{"title":"Model-Driven Run-Time Dependency Graphs for Component-Based Robotic Software","authors":"V. Nagrath, C. Schlegel","doi":"10.1109/irc52146.2021.00033","DOIUrl":"https://doi.org/10.1109/irc52146.2021.00033","url":null,"abstract":"For the observance of a system’s non-functional properties, one must first parameterise them as elemental or compound objects. Dependency objects are defined as entities that encapsulate a distinct system characteristic that is relevant to and is altered by components and connections that compose the system. Software components and network connections form nodes of a graph, edges of which represent a change of one or more system-wide properties. Dependency graphs are networks of dependencies that emerge from the flow of system-level characteristics, controlled by evidence and business logic. Component developers and network experts provide functional units to describe how the value of a particular dependency object is transferred across computational or connection nodes respectively. Run-time dependency graph models for independently developed software components and network connections are integrated, built and explored while building or validating a system. These run-time models are used to observe networks of dependencies that emerge from the flow of system-level features graphically and programmatically. The design and engineering anatomy of such a toolchain is presented in this paper.","PeriodicalId":439358,"journal":{"name":"2021 Fifth IEEE International Conference on Robotic Computing (IRC)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132870457","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"On the Probabilistic Coupling Between Rotation and Translation in State Estimation","authors":"Lino Antoni Giefer, J. Clemens","doi":"10.1109/IRC52146.2021.00017","DOIUrl":"https://doi.org/10.1109/IRC52146.2021.00017","url":null,"abstract":"Object tracking is an essential part of autonomous systems and deals with the estimation of the states of all dynamic objects within the area of surveillance. An appropriate state representation is highly important to capture the associated uncertainties correctly and Lie groups have been investigated with respect to this aspect over the last years. In this paper, we evaluate the performance of an extended Kalman filter on Lie groups employing two different state space representations: the direct and the semi-direct product of the two-dimensional special orthogonal group and a two-dimensional Euclidean vector capturing the rotational and translational component, respectively. Focus of our study is to investigate if the intrinsic relationship between rotation and translation is appropriately captured by means of the covariance matrix or if an encapsulation into the state space is beneficial. Statistical evaluation shows that a representation using the semi-direct product of the two components yields a better performance in terms of the Wasserstein distance and the root-mean-square errors of position and orientation.","PeriodicalId":439358,"journal":{"name":"2021 Fifth IEEE International Conference on Robotic Computing (IRC)","volume":"189 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130157508","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Flexible-Joint Manipulator Trajectory Tracking with Learned Two-Stage Model employing One-Step Future Prediction","authors":"D. Pavlichenko, Sven Behnke","doi":"10.1109/IRC52146.2021.00008","DOIUrl":"https://doi.org/10.1109/IRC52146.2021.00008","url":null,"abstract":"Flexible-joint manipulators are frequently used for increased safety during human-robot collaboration and shared workspace tasks. However, joint flexibility significantly reduces the accuracy of motion, especially at high velocities and with inexpensive actuators. In this paper, we present a learning-based approach to identify the unknown dynamics of a flexible-joint manipulator and improve the trajectory tracking at high velocities. We propose a two-stage model which is composed of a one-step forward dynamics future predictor and an inverse dynamics estimator. The second part is based on linear time-invariant dynamical operators to approximate the feed-forward joint position and velocity commands. We train the model end-to-end on real-world data and evaluate it on the Baxter robot. Our experiments indicate that augmenting the input with one-step future state prediction improves the performance, compared to the same model without prediction. We compare joint position, joint velocity and end-effector position tracking accuracy against the classical baseline controller and several simpler models.","PeriodicalId":439358,"journal":{"name":"2021 Fifth IEEE International Conference on Robotic Computing (IRC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131057543","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Upinder Kaur, Haozhe Zhou, Xiaxin Shen, B. Min, R. Voyles
{"title":"RoboMal: Malware Detection for Robot Network Systems","authors":"Upinder Kaur, Haozhe Zhou, Xiaxin Shen, B. Min, R. Voyles","doi":"10.1109/IRC52146.2021.00016","DOIUrl":"https://doi.org/10.1109/IRC52146.2021.00016","url":null,"abstract":"Robot systems are increasingly integrating into numerous avenues of modern life. From cleaning houses to providing guidance and emotional support, robots now work directly with humans. Due to their far-reaching applications and progressively complex architecture, they are being targeted by adversarial attacks such as sensor-actuator attacks, data spoofing, malware, and network intrusion. Therefore, security for robotic systems has become crucial. In this paper, we address the underserved area of malware detection in robotic software. Since robots work in close proximity to humans, often with direct interactions, malware could have life-threatening impacts. Hence, we propose the RoboMal framework of static malware detection on binary executables to detect malware before it gets a chance to execute. Additionally, we address the great paucity of data in this space by providing the RoboMal dataset1 comprising controller executables of a small-scale autonomous car. The performance of the framework is compared against widely used supervised learning models: GRU, CNN, and ANN. Notably, the LSTM-based RoboMal model outperforms the other models with an accuracy of 85% and precision of 87% in 10-fold cross-validation, hence proving the effectiveness of the proposed framework.","PeriodicalId":439358,"journal":{"name":"2021 Fifth IEEE International Conference on Robotic Computing (IRC)","volume":"148 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133365779","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Lars Leyendecker, Markus Schmitz, H. Zhou, V. Samsonov, Marius Rittstieg, Daniel Lütticke
{"title":"Deep Reinforcement Learning for Robotic Control in High-Dexterity Assembly Tasks - A Reward Curriculum Approach","authors":"Lars Leyendecker, Markus Schmitz, H. Zhou, V. Samsonov, Marius Rittstieg, Daniel Lütticke","doi":"10.1109/IRC52146.2021.00012","DOIUrl":"https://doi.org/10.1109/IRC52146.2021.00012","url":null,"abstract":"For years, the fully-automated robotic assembly has been a highly sought-after technology in large-scale manufacturing. Yet it still struggles to find widespread implementation in industrial environments. Traditional programming has so far proven to be insufficient to provide the required flexibility and dexterity to solve complex assembly tasks. Although research in robotic control using deep reinforcement learning (DRL) advances quickly, the transfer to real-world applications in industrial settings is lagging behind. In this study, we apply DRL for robotic motion control at the use-case of a multi-body contact automotive assembly task and focus on optimizing the final performance on the real-world setup. We propose a reward-curriculum learning approach in combination with domain randomization to obtain both force-sensitivity and generalizability. We train an agent exclusively in simulation and successfully perform the Sim-to-Real transfer. Finally, we evaluate the controller’s performance and robustness on an industrial setup and reflect its adherence to the high automotive production standards.","PeriodicalId":439358,"journal":{"name":"2021 Fifth IEEE International Conference on Robotic Computing (IRC)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132937815","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yaqin Wang, Facundo Esquivel Fagiani, K. Ho, E. Matson
{"title":"A Feature Engineering Focused System for Acoustic UAV Detection","authors":"Yaqin Wang, Facundo Esquivel Fagiani, K. Ho, E. Matson","doi":"10.1109/irc52146.2021.00031","DOIUrl":"https://doi.org/10.1109/irc52146.2021.00031","url":null,"abstract":"The evolution of Unmanned Aerial Vehicles (UAVs) technology has made these devices suitable for a wide new range of applications, but it has also raised safety concerns as UAVs can be used for carrying explosives or weapons with malicious intentions. In this paper, Machine Learning (ML) algorithms are used to identify UAVs by using the sound signals they emit. We evaluate and propose a feature-based classification. Five individual features, and one combination of features are used to train four machine learning classification approaches: a neural network (NN), a support vector machine (SVM), a Gaussian Naive Bayes (GNB), and K-Nearest Neighbor (KNN). The training and testing dataset is composed of sound samples of UAVs and noise. The labels in the dataset we collected include the sound files of noise and UAVs. The results show that the combination of features outperforms the individual ones, with higher average accuracy scores.","PeriodicalId":439358,"journal":{"name":"2021 Fifth IEEE International Conference on Robotic Computing (IRC)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116076019","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Automated behavior modeling for verifying safety-relevant modules","authors":"Vladislav Nenchev","doi":"10.1109/IRC52146.2021.00021","DOIUrl":"https://doi.org/10.1109/IRC52146.2021.00021","url":null,"abstract":"Despite employing state-of-the-art safety mechanisms, the intractable variety of possible dynamical behaviors requires automating verification in safety-relevant domains like automated driving. This paper proposes an automatic modeling approach for safety-relevant modules amenable to verification of formal requirements. A logical predicate abstraction is imposed over the module’s inputs and outputs. By stimulating the module with possible finite input sequences, an approximate behavior model is obtained. The approximation accuracy can be improved by increasing the trace length. Then, the satisfaction of the specification is evaluated by model checking in an iterative manner, as shown for the implementation of an automated driving system supervisor.","PeriodicalId":439358,"journal":{"name":"2021 Fifth IEEE International Conference on Robotic Computing (IRC)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131468947","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"FingerVision with Whiskers: Light Touch Detection with Vision-based Tactile Sensors","authors":"Akihiko Yamaguchi","doi":"10.1109/IRC52146.2021.00015","DOIUrl":"https://doi.org/10.1109/IRC52146.2021.00015","url":null,"abstract":"In order to increase the sensitivity of the vision-based tactile sensor FingerVision especially to normal force, we explore an idea of introducing whiskers as an alternative to markers. Since whiskers deforms more largely against light touch than markers, the image change of the FingerVision camera is larger, and thus the resolution of force is increased. In this paper, we fabricate and compare some versions of FingerVision with whiskers. The empirical comparisons demonstrate that the idea to introduce whiskers work as we expect. This paper also demonstrates intuitive applications, pulling a tissue paper grasped by a robot and poking a standing pencil by a robot.","PeriodicalId":439358,"journal":{"name":"2021 Fifth IEEE International Conference on Robotic Computing (IRC)","volume":"2016 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127424800","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}