Horst-Michael Gross

• Prof. Dr.
• Head of Department at Technische Universität Ilmenau

Mobile service robots for transportation tasks are usually restricted to a barrier-free environment where they can navigate freely. To enable the use of such assistive robots in existing buildings, the robot should be able to overcome closed doors independently and operate elevators with the interface designed for humans while being polite to passe...

In most re-identification approaches, embedding vectors are compared to identify the best match for a given query. However, this comparison does not take into account whether the encoded information in the embedding vectors was extracted reliably from the input images. We propose the first attempt that illustrates how all three types of uncertainty...

Telepresence robots can enhance communication experiences by providing a sense of physical presence, embodiment and may evoke co-presence. In spite of that, telepresence robots have not made it fully to consumer markets. In this paper, we investigate how different levels of controlling a telepresence robot (teleoperation, shared control, and no con...

Object detection is a crucial capability of autonomous agents for human–robot collaboration, as it facilitates the identification of the current processing state. In industrial scenarios, it is uncommon to have comprehensive knowledge of all the objects involved in a given task. Furthermore, training during deployment is not a viable option. Conseq...

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 orien...

As collaborative robots (cobots) continue to gain popularity in industrial manufacturing, effective human-robot collaboration becomes crucial. Cobots should be able to recognize human actions to assist with assembly tasks and act autonomously. To achieve this, skeleton-based approaches are often used due to their ability to generalize across variou...

In the context of collaborative robotics, handing over hand-held objects to a robot is a safety-critical task. Therefore, a robust distinction between human hands and presented objects in image data is essential to avoid contact with robotic grippers. To be able to develop machine learning methods for solving this problem, we created the OHO (Objec...

As collaborative robots (cobots) continue to gain popularity in industrial manufacturing, effective human-robot collaboration becomes crucial. Cobots should be able to recognize human actions to assist with assembly tasks and act autonomously. To achieve this, skeleton-based approaches are often used due to their ability to generalize across variou...

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...

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 computin...

For autonomous mobile service robots, closed doors that are in their way are restricting obstacles. In order to open doors with on-board manipulation skills, a robot needs to be able to localize the door’s key features, such as the hinge and handle, as well as the current opening angle. While there are vision-based approaches for detecting doors an...

With the emergence of collaborative robots (cobots), human-robot collaboration in industrial manufacturing is coming into focus. For a cobot to act autonomously and as an assistant, it must understand human actions during assembly. To effectively train models for this task, a dataset containing suitable assembly actions in a realistic setting is cr...

Humans are able to learn to recognize new objects even from a few examples. In contrast, training deep-learning-based object detectors requires huge amounts of annotated data. To avoid the need to acquire and annotate these huge amounts of data, few-shot object detection (FSOD) aims to learn from few object instances of new categories in the target...

Person re-identification plays a key role in applications where a mobile robot needs to track its users over a long period of time, even if they are partially unobserved for some time, in order to follow them or be available on demand. In this context, deep-learning based real-time feature extraction on a mobile robot is often performed on special-...

Reinforcement Learning (RL) can enable agents to learn complex tasks. However, it is difficult to interpret the knowledge and reuse it across tasks. Inductive biases can address such issues by explicitly providing generic yet useful decomposition that is otherwise difficult or expensive to learn implicitly. For example, object-centered approaches d...

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...

Background: Loneliness and social isolation in older age are considered major public health concerns and research on technology-based solutions is growing rapidly. This scoping review of reviews aims to summarize the communication technologies (CTs) (review question RQ1), theoretical frameworks (RQ2), study designs (RQ3), and positive effects of t...

Averaging predictions of a deep ensemble of networks is apopular and effective method to improve predictive performance andcalibration in various benchmarks and Kaggle competitions. However, theruntime and training cost of deep ensembles grow linearly with the size ofthe ensemble, making them unsuitable for many applications. Averagingensemble weig...

Semantic scene understanding is essential for mobile agents acting in various environments. Although semantic segmentation already provides a lot of information, details about individual objects as well as the general scene are missing but required for many real-world applications. However, solving multiple tasks separately is expensive and cannot...

A key proficiency an autonomous mobile robot must have to perform high-level tasks is a strong understanding of its environment. This involves information about what types of objects are present, where they are, what their spatial extend is, and how they can be reached, i.e., information about free space is also crucial. Semantic maps are a powerfu...

Humans are able to learn to recognize new objects even from a few examples. In contrast, training deep-learning-based object detectors requires huge amounts of annotated data. To avoid the need to acquire and annotate these huge amounts of data, few-shot object detection aims to learn from few object instances of new categories in the target domain...

The grandparent-grandchild (GP-GC) relationship is a relevant factor for the wellbeing of both grandchildren and grandparents. Digital communication technologies play an important role in maintaining it, especially when face-to-face interactions are not possible, e.g., due to living far from each other or pandemic contact restrictions. The aim of t...

This paper presents the technological status of robot-assisted gait self-training under real clinical environment conditions. A successful rehabilitation after surgery in hip endoprosthetics comprises self-training of the lessons taught by physiotherapists. While doing this, immediate feedback to the patient about deviations from the expected physi...

Appearance-based person re-identification is very challenging, i.a. due to changing illumination, image distortion, and differences in viewpoint. Therefore, it is crucial to learn an expressive feature embedding that compensates for changing environmental conditions. There are many loss functions available to achieve this goal. However, it is hard...

Through deep learning, major advances have been made in the field of visual road condition assessment in recent years. However, many approaches train from scratch and avoid transfer learning due to the different nature of road surface data and the ImageNet dataset, which is commonly used for pre-training neural networks for visual recognition. We s...

This paper presents an application of neural networks operating on multimodal 3D data (3D point cloud, RGB, thermal) to effectively and precisely segment human hands and objects held in hand to realize a safe human–robot object handover. We discuss the problems encountered in building a multimodal sensor system, while the focus is on the calibratio...

There are multiple attempts to decrease costs in the healthcare system while maintaining a high treatment quality. Digital therapies receive increasing attention in clinical practice, mainly relating to home-based exercises supported by mobile devices, eventually in combination with wearable sensors. The aim of this study was to determine if patien...

Clinical decision support using deep neural networks has become a topic of steadily growing interest. While recent work has repeatedly demonstrated that deep learning offers major advantages for medical image classification over traditional methods, clinicians are often hesitant to adopt the technology because its underlying decision-making process...

Robustly estimating the orientations of people is a crucial precondition for a wide range of applications. Especially for autonomous systems operating in populated environments, the orientation of a person can give valuable information to increase their acceptance. Given people’s orientations, mobile systems can apply navigation strategies which ta...

Analyzing scenes thoroughly is crucial for mobile robots acting in different environments. Semantic segmentation can enhance various subsequent tasks, such as (semantically assisted) person perception, (semantic) free space detection, (semantic) mapping, and (semantic) navigation. In this paper, we propose an efficient and robust RGB-D segmentation...

Motivated by recent advancements in the detection and classification of road distress, we aim to align road images from different years to facilitate automated change detection. We present a variable and efficient variant of the Regional Mutual Information (RMI) similarity metric to speed up the registration process while keeping the alignment robu...

In this paper, we present the developments regarding an expressive robot head for our socially assistive mobile robot HERA, which among other things is serving as an autonomous delivery system in public buildings. One aspect of that task is contacting and interacting with unconcerned people in order get help when doors are to open or an elevator ha...

StickyPillars introduces a sparse feature matching method on point clouds. It is the first approach applying Graph Neural Networks on point clouds to stick points of interest. The feature estimation and assignment relies on the optimal transport problem, where the cost is based on the neural network itself. We utilize a Graph Neural Network for con...

In order to meet the increasing demands of mobile service robot applications, a dedicated perception module is an essential requirement for the interaction with users in real-world scenarios. In particular, multi sensor fusion and human re-identification are recognized as active research fronts. Through this paper we contribute to the topic and pre...

The ability to handle closed doors and elevators would extend the applicability of Socially Assistive Robots (SAR) enormously. In this paper, we present a new approach which integrates uninstructed persons as helpers to open doors and to call and operate elevators. The current implementation status of these two abilities into a robotic application...

We present the first approach for 3D point-cloud to image translation based on conditional Generative Adversarial Networks (cGAN). The model handles multi-modal information sources from different domains, i.e. raw point-sets and images. The generator is capable of processing three conditions, whereas the point-cloud is encoded as raw point-set and...

One of the limiting factors when using deep learning methods in the field of highly automated driving is their lack of robustness. Objects that suddenly appear or disappear from one image to another due to inaccurate predictions as well as occurring perturbations in the input data can have devastating consequences. A possibility to increase model r...

Aging public roads need frequent inspections to analyze their condition and guarantee their permanent availability. Unfortunately, condition assessment in terms of distress detection and classification requires manual visual inspection. This manual labor is not only expensive but very time-consuming if millions of high-resolution road images of a c...

With more than 1,800,000 cases and over 862,000 deaths per year, metastatic colorectal cancer is the second leading cause of cancer related deaths in modern societies. The estimated patient survival is one of the main factors for therapy adjustment. While proportional hazard models are a key instrument for survival analysis within the last centurie...

A successful rehabilitation after surgery in hip endoprosthetics comprises self-training of the lessons taught by physiotherapists. While doing this, immediate feedback to the patient about deviations from physiological gait patterns during training is important. Such immediate feedback also concerns the correct usage of forearm crutches in three-p...

Accurate detection of 3D objects is a fundamental problem in computer vision and has an enormous impact on autonomous cars, augmented/virtual reality and many applications in robotics. In this work we present a novel fusion of neural network based state-of-the-art 3D detector and visual semantic segmentation in the context of autonomous driving. Ad...

Lidar based 3D object detection is inevitable for autonomous driving, because it directly links to environmental understanding and therefore builds the base for prediction and motion planning. The capacity of inferencing highly sparse 3D data in real-time is an ill-posed problem for lots of other application areas besides automated vehicles, e.g. a...

To allow for safe Human-Robot-Interaction in industrial scenarios like manufacturing plants, it is essential to always be aware of the location and pose of humans in the shared workspace. We introduce a real-time 3D pose estimation system using single depth images that is aimed to run on limited hardware, such as a mobile robot. For this, we optimi...

Being responsible for over 50,000 death per year within the US alone, colorectal cancer (CRC) is the second leading cause of cancer related deaths in industry nations with increasing prevalence. Within the scope of personalized medicine, precise estimates on future progress are crucial. We thus propose a novel deep learning based system using deep...

Using mobile robots in rehabilitation is an upcoming trend in the field of robotic healthcare. A possible application is robot assisted self-training after orthopedic knee or hip endoprosthesis surgery. In this scenario, it is particularly important to be able to continuously observe the patients movements in order to give timely feedback on the on...

Socially assistive robots are in the focus of research for a while. These robots are to be in close interaction with humans and try to communicate in a natural way. One intuitive modality for interaction is touch. This paper describes the design of our service robot intended for use in private homes of elderly people. We combined capacitive touch s...

Lidar based 3D object detection is inevitable for autonomous driving, because it directly links to environmental understanding and therefore builds the base for prediction and motion planning. The capacity of inferencing highly sparse 3D data in real-time is an ill-posed problem for lots of other application areas besides automated vehicles, e.g. a...

In order to allow for flexible realization of diverse navigation tasks of mobile robots, objective-based motion planner proved to be very successful. The quality of a selected control command for a certain time step is inherently connected to the considered diversity of future trajectories. Therefore, we propose an evolutionary motion planning (EMP...

In recent years, Deep Learning (DL) showed new top performances in almost all computer vision tasks that are important for automotive and robotic applications. In these applications both space and power are limited resources. Therefore, there is a need to apply DL approaches on a small and power efficient device, like the NVIDIA Jetson TX1 with a p...

Road condition acquisition and assessment are the key to guarantee their permanent availability. In order to maintain a country's whole road network, millions of high-resolution images have to be analyzed annually. Currently, this requires cost and time excessive manual labor. We aim to automate this process to a high degree by applying deep neural...

This paper describes the objectives and the state of implementation of the ROREAS project which aims at developing a socially assistive robot coach for walking and orientation training of stroke patients in the clinical rehabilitation. The robot coach is to autonomously accompany the patients during their exercises practicing their mobility skills....

This paper wants to make a further contribution towards a more transparent and systematic technical evaluation of implemented services and underlying HRI and navigation functionalities of socially assistive robots for public or domestic applications. Based on a set of selected issues, our mobile walking coach robot developed in the recently finishe...

Mobile robots following and guiding stroke patients during their rehabilitation program are in the focus of our research in rehabilitation robotics. To be able to act autonomously, it is crucial for the robot to extract long and precise movement trajectories of the patients. But already keeping track on one specific person in a crowded dynamic envi...

Kurzfassung Dieser Beitrag stellt für das Gebiet der sozialen Assistenzrobotik für die Gesundheitsassistenz einen kompakten Leitfa-den für eine systematische Bestandsaufnahme implementierter Roboterservices und der zugrundeliegenden HRI-und Navigationsbasisleistungen im Rahmen von Funktions-und technischen Nutzertests zur Verfügung. Basierend auf d...

Robust person detection is required by many computer vision applications. State of the art hand-crafted features rely on texture only or make only limited use of color. We deliver insights into features extracted by a deep learning approach, that combines three Convolutional Neural Networks to detect people at different scales. The networks learn f...

Older people tend to have difficulties using unknown technical devices and are less willing to accept technical shortcomings. Therefore, a robot that is supposed to support older people in managing daily life has to adapt to the users' needs and capabilities that are very heterogeneous within the target group. The aim of the presented case study wa...