004 Datenverarbeitung; Informatik
Refine
H-BRS Bibliography
- yes (57)
Departments, institutes and facilities
- Fachbereich Informatik (51)
- Institute of Visual Computing (IVC) (9)
- Institut für Cyber Security & Privacy (ICSP) (8)
- Graduierteninstitut (4)
- Institut für Technik, Ressourcenschonung und Energieeffizienz (TREE) (4)
- Fachbereich Wirtschaftswissenschaften (2)
- Institut für IT-Service (ITS) (1)
- Institut für Verbraucherinformatik (IVI) (1)
- Institut für funktionale Gen-Analytik (IFGA) (1)
Document Type
- Conference Object (29)
- Article (7)
- Preprint (5)
- Doctoral Thesis (4)
- Part of a Book (3)
- Research Data (3)
- Report (3)
- Book (monograph, edited volume) (2)
- Conference Proceedings (1)
Year of publication
- 2021 (57) (remove)
Keywords
- Cognitive robot control (2)
- Dimensionality reduction (2)
- Explainable robotics (2)
- Generative Models (2)
- Human-Computer Interaction (2)
- Learning from experience (2)
- LoRa (2)
- LoRaWAN (2)
- Low-Power Wide Area Network (LP-WAN) (2)
- Measurement (2)
Jahresbericht 2020
(2021)
It has been well proved that deep networks are efficient at extracting features from a given (source) labeled dataset. However, it is not always the case that they can generalize well to other (target) datasets which very often have a different underlying distribution. In this report, we evaluate four different domain adaptation techniques for image classification tasks: DeepCORAL, DeepDomainConfusion, CDAN and CDAN+E. These techniques are unsupervised given that the target dataset dopes not carry any labels during training phase. We evaluate model performance on the office-31 dataset. A link to the github repository of this report can be found here: https://github.com/agrija9/Deep-Unsupervised-Domain-Adaptation.
Ice accumulation in the blades of wind turbines can cause them to describe anomalous rotations or no rotations at all, thus affecting the generation of electricity and power output. In this work, we investigate the problem of ice accumulation in wind turbines by framing it as anomaly detection of multi-variate time series. Our approach focuses on two main parts: first, learning low-dimensional representations of time series using a Variational Recurrent Autoencoder (VRAE), and second, using unsupervised clustering algorithms to classify the learned representations as normal (no ice accumulated) or abnormal (ice accumulated). We have evaluated our approach on a custom wind turbine time series dataset, for the two-classes problem (one normal versus one abnormal class), we obtained a classification accuracy of up to 96$\%$ on test data. For the multiple-class problem (one normal versus multiple abnormal classes), we present a qualitative analysis of the low-dimensional learned latent space, providing insights into the capacities of our approach to tackle such problem. The code to reproduce this work can be found here https://github.com/agrija9/Wind-Turbines-VRAE-Paper.
Machine learning and neural networks are now ubiquitous in sonar perception, but it lags behind the computer vision field due to the lack of data and pre-trained models specifically for sonar images. In this paper we present the Marine Debris Turntable dataset and produce pre-trained neural networks trained on this dataset, meant to fill the gap of missing pre-trained models for sonar images. We train Resnet 20, MobileNets, DenseNet121, SqueezeNet, MiniXception, and an Autoencoder, over several input image sizes, from 32 x 32 to 96 x 96, on the Marine Debris turntable dataset. We evaluate these models using transfer learning for low-shot classification in the Marine Debris Watertank and another dataset captured using a Gemini 720i sonar. Our results show that in both datasets the pre-trained models produce good features that allow good classification accuracy with low samples (10-30 samples per class). The Gemini dataset validates that the features transfer to other kinds of sonar sensors. We expect that the community benefits from the public release of our pre-trained models and the turntable dataset.
Robot Action Diagnosis and Experience Correction by Falsifying Parameterised Execution Models
(2021)
When faced with an execution failure, an intelligent robot should be able to identify the likely reasons for the failure and adapt its execution policy accordingly. This paper addresses the question of how to utilise knowledge about the execution process, expressed in terms of learned constraints, in order to direct the diagnosis and experience acquisition process. In particular, we present two methods for creating a synergy between failure diagnosis and execution model learning. We first propose a method for diagnosing execution failures of parameterised action execution models, which searches for action parameters that violate a learned precondition model. We then develop a strategy that uses the results of the diagnosis process for generating synthetic data that are more likely to lead to successful execution, thereby increasing the set of available experiences to learn from. The diagnosis and experience correction methods are evaluated for the problem of handle grasping, such that we experimentally demonstrate the effectiveness of the diagnosis algorithm and show that corrected failed experiences can contribute towards improving the execution success of a robot.
A qualitative study of Machine Learning practices and engineering challenges in Earth Observation
(2021)
Machine Learning (ML) is ubiquitously on the advance. Like many domains, Earth Observation (EO) also increasingly relies on ML applications, where ML methods are applied to process vast amounts of heterogeneous and continuous data streams to answer socially and environmentally relevant questions. However, developing such ML- based EO systems remains challenging: Development processes and employed workflows are often barely structured and poorly reported. The application of ML methods and techniques is considered to be opaque and the lack of transparency is contradictory to the responsible development of ML-based EO applications. To improve this situation a better understanding of the current practices and engineering-related challenges in developing ML-based EO applications is required. In this paper, we report observations from an exploratory study where five experts shared their view on ML engineering in semi-structured interviews. We analysed these interviews with coding techniques as often applied in the domain of empirical software engineering. The interviews provide informative insights into the practical development of ML applications and reveal several engineering challenges. In addition, interviewees participated in a novel workflow sketching task, which provided a tangible reflection of implicit processes. Overall, the results confirm a gap between theoretical conceptions and real practices in ML development even though workflows were sketched abstractly as textbook-like. The results pave the way for a large-scale investigation on requirements for ML engineering in EO.
When an autonomous robot learns how to execute actions, it is of interest to know if and when the execution policy can be generalised to variations of the learning scenarios. This can inform the robot about the necessity of additional learning, as using incomplete or unsuitable policies can lead to execution failures. Generalisation is particularly relevant when a robot has to deal with a large variety of objects and in different contexts. In this paper, we propose and analyse a strategy for generalising parameterised execution models of manipulation actions over different objects based on an object ontology. In particular, a robot transfers a known execution model to objects of related classes according to the ontology, but only if there is no other evidence that the model may be unsuitable. This allows using ontological knowledge as prior information that is then refined by the robot’s own experiences. We verify our algorithm for two actions – grasping and stowing everyday objects – such that we show that the robot can deduce cases in which an existing policy can generalise to other objects and when additional execution knowledge has to be acquired.
Target meaning representations for semantic parsing tasks are often based on programming or query languages, such as SQL, and can be formalized by a context-free grammar. Assuming a priori knowledge of the target domain, such grammars can be exploited to enforce syntactical constraints when predicting logical forms. To that end, we assess how syntactical parsers can be integrated into modern encoder-decoder frameworks. Specifically, we implement an attentional SEQ2SEQ model that uses an LR parser to maintain syntactically valid sequences throughout the decoding procedure. Compared to other approaches to grammar-guided decoding that modify the underlying neural network architecture or attempt to derive full parse trees, our approach is conceptually simpler, adds less computational overhead during inference and integrates seamlessly with current SEQ2SEQ frameworks. We present preliminary evaluation results against a recurrent SEQ2SEQ baseline on GEOQUERY and ATIS and demonstrate improved performance while enforcing grammatical constraints.
Application of underwater robots are on the rise, most of them are dependent on sonar for underwater vision, but the lack of strong perception capabilities limits them in this task. An important issue in sonar perception is matching image patches, which can enable other techniques like localization, change detection, and mapping. There is a rich literature for this problem in color images, but for acoustic images, it is lacking, due to the physics that produce these images. In this paper we improve on our previous results for this problem (Valdenegro-Toro et al, 2017), instead of modeling features manually, a Convolutional Neural Network (CNN) learns a similarity function and predicts if two input sonar images are similar or not. With the objective of improving the sonar image matching problem further, three state of the art CNN architectures are evaluated on the Marine Debris dataset, namely DenseNet, and VGG, with a siamese or two-channel architecture, and contrastive loss. To ensure a fair evaluation of each network, thorough hyper-parameter optimization is executed. We find that the best performing models are DenseNet Two-Channel network with 0.955 AUC, VGG-Siamese with contrastive loss at 0.949 AUC and DenseNet Siamese with 0.921 AUC. By ensembling the top performing DenseNet two-channel and DenseNet-Siamese models overall highest prediction accuracy obtained is 0.978 AUC, showing a large improvement over the 0.91 AUC in the state of the art.
The dataset contains the following data from successful and failed executions of the Toyota HSR robot placing a book on a shelf.
RGB images from the robot's head camera
Depth images from the robot's head camera
Rendered images of the robot's 3D model from the point of view of the robot's head camera
Force-torque readings from a wrist-mounted force-torque sensor
Joint efforts, velocities and positions
extrinsic and intrinsic camera calibration parameters
frame-level anomaly annotations
The anomalies that occur during execution include:
the manipulated book falling down
books on the shelf being disturbed significantly
camera occlusions
robot being disturbed by an external collision
The dataset is split into a train, validation and test set with the following number of trials:
Train: 48 successful trials
Validation: 6 successful trials
Test: 60 anomalous trials and 7 successful trials
Property-Based Testing in Simulation for Verifying Robot Action Execution in Tabletop Manipulation
(2021)
An important prerequisite for the reliability and robustness of a service robot is ensuring the robot’s correct behavior when it performs various tasks of interest. Extensive testing is one established approach for ensuring behavioural correctness; this becomes even more important with the integration of learning-based methods into robot software architectures, as there are often no theoretical guarantees about the performance of such methods in varying scenarios. In this paper, we aim towards evaluating the correctness of robot behaviors in tabletop manipulation through automatic generation of simulated test scenarios in which a robot assesses its performance using property-based testing. In particular, key properties of interest for various robot actions are encoded in an action ontology and are then verified and validated within a simulated environment. We evaluate our framework with a Toyota Human Support Robot (HSR) which is tested in a Gazebo simulation. We show that our framework can correctly and consistently identify various failed actions in a variety of randomised tabletop manipulation scenarios, in addition to providing deeper insights into the type and location of failures for each designed property.
Execution monitoring is essential for robots to detect and respond to failures. Since it is impossible to enumerate all failures for a given task, we learn from successful executions of the task to detect visual anomalies during runtime. Our method learns to predict the motions that occur during the nominal execution of a task, including camera and robot body motion. A probabilistic U-Net architecture is used to learn to predict optical flow, and the robot's kinematics and 3D model are used to model camera and body motion. The errors between the observed and predicted motion are used to calculate an anomaly score. We evaluate our method on a dataset of a robot placing a book on a shelf, which includes anomalies such as falling books, camera occlusions, and robot disturbances. We find that modeling camera and body motion, in addition to the learning-based optical flow prediction, results in an improvement of the area under the receiver operating characteristic curve from 0.752 to 0.804, and the area under the precision-recall curve from 0.467 to 0.549.
Short summary
Accompanying dataset for our paper
A. Mitrevski, P. G. Plöger, and G. Lakemeyer, "Robot Action Diagnosis and Experience Correction by Falsifying Parameterised Execution Models," in Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2021.
Contents
The dataset includes a single zip archive, containing data from the experiment described in the paper (conducted with a Toyota HSR). The zip archive contains three subdirectories:
handle_grasping_failure_database: A dump of a MongoDB database containing data from the handle grasping experiment, including ground-truth grasping failure annotations
pre_arm_motion_images: Images collected from the robot's hand camera before moving the robot's hand towards the handle
pregrasp_images: Images collected from the robot's hand camera just before closing the gripper for grasping
The image names include the time stamp at which the images were taken; this allows matching each image with the execution data in the database.
Database usage
After unzipping the archive, the database can be restored with the command
mongorestore handle_grasping_failure_database
This will create a MongoDB database with the name drawer_handle_grasping_failures.
Code for processing the data and failure analysis can be found in our <a href="https://github.com/alex-mitrevski/explainable-robot-execution-models">GitHub repository.
Contents
There are two zip archives included (grasping.zip and throwing.zip), corresponding to two experiments (grasping objects and throwing them in a drawer), both performed with a Toyota HSR. Each archive contains two directories - learning and generalisation - with object-specific learning and generalisation data. For each object, we provide a dump of a MongoDB database, which contains data sufficient for learning the models used in our experiments.
Usage
After unzipping the archives, each database can be restored with the command
mongorestore [data_directory_name]
This will create a MongoDB database with the name of the directory. Code for processing the data and model learning can be found in our <a href="https://github.com/alex-mitrevski/explainable-robot-execution-models">GitHub repository.
This thesis explores novel haptic user interfaces for touchscreens, virtual and remote environments (VE and RE). All feedback modalities have been designed to study performance and perception while focusing on integrating an additional sensory channel - the sense of touch. Related work has shown that tactile stimuli can increase performance and usability when interacting with a touchscreen. It was also shown that perceptual aspects in virtual environments could be improved by haptic feedback. Motivated by previous findings, this thesis examines the versatility of haptic feedback approaches. For this purpose, five haptic interfaces from two application areas are presented. Research methods from prototyping and experimental design are discussed and applied. These methods are used to create and evaluate the interfaces; therefore, seven experiments have been performed. All five prototypes use a unique feedback approach. While three haptic user interfaces designed for touchscreen interaction address the fingers, two interfaces developed for VE and RE target the feet. Within touchscreen interaction, an actuated touchscreen is presented, and study shows the limits and perceptibility of geometric shapes. The combination of elastic materials and a touchscreen is examined with the second interface. A psychophysical study has been conducted to highlight the potentials of the interface. The back of a smartphone is used for haptic feedback in the third prototype. Besides a psychophysical study, it is found that the touch accuracy could be increased. Interfaces presented in the second application area also highlight the versatility of haptic feedback. The sides of the feet are stimulated in the first prototype. They are used to provide proximity information of remote environments sensed by a telepresence robot. In a study, it was found that spatial awareness could be increased. Finally, the soles of the feet are stimulated. A designed foot platform that provides several feedback modalities shows that self-motion perception can be increased.