Anzahl der Treffer: 493
Erstellt: Sat, 13 Jul 2024 23:12:40 +0200 in 0.0705 sec

Wengefeld, Tim; Seichter, Daniel; Lewandowski, Benjamin; Groß, Horst-Michael
Enhancing person perception for mobile robotics by real-time RGB-D person attribute estimation. - In: 2024 IEEE/SICE International Symposium on System Integration (SII), (2024), S. 914-921

Person attribute estimation is a task of great importance for a variety of real-world robotic applications. While the computer vision community has made impressive progress over the last decade, they often rely on the sole use of RGB images from surveillance datasets and large deep- learning models without considering real-time requirements. By contrast, mobile robotic platforms have to deal with restricted resources but are often equipped with RGB-D cameras, offering complementary modalities. This paper presents an approach to robustly estimate soft-biometric attributes from full-body RGB-D appearances of persons in the surroundings of a mobile robot. The effects of depth, RGB and RGB-D data as input are analyzed, taking into account runtime and resource requirements. On the robotic attribute dataset SRL, it is shown that the presented approach outperforms other state-of-the-art approaches by a large margin. Furthermore, real-time requirements are met when applied on an NVIDIA Jetson AGX Xavier or even on a mobile CPU only. Finally, a previous system for person detection, upper body orientation estimation, and posture classification is integrated to enable an even more comprehensive perception of persons in the surroundings of a mobile robot in one joint approach. The source code for training and application will be made publicly available on GitHub.
Döring, Nicola; Mikhailova, Veronika; Brandenburg, Karlheinz; Broll, Wolfgang; Groß, Horst-Michael; Werner, Stephan; Raake, Alexander
Digital media in intergenerational communication: status quo and future scenarios for the grandparent-grandchild relationship. - In: Universal access in the information society, ISSN 1615-5297, Bd. 23 (2024), 1, S. 379-394

Communication technologies play an important role in maintaining the grandparent-grandchild (GP-GC) relationship. Based on Media Richness Theory, this study investigates the frequency of use (RQ1) and perceived quality (RQ2) of established media as well as the potential use of selected innovative media (RQ3) in GP-GC relationships with a particular focus on digital media. A cross-sectional online survey and vignette experiment were conducted in February 2021 among N = 286 university students in Germany (mean age 23 years, 57% female) who reported on the direct and mediated communication with their grandparents. In addition to face-to-face interactions, non-digital and digital established media (such as telephone, texting, video conferencing) and innovative digital media, namely augmented reality (AR)-based and social robot-based communication technologies, were covered. Face-to-face and phone communication occurred most frequently in GP-GC relationships: 85% of participants reported them taking place at least a few times per year (RQ1). Non-digital established media were associated with higher perceived communication quality than digital established media (RQ2). Innovative digital media received less favorable quality evaluations than established media. Participants expressed doubts regarding the technology competence of their grandparents, but still met innovative media with high expectations regarding improved communication quality (RQ3). Richer media, such as video conferencing or AR, do not automatically lead to better perceived communication quality, while leaner media, such as letters or text messages, can provide rich communication experiences. More research is needed to fully understand and systematically improve the utility, usability, and joy of use of different digital communication technologies employed in GP-GC relationships.
Stephan, Benedict; Dontsov, Ilja; Müller, Steffen; Groß, Horst-Michael
On learning of inverse kinematics for highly redundant robots with neural networks. - In: 2023 21st International Conference on Advanced Robotics (ICAR), (2023), S. 402-408

The inverse kinematic problem for redundant robots is still difficult to solve. One approach is learning the inverse kinematic model with artificial neural networks, while the key challenge is the ambiguity of solutions. Due to the redundancy in the robot's degrees of freedom, there are multiple or even unlimited valid joint states bringing the end effector to a desired position. We show to what extent this problem influences the achievable accuracy of supervised training approaches depending on the number of degrees of freedom. To overcome the difficulties, a new training scheme is proposed, which uses the analytically solvable forward kinematics model. The new unsupervised training method uses random sampling in the joint state space and is not dependent on ambiguous tuples of joint values and end effector poses. We analyze the effect of the sample density on the remaining position error and show that additional soft constraints can easily be integrated in the training scheme, which offers the possibility to consider obstacle avoidance directly in the inverse kinematic model. Evaluations have been done using different robot models with up to 20 degrees of freedom, while not only position, but also the end effector's orientation at the goal point is considered.
Seichter, Daniel; Stephan, Benedict; Fischedick, Söhnke Benedikt; Müller, Steffen; Rabes, Leonard; Groß, Horst-Michael
PanopticNDT: efficient and robust panoptic mapping. - In: 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), (2023), S. 7233-7240

As the application scenarios of mobile robots are getting more complex and challenging, scene understanding becomes increasingly crucial. A mobile robot that is supposed to operate autonomously in indoor environments must have precise knowledge about what objects are present, where they are, what their spatial extent is, and how they can be reached; i.e., information about free space is also crucial. Panoptic mapping is a powerful instrument providing such information. However, building 3D panoptic maps with high spatial resolution is challenging on mobile robots, given their limited computing capabilities. In this paper, we propose PanopticNDT – an efficient and robust panoptic mapping approach based on occupancy normal distribution transform (NDT) mapping. We evaluate our approach on the publicly available datasets Hypersim and ScanNetV2. The results reveal that our approach can represent panoptic information at a higher level of detail than other state-of-the-art approaches while enabling real-time panoptic mapping on mobile robots. Finally, we prove the real-world applicability of PanopticNDT with qualitative results in a domestic application.
Scheidig, Andrea; Hartramph, Robert; Schütz, Benjamin; Müller, Steffen; Kunert, Kathleen S.; Lahne, Johanna; Oelschlegel, Ute; Scheidig, Rüdiger; Groß, Horst-Michael
Feasibility study: towards a robot-assisted gait training in ophthalmological rehabilitation. - In: 2023 International Conference on Rehabilitation Robotics (ICORR), (2023), insges. 6 S.

The idea of using mobile assistance robots for gait training in rehabilitation has been increasingly explored in recent years due to the associated benefits. This paper describes how the previous results of research and praxis on gait training with a mobile assistance robot in orthopedic rehabilitation can be transferred to ophthalmic-related orientation and mobility training for blind and visually impaired people. To this end, the specific requirements for such orientation and mobility training are presented from a therapeutic perspective. Using sensory data, it is investigated how the analysis of training errors can be automated and transferred back to the training person. These pre-examinations are the prerequisite for any form of robot-assisted mobile gait training in ophthamological rehabilitation, which does not exist so far and which is expected to be of great benefit to these patients.
Müller, Tristan; Müller, Steffen; Groß, Horst-Michael
Door manipulation as a fundamental skill realized on robots with differential drive. - In: ISR Europe 2023: 56th International Symposium on Robotics, (2023), S. 338-345

In the context of assistive mobile service robotics for elderly living in nursing homes, but also for robots realizing autonomous transport in large public buildings in general, a fundamental challenge is to overcome closed doors on their way. We review the state of the art for autonomous door opening by mobile robots and present a modular framework for enabling various robots in this task. The necessary building blocks are introduced, and evaluation results for their application on two different robot platforms are presented. A common property of our platforms, which can be found on many commercial lowcost robots is the use of differential drives. This is limiting the maneuverability and is, therefore, an important constraint for the realization of door manipulation strategies. Furthermore, our method is not dependent on computationally expensive computer vision methods but utilizes the usually available laser-range scanner for localizing and analyzing the door to be manipulated.
Fischedick, Söhnke B.; Richter, Kay; Wengefeld, Tim; Seichter, Daniel; Scheidig, Andrea; Döring, Nicola; Broll, Wolfgang; Werner, Stephan; Raake, Alexander; Groß, Horst-Michael
Bridging distance with a collaborative telepresence robot for older adults - report on progress in the CO-HUMANICS project. - In: ISR Europe 2023: 56th International Symposium on Robotics, (2023), S. 346-353

In an aging society, the social needs of older adults, such as regular interactions and independent living, are crucial for their quality of life. However, due to spatial separation from their family and friends, it is difficult to maintain social relationships. Our multidisciplinary project, CO-HUMANICS, aims to meet these needs, even over long distances, through the utilization of innovative technologies, including a robot-based system. This paper presents the first prototype of our system, designed to connect family members or friends virtually present through a mobile robot with an older adult. The system incorporates bi-directional video telephony, remote control capabilities, and enhanced visualization methods. A comparison is made with other state-of-the-art robotic approaches, focusing on remote control capabilities. We provide details about the hard- and software components, e.g., a projector-based pointing unit for collaborative telepresence to assist in everyday tasks. Our comprehensive scene representation is discussed, which utilizes 3D NDT maps, enabling advanced remote navigation features, such as autonomously driving to a specific object. Finally, insights about past and concepts for future evaluation are provided to assess the developed system.
Müller, Steffen; Stephan, Benedict; Müller, Tristan; Groß, Horst-Michael
Robust perception skills for autonomous elevator operation by mobile robots. - In: Proceedings of the 11th European Conference on Mobile Robots, (2023), insges. 7 S.

Autonomous mobile service robots with transportation tasks are often restricted to work on a single floor, since remote access to elevators is expensive to integrate for reasons of safety certification. Therefore, already ten years ago first robots have been enabled to use the human interface for riding an elevator. This requires a variety of perception and manipulation capabilities as well as social skills when it comes to interaction with other people who want to use the elevator too. We summarize the progress in solving the specific tasks of detecting and localizing the required buttons to press robustly. A deep-learning approach for detecting buttons in images is combined with a verification based on predefined knowledge on button arrangements in the elevator's control panels. Also perception of the elevator's state and our realization of the robot's elevator riding capabilities are discussed.
Fischedick, Söhnke Benedikt; Seichter, Daniel; Schmidt, Robin; Rabes, Leonard; Groß, Horst-Michael
Efficient multi-task scene analysis with RGB-D transformers. - In: IJCNN 2023 conference proceedings, (2023), insges. 10 S.

Scene analysis is essential for enabling autonomous systems, such as mobile robots, to operate in real-world environments. However, obtaining a comprehensive understanding of the scene requires solving multiple tasks, such as panoptic segmentation, instance orientation estimation, and scene classification. Solving these tasks given limited computing and battery capabilities on mobile platforms is challenging. To address this challenge, we introduce an efficient multi-task scene analysis approach, called EMSAFormer, that uses an RGB-D Transformer-based encoder to simultaneously perform the aforementioned tasks. Our approach builds upon the previously published EMSANet. However, we show that the dual CNN-based encoder of EMSANet can be replaced with a single Transformer-based encoder. To achieve this, we investigate how information from both RGB and depth data can be effectively incorporated in a single encoder. To accelerate inference on robotic hardware, we provide a custom NVIDIA TensorRT extension enabling highly optimization for our EMSAFormer approach. Through extensive experiments on the commonly used indoor datasets NYUv2, SUNRGB-D, and ScanNet, we show that our approach achieves state-of-the-art performance while still enabling inference with up to 39.1 FPS on an NVIDIA Jetson AGX Orin 32 GB.
Aganian, Dustin; Köhler, Mona; Baake, Sebastian; Eisenbach, Markus; Groß, Horst-Michael
How object information improves skeleton-based human action recognition in assembly tasks. - In: IJCNN 2023 conference proceedings, (2023), insges. 9 S.

As the use of collaborative robots (cobots) in industrial manufacturing continues to grow, human action recognition for effective human-robot collaboration becomes increasingly important. This ability is crucial for cobots to act autonomously and assist in assembly tasks. Recently, skeleton-based approaches are often used as they tend to generalize better to different people and environments. However, when processing skeletons alone, information about the objects a human interacts with is lost. Therefore, we present a novel approach of integrating object information into skeleton-based action recognition. We enhance two state-of-the-art methods by treating object centers as further skeleton joints. Our experiments on the assembly dataset IKEA ASM show that our approach improves the performance of these state-of-the-art methods to a large extent when combining skeleton joints with objects predicted by a state-of-the-art instance segmentation model. Our research sheds light on the benefits of combining skeleton joints with object information for human action recognition in assembly tasks. We analyze the effect of the object detector on the combination for action classification and discuss the important factors that must be taken into account.