Raphael Memmesheimer

Vitalii Tutevych, Raphael Memmesheimer, Luca Eichler et al.

Reliable object perception is necessary for general-purpose service robots. Open-vocabulary detectors struggle to generalize beyond a few classes and fully supervised training of object detectors requires time-intensive annotations. We present a semi-supervised label propagation approach for household object segmentation. A segment proposer generates class-agnostic masks, and an ensemble of Hopfield networks assigns labels by learning representative embeddings in complementary foundation model embedding spaces (CLIP, ViT, Theia). Our approach scales to 50 object classes with limited annotation overhead and can automatically label 60% of the data in a RoboCup@Home setting, where preparation time is severely constrained. Dataset and code are publicly available at https://github.com/ais-bonn/label_propagation.

Simon Bultmann, Raphael Memmesheimer, Sven Behnke

We present an approach for estimating a mobile robot's pose w.r.t. the allocentric coordinates of a network of static cameras using multi-view RGB images. The images are processed online, locally on smart edge sensors by deep neural networks to detect the robot and estimate 2D keypoints defined at distinctive positions of the 3D robot model. Robot keypoint detections are synchronized and fused on a central backend, where the robot's pose is estimated via multi-view minimization of reprojection errors. Through the pose estimation from external cameras, the robot's localization can be initialized in an allocentric map from a completely unknown state (kidnapped robot problem) and robustly tracked over time. We conduct a series of experiments evaluating the accuracy and robustness of the camera-based pose estimation compared to the robot's internal navigation stack, showing that our camera-based method achieves pose errors below 3 cm and 1° and does not drift over time, as the robot is localized allocentrically. With the robot's pose precisely estimated, its observations can be fused into the allocentric scene model. We show a real-world application, where observations from mobile robot and static smart edge sensors are fused to collaboratively build a 3D semantic map of a $\sim$240 m$^2$ indoor environment.

Evgenii Kruzhkov, Raphael Memmesheimer, Sven Behnke

Robust robot localization is an important prerequisite for navigation, but it becomes challenging when the map and robot measurements are obtained from different sensors. Prior methods are often tailored to specific environments, relying on closed-set semantics or fine-tuned features. In this work, we extend Monte Carlo Localization with vision-language features, allowing OMCL to robustly compute the likelihood of visual observations given a camera pose and a 3D map created from posed RGB-D images or aligned point clouds. These open-vocabulary features enable us to associate observations and map elements from different modalities, and to natively initialize global localization through natural language descriptions of nearby objects. We evaluate our approach using Matterport3D and Replica for indoor scenes and demonstrate generalization on SemanticKITTI for outdoor scenes.

Raphael Memmesheimer, Isabelle Kuhlmann, Mark Mints et al.

We present Scratchy---a modular, lightweight robot built for low budget competition attendances. Its base is mainly built with standard 4040 aluminium profiles and the robot is driven by four mecanum wheels on brushless DC motors. In combination with a laser range finder we use estimated odometry -- which is calculated by encoders -- for creating maps using a particle filter. A RGB-D camera is utilized for object detection and pose estimation. Additionally, there is the option to use a 6-DOF arm to grip objects from an estimated pose or generally for manipulation tasks. The robot can be assembled in less than one hour and fits into two pieces of hand luggage or one bigger suitcase. Therefore, it provides a huge advantage for student teams that participate in robot competitions like the European Robotics League or RoboCup. Thus, this keeps the funding required for participation, which is often a big hurdle for student teams to overcome, low. The software and additional hardware descriptions are available under: https://github.com/homer-robotics/scratchy.

Jonas Bode, Bastian Pätzold, Raphael Memmesheimer et al.

Recent advances in LLM have been instrumental in autonomous robot control and human-robot interaction by leveraging their vast general knowledge and capabilities to understand and reason across a wide range of tasks and scenarios. Previous works have investigated various prompt engineering techniques for improving the performance of LLM to accomplish tasks, while others have proposed methods that utilize LLMs to plan and execute tasks based on the available functionalities of a given robot platform. In this work, we consider both lines of research by comparing prompt engineering techniques and combinations thereof within the application of high-level task planning and execution in service robotics. We define a diverse set of tasks and a simple set of functionalities in simulation, and measure task completion accuracy and execution time for several state-of-the-art models.

Jonas Bode, Raphael Memmesheimer, Sven Behnke

Acting in human environments is a crucial capability for general-purpose robots, necessitating a robust understanding of natural language and its application to physical tasks. This paper seeks to harness the capabilities of diffusion models within a visuomotor policy framework that merges visual and textual inputs to generate precise robotic trajectories. By employing reference demonstrations during training, the model learns to execute manipulation tasks specified through textual commands within the robot's immediate environment. The proposed research aims to extend an existing model by leveraging improved embeddings, and adapting techniques from diffusion models for image generation. We evaluate our methods on the CALVIN dataset, proving enhanced performance on various manipulation tasks and an increased long-horizon success rate when multiple tasks are executed in sequence. Our approach reinforces the usefulness of diffusion models and contributes towards general multitask manipulation.

Yihao Wang, Raphael Memmesheimer, Sven Behnke

The availability of large language models and open-vocabulary object perception methods enables more flexibility for domestic service robots. The large variability of domestic tasks can be addressed without implementing each task individually by providing the robot with a task description along with appropriate environment information. In this work, we propose LIAM - an end-to-end model that predicts action transcripts based on language, image, action, and map inputs. Language and image inputs are encoded with a CLIP backbone, for which we designed two pre-training tasks to fine-tune its weights and pre-align the latent spaces. We evaluate our method on the ALFRED dataset, a simulator-generated benchmark for domestic tasks. Our results demonstrate the importance of pre-aligning embedding spaces from different modalities and the efficacy of incorporating semantic maps.

Svetlana Seliunina, Artem Otelepko, Raphael Memmesheimer et al.

Robots need to perceive persons in their surroundings for safety and to interact with them. In this paper, we present a person segmentation and action classification approach that operates on 3D scans of hemisphere field of view LiDAR sensors. We recorded a data set with an Ouster OSDome-64 sensor consisting of scenes where persons perform three different actions and annotated it. We propose a method based on a MaskDINO model to detect and segment persons and to recognize their actions from combined spherical projected multi-channel representations of the LiDAR data with an additional positional encoding. Our approach demonstrates good performance for the person segmentation task and further performs well for the estimation of the person action states walking, waving, and sitting. An ablation study provides insights about the individual channel contributions for the person segmentation task. The trained models, code and dataset are made publicly available.

Christian Korbach, Markus D. Solbach, Raphael Memmesheimer et al.

The presentation and analysis of image data from a single viewpoint are often not sufficient to solve a task. Several viewpoints are necessary to obtain more information. The next-best-view problem attempts to find the optimal viewpoint with the greatest information gain for the underlying task. In this work, a robot arm holds an object in its end-effector and searches for a sequence of next-best-view to explicitly identify the object. We use Soft Actor-Critic (SAC), a method of deep reinforcement learning, to learn these next-best-views for a specific set of objects. The evaluation shows that an agent can learn to determine an object pose to which the robot arm should move an object. This leads to a viewpoint that provides a more accurate prediction to distinguish such an object from other objects better. We make the code publicly available for the scientific community and for reproducibility.

Michael Duhme, Raphael Memmesheimer, Dietrich Paulus

In this paper, we present Fusion-GCN, an approach for multimodal action recognition using Graph Convolutional Networks (GCNs). Action recognition methods based around GCNs recently yielded state-of-the-art performance for skeleton-based action recognition. With Fusion-GCN, we propose to integrate various sensor data modalities into a graph that is trained using a GCN model for multi-modal action recognition. Additional sensor measurements are incorporated into the graph representation, either on a channel dimension (introducing additional node attributes) or spatial dimension (introducing new nodes). Fusion-GCN was evaluated on two public available datasets, the UTD-MHAD- and MMACT datasets, and demonstrates flexible fusion of RGB sequences, inertial measurements and skeleton sequences. Our approach gets comparable results on the UTD-MHAD dataset and improves the baseline on the large-scale MMACT dataset by a significant margin of up to 12.37% (F1-Measure) with the fusion of skeleton estimates and accelerometer measurements.

Raphael Memmesheimer, Simon Häring, Nick Theisen et al.

One-shot action recognition allows the recognition of human-performed actions with only a single training example. This can influence human-robot-interaction positively by enabling the robot to react to previously unseen behaviour. We formulate the one-shot action recognition problem as a deep metric learning problem and propose a novel image-based skeleton representation that performs well in a metric learning setting. Therefore, we train a model that projects the image representations into an embedding space. In embedding space the similar actions have a low euclidean distance while dissimilar actions have a higher distance. The one-shot action recognition problem becomes a nearest-neighbor search in a set of activity reference samples. We evaluate the performance of our proposed representation against a variety of other skeleton-based image representations. In addition, we present an ablation study that shows the influence of different embedding vector sizes, losses and augmentation. Our approach lifts the state-of-the-art by 3.3% for the one-shot action recognition protocol on the NTU RGB+D 120 dataset under a comparable training setup. With additional augmentation our result improved over 7.7%.

Raphael Memmesheimer, Nick Theisen, Dietrich Paulus

Recognizing an activity with a single reference sample using metric learning approaches is a promising research field. The majority of few-shot methods focus on object recognition or face-identification. We propose a metric learning approach to reduce the action recognition problem to a nearest neighbor search in embedding space. We encode signals into images and extract features using a deep residual CNN. Using triplet loss, we learn a feature embedding. The resulting encoder transforms features into an embedding space in which closer distances encode similar actions while higher distances encode different actions. Our approach is based on a signal level formulation and remains flexible across a variety of modalities. It further outperforms the baseline on the large scale NTU RGB+D 120 dataset for the One-Shot action recognition protocol by 5.6%. With just 60% of the training data, our approach still outperforms the baseline approach by 3.7%. With 40% of the training data, our approach performs comparably well to the second follow up. Further, we show that our approach generalizes well in experiments on the UTD-MHAD dataset for inertial, skeleton and fused data and the Simitate dataset for motion capturing data. Furthermore, our inter-joint and inter-sensor experiments suggest good capabilities on previously unseen setups.

Raphael Memmesheimer, Nick Theisen, Dietrich Paulus

We present a simple, yet effective and flexible method for action recognition supporting multiple sensor modalities. Multivariate signal sequences are encoded in an image and are then classified using a recently proposed EfficientNet CNN architecture. Our focus was to find an approach that generalizes well across different sensor modalities without specific adaptions while still achieving good results. We apply our method to 4 action recognition datasets containing skeleton sequences, inertial and motion capturing measurements as well as \wifi fingerprints that range up to 120 action classes. Our method defines the current best CNN-based approach on the NTU RGB+D 120 dataset, lifts the state of the art on the ARIL Wi-Fi dataset by +6.78%, improves the UTD-MHAD inertial baseline by +14.4%, the UTD-MHAD skeleton baseline by 1.13% and achieves 96.11% on the Simitate motion capturing data (80/20 split). We further demonstrate experiments on both, modality fusion on a signal level and signal reduction to prevent the representation from overloading.

Pascal Schneider, Raphael Memmesheimer, Ivanna Kramer et al.

Gesture recognition opens up new ways for humans to intuitively interact with machines. Especially for service robots, gestures can be a valuable addition to the means of communication to, for example, draw the robot's attention to someone or something. Extracting a gesture from video data and classifying it is a challenging task and a variety of approaches have been proposed throughout the years. This paper presents a method for gesture recognition in RGB videos using OpenPose to extract the pose of a person and Dynamic Time Warping (DTW) in conjunction with One-Nearest-Neighbor (1NN) for time-series classification. The main features of this approach are the independence of any specific hardware and high flexibility, because new gestures can be added to the classifier by adding only a few examples of it. We utilize the robustness of the Deep Learning-based OpenPose framework while avoiding the data-intensive task of training a neural network ourselves. We demonstrate the classification performance of our method using a public dataset.

Raphael Memmesheimer, Ivanna Mykhalchyshyna, Viktor Seib et al.

We present Simitate --- a hybrid benchmarking suite targeting the evaluation of approaches for imitation learning. A dataset containing 1938 sequences where humans perform daily activities in a realistic environment is presented. The dataset is strongly coupled with an integration into a simulator. RGB and depth streams with a resolution of 960$\mathbb{\times}$540 at 30Hz and accurate ground truth poses for the demonstrator's hand, as well as the object in 6 DOF at 120Hz are provided. Along with our dataset we provide the 3D model of the used environment, labeled object images and pre-trained models. A benchmarking suite that aims at fostering comparability and reproducibility supports the development of imitation learning approaches. Further, we propose and integrate evaluation metrics on assessing the quality of effect and trajectory of the imitation performed in simulation. Simitate is available on our project website: \url{https://agas.uni-koblenz.de/data/simitate/}.

Mauricio Matamoros, Viktor Seib, Raphael Memmesheimer et al.

Scientific competitions are important in robotics because they foster knowledge exchange and allow teams to test their research in unstandardized scenarios and compare result. In the field of service robotics its role becomes crucial. Competitions like RoboCup@Home bring robots to people, a fundamental step to integrate them into society. In this paper we summarize and discuss the differences between the achievements claimed by teams in their team description papers, and the results observed during the competition^1 from a qualitative perspective. We conclude with a set of important challenges to be conquered first in order to take robots to people's homes. We believe that competitions are also an excellent opportunity to collect data of direct and unbiased interactions for further research. ^1 The authors belong to several teams who have participated in RoboCup@Home as early as 2007

Raphael Memmesheimer, Ivanna Mykhalchyshyna, Viktor Seib et al.

In this paper we present an approach for learning to imitate human behavior on a semantic level by markerless visual observation. We analyze a set of spatial constraints on human pose data extracted using convolutional pose machines and object informations extracted from 2D image sequences. A scene analysis, based on an ontology of objects and affordances, is combined with continuous human pose estimation and spatial object relations. Using a set of constraints we associate the observed human actions with a set of executable robot commands. We demonstrate our approach in a kitchen task, where the robot learns to prepare a meal.