This paper presents a CNN-based network architecture aimed to classify and detect joint types within Articulated objects, specifically the Push-P joints, P-joints, R-joints and objects lacking joints. The movement mod...
This paper presents a CNN-based network architecture aimed to classify and detect joint types within Articulated objects, specifically the Push-P joints, P-joints, R-joints and objects lacking joints. The movement modeling of the detected objects is explored by processing pre and post interaction RGB images within the SAPIEN PartNet-Mobility dataset. In order to achieve this, an architecture is proposed to leverage consecutive CNN encoders based on the VGG architecture, in order to classify joints based on pre and post-interaction images. Additionally, in order to detect the effect-point and movement vector, a convolutional encoder is applied for each joint type. Moreover, extensive evaluation is made to showcase the results, achieving 96% accuracy in joint classification and 94% accuracy in regression on the considered dataset. Elaborate details regarding network architectures, training procedures, and testing methodologies are available at source code repository.
Each lexical expression in a language has its own history: elements of a language are the result of several linguistic processes and may descend from expressions of other languages. In this paper, we propose an ontolo...
详细信息
Exergaming, blending exercise and gaming, improves the physical and mental health of older adults. We currently do not fully know the factors that drive older adults to either engage in or abstain from exergaming. Lar...
详细信息
This paper introduces a pioneering experimental study on the automated packing of a catering package using a two-fingered gripper affixed to a 3-degree-of-freedom Delta parallel robot. A distinctive contribution lies ...
详细信息
ISBN:
(数字)9798350376340
ISBN:
(纸本)9798350376357
This paper introduces a pioneering experimental study on the automated packing of a catering package using a two-fingered gripper affixed to a 3-degree-of-freedom Delta parallel robot. A distinctive contribution lies in the application of a deep learning approach to tackle this challenge. A custom dataset, comprising 1,500 images, is meticulously curated for this endeavor, representing a noteworthy initiative as the first dataset focusing on Persian-manufactured products. The study employs the YOLOV5 model for object detection, followed by segmentation using the FastSAM model. Subsequently, rotation angle calculation is facilitated with segmentation masks, and a rotated rectangle encapsulating the object is generated. This rectangle forms the basis for calculating two grasp points using a novel geometrical approach involving eigenvectors. An extensive experimental study validates the proposed model, where all pertinent information is seamlessly transmitted to the 3-DOF Delta parallel robot. The proposed algorithm ensures real-time detection, calibration, and the fully autonomous packing process of a catering package, boasting an impressive over 80% success rate in automatic grasping. This study marks a significant stride in advancing the capabilities of robotic systems for practical applications in packaging automation.
Personalized learning is hard to apply in classroom practice due to the workload of teachers. Recommender systems can help teachers make choices and hence personalize the learning environment. However, few studies hav...
详细信息
People are increasingly eager to know more about themselves through technology. To date, technology has primarily provided information on our physiology. Yet, with advances in wearable technology and artificial intell...
详细信息
Currently, the shortage of personnel and the increasing proportions of older individuals in need of care pose enormous challenges to care facilities. Some of the resulting hospitalizations in nursing home are not medi...
详细信息
Person image synthesis with controllable body poses and appearances is an essential task owing to the practical needs in the context of virtual try-on, image editing and video production. However, existing methods fac...
详细信息
As technology permeates people's everyday lives, opportunities arise for HCI to design, develop and research technologies that focus on broader societal challenges such as sustainability, race, gender, and power. ...
详细信息
Recent research in robotic proxies has demonstrated that one can automatically reproduce many non-verbal cues important in co-located collaboration. However, they often require a symmetrical hardware setup in each loc...
ISBN:
(纸本)9798400701320
Recent research in robotic proxies has demonstrated that one can automatically reproduce many non-verbal cues important in co-located collaboration. However, they often require a symmetrical hardware setup in each location. We present the VRoxy system, designed to enable access to remote spaces through a robotic embodiment, using a VR headset in a much smaller space, such as a personal office. VRoxy maps small movements in VR space to larger movements in the physical space of the robot, allowing the user to navigate large physical spaces easily. Using VRoxy, the VR user can quickly explore and navigate in a low-fidelity rendering of the remote space. Upon the robot’s arrival, the system uses the feed of a 360 camera to support real-time interactions. The system also facilitates various interaction modalities by rendering the micro-mobility around shared spaces, head and facial animations, and pointing gestures on the proxy. We demonstrate how our system can accommodate mapping multiple physical locations onto a unified virtual space. In a formative study, users could complete a design decision task where they navigated and collaborated in a complex 7.5m x 5m layout using a 3m x 2m VR space.
暂无评论