flexibly interact with humans. A monocular multi-person three-dimensional (3D) pose estimation method is first proposed to perceive multi-person two-dimensional (2D) and 3D poses in interaction scenarios. Furthermore, a 3D skeleton poses tracking approach is adopted to locate the identity of each person in consecutive frames and enhance interactive stability. Then, an action recognition model is developed, which exploits tracked pose features to recognize the intentions of humans. An action-controlled interaction system is built with a modular approach to ensure flexibility in meeting multiple task requirements and facilitating flexible interaction. In the system, a distance-based safety solution is designed to avoid collisions between humans and robots. Finally, experimental results are presented to demonstrate the feasibility and effectiveness of the proposed methods and system.

PrimitivePose: Generic Model and Representation for 3D Bounding Box Prediction of Unseen Objects

A considerable amount of research is concerned with the challenging task of estimating three-dimensional (3D) pose and size for multi-object indoor scene configurations. Many existing models rely on a priori known object models, such as 3D CAD models and are therefore limited to a predefined set of object categories. This closed-set constraint limits the range of applications for robots interacting in dynamic environments where previously unseen objects may appear. This paper addresses this problem with a highly generic 3D bounding box detection method that relies entirely on geometric cues obtained from depth data percepts. While the generation of synthetic data, e.g. synthetic depth maps, is commonly used for this task, the well-known synth-to-real gap often emerges, which prohibits transition of models trained solely on synthetic data to the real world. To ameliorate this problem, we use stereo depth computation on synthetic data to obtain pseudo-realistic disparity maps. We then propose an intermediate representation, namely disparity-scaled surface normal (SN) images, which encodes geometry and at the same time preserves depth/scale information unlike the commonly used standard SNs. In a series of experiments, we demonstrate the usefulness of our approach, detecting everyday objects on a captured data set of tabletop scenes, and compare it to the popular PoseCNN model. We quantitatively show that standard SNs are less adequate for challenging 3D detection tasks by comparing predictions from the model trained on disparity alone, SNs and disparity-scaled SNs. Additionally, in an ablation study we investigate the minimal number of training samples required for such a learning task. Lastly, we make the tool used for 3D object annotation publicly available at: https://preview.tinyurl.com/3ycn8v5k . A video showcasing our results can be found at: https://preview.tinyurl.com/dzdzabek .

MInet: A Novel Network Model for Point Cloud Processing by Integrating Multi-Modal Information.

Three-dimensional LiDAR systems that capture point cloud data enable the simultaneous acquisition of spatial geometry and multi-wavelength intensity information, thereby paving the way for three-dimensional point cloud recognition and processing. However, due to the irregular distribution, low resolution of point clouds, and limited spatial recognition accuracy in complex environments, inherent errors occur in classifying and segmenting the acquired target information. Conversely, two-dimensional visible light images provide real-color information, enabling the distinction of object contours and fine details, thus yielding clear, high-resolution images when desired. The integration of two-dimensional information with point clouds offers complementary advantages. In this paper, we present the incorporation of two-dimensional information to form a multi-modal representation. From this, we extract local features to establish three-dimensional geometric relationships and two-dimensional color relationships. We introduce a novel network model, termed MInet (Multi-Information net), which effectively captures features relating to both two-dimensional color and three-dimensional pose information. This enhanced network model improves feature saliency, thereby facilitating superior segmentation and recognition tasks. We evaluate our MInet architecture using the ShapeNet and ThreeDMatch datasets for point cloud segmentation, and the Stanford dataset for object recognition. The robust results, coupled with quantitative and qualitative experiments, demonstrate the superior performance of our proposed method in point cloud segmentation and object recognition tasks.

Three-Dimensional Human Pose Estimation from Sparse IMUs through Temporal Encoder and Regression Decoder

Three-dimensional (3D) pose estimation has been widely used in many three-dimensional human motion analysis applications, where inertia-based path estimation is gradually being adopted. Systems based on commercial inertial measurement units (IMUs) usually rely on dense and complex wearable sensors and time-consuming calibration, causing intrusions to the subject and hindering free body movement. The sparse IMUs-based method has drawn research attention recently. Existing sparse IMUs-based three-dimensional pose estimation methods use neural networks to obtain human poses from temporal feature information. However, these methods still suffer from issues, such as body shaking, body tilt, and movement ambiguity. This paper presents an approach to improve three-dimensional human pose estimation by fusing temporal and spatial features. Based on a multistage encoder-decoder network, a temporal convolutional encoder and human kinematics regression decoder were designed. The final three-dimensional pose was predicted from the temporal feature information and human kinematic feature information. Extensive experiments were conducted on two benchmark datasets for three-dimensional human pose estimation. Compared to state-of-the-art methods, the mean per joint position error was decreased by 13.6% and 19.4% on the total capture and DIP-IMU datasets, respectively. The quantitative comparison demonstrates that the proposed temporal information and human kinematic topology can improve pose accuracy.

A Method for 3D Human Pose Estimation and Similarity Calculation in Tai Chi Videos

Human pose estimation from video sequences has become a hot research topic in the domain of robotics and computer vision. However, existing three-dimensional (3D) pose estimation methods usually analyze individual frames, which have a low accuracy due to various human movement speed, limiting its practical application. In this paper, we propose a method for estimating 3D pose and calculating similarity from Tai Chi video sequences based on Seq2Seq network. Specifically, using 2D joint point coordinate sequence of the original image as input, our method constructs an encoder and a decoder to build a Seq2Seq network. Our method introduces an attention mechanism for weighing the input data to obtain an intermediate vector and decode it to estimate the 3D joint point sequence. Afterwards, using a template video and a target video as input, our method calculates the cost of passing through each point within the constraints to construct a cost matrix for video similarity. With the cost matrix, our method can determine the optimal path and use the correspondence of the video sequence to calculate the image similarity of the corresponding frame. The experimental data show that the proposed method can effectively improve the accuracy of 3D pose estimation, and increase the speed for video similarity calculation.

Recognition and Prediction of Pedestrian Hazardous Crossing Intentions in Visual Field Obstruction Areas Based on IPVO-LSTM

Pedestrians who suddenly cross the street from within the blind spot of a vehicle’s field of view can pose a significant threat to traffic safety. The dangerous pedestrian crossing intentions in view-obscured scenarios have not received as much attention as the prediction of pedestrian crossing intentions. In this paper, we present a method for recognizing and predicting the dangerous crossing intention of pedestrians in a view-obscured region based on the interference, pose, velocity observation–long short-term memory (IPVO-LSTM) algorithm from a road-based view. In the first step, the road-based camera captures the pedestrian’s image. Then, we construct a pedestrian interference state feature module, pedestrian three-dimensional pose feature module, pedestrian velocity feature module, and pedestrian blind observation state feature module and extract the corresponding features of the studied pedestrians. Finally, the pedestrian hazard crossing intention prediction module based on a feature-fused LSTM (ff-LSTM) and attention mechanism is used to fuse and process the above features in a cell state process to recognize and predict the pedestrian hazard crossing intention in the blind visual area. Experiments are compared with current common algorithms in terms of the input parameter selection, intention recognition algorithm, and intention prediction time range, and the experimental results validate our state-of-the-art method.

PYNet: Poseclass and Yaw Angle Output Network for Object Pose Estimation

The issues of estimating the poses of simple-shaped objects, such as retail store goods, have been addresses to ease the grasping of objects by robots. Conventional methods to estimate poses with an RGBD camera mounted on robots have difficulty estimating the three-dimensional poses of simple-shaped objects with few shape features. Therefore, in this study, we propose a new class called “poseclass” to indicate the grounding face of an object. The poseclass is of discrete value and solvable as a classification problem; it can be estimated with high accuracy; in addition, the three-dimensional pose estimation problems can be simplified into one-dimensional pose-estimation problem to estimate the yaw angles on the grounding face. We have developed a new neural network (PYNet) to estimate the poseclass and yaw angle, and compared it with conventional methods to determine its ratio of estimating unknown simple-shaped object poses with an angle error of 30° or less. The ratio of PYNet (68.9%) is an 18.1 pt higher than that of the conventional methods (50.8%). Additionally, a PYNet-implemented robot successfully grasped convenience store goods.