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 present a modular detection and tracking system that models position and additional properties of persons in the surroundings of a mobile robot. The proposed system introduces a probability-based data association method that besides the position can incorporate face and color-based appearance features in order to realize a re-identification of persons when tracking gets interrupted. The system combines the results of various state-of-the-art image-based detection systems for person recognition, person identification and attribute estimation. This allows a stable estimate of a mobile robot’s user, even in complex, cluttered environments with long-lasting occlusions. In our benchmark, we introduce a new measure for tracking consistency and show the improvements when face and appearance-based re-identification are combined. The tracking system was applied in a real world application with a mobile rehabilitation assistant robot in a public hospital. The estimated states of persons are used for the user-centered navigation behaviors, e.g., guiding or approaching a person, but also for realizing a socially acceptable navigation in public environments.

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 calibration and alignment of a set of cameras including RGB, thermal, and NIR cameras. We propose the use of a copper–plastic chessboard calibration target with an internal active light source (near-infrared and visible light). By brief heating, the calibration target could be simultaneously and legibly captured by all cameras. Based on the multimodal dataset captured by our sensor system, PointNet, PointNet++, and RandLA-Net are utilized to verify the effectiveness of applying multimodal point cloud data for hand–object segmentation. These networks were trained on various data modes (XYZ, XYZ-T, XYZ-RGB, and XYZ-RGB-T). The experimental results show a significant improvement in the segmentation performance of XYZ-RGB-T (mean Intersection over Union: $82.8\%$ by RandLA-Net) compared with the other three modes ($77.3\%$ by XYZ-RGB, $35.7\%$ by XYZ-T, $35.7\%$ by XYZ), in which it is worth mentioning that the Intersection over Union for the single class of hand achieves $92.6\%$.

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 (Object Hand-Over) dataset of tools and other everyday objects being held by human hands. Our dataset consists of color, depth, and thermal images with the addition of pose and shape information about the objects in a real-world scenario. Although the focus of this paper is on instance segmentation, our dataset also enables training for different tasks such as 3D pose estimation or shape estimation of objects. For the instance segmentation task, we present a pipeline for automated label generation in point clouds, as well as image data. Through baseline experiments, we show that these labels are suitable for training an instance segmentation to distinguish hands from objects on a per-pixel basis. Moreover, we present qualitative results for applying our trained model in a real-world application.

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 and handles in images, we concentrate on analyzing 2D laser range scans. This requires less computational effort, and laser-scan sensors are available on most mobile robot platforms. Therefore, we developed three different machine learning approaches and a heuristic method based on line fitting able to extract the required position data. The algorithms are compared with respect to localization accuracy with help of a dataset containing laser range scans of doors. Our LaserDoors dataset is publicly available for academic use. Pros and cons of the individual methods are discussed; basically, the machine learning methods could outperform the heuristic method, but require special training data when applied in a real application.