Pub Date : 2016-12-20DOI: 10.1109/IROS.2016.7759087
R. Balachandran, J. Artigas, U. Mehmood, J. Ryu
This paper presents initial results of a set of experiments to compare time-delayed teleoperation performance of selected architectures based on two popular passivity based methods, namely, Wave Variables Transformation (WVT) and Time Domain Passivity Approach (TDPA). Five different architectures widely used and available in literature are selected: 2-channel and 3-channel for both WV and TDPA, and 4-channel based on TDPA. An empirical approach for measuring transparency is proposed, which presents three main qualities: 1) Controller independency 2) Frequency dependency of performance and 3) Removal of the human operator out of the loop. In order to achieve this, the human operator is replaced by a linear actuator equipped with a force sensor. Deterministic interactions between the simulated operator and the rest of the system can thus be easily implemented and registered. Therefore, this approach allows to isolate pure effects of any control method and perform a proper analysis in terms of selected attributes for a desired metrics. In this article, these are chosen to be effective impedance and position tracking error, both in the frequency domain. In addition to the quantitative results, a qualitative analysis is presented which underlines practical implications of each architecture and control method. The comparison sample presented contains five different delays, varying from 0 to 200 milliseconds, five different environmental impedances and 5 bilateral control architectures along with an analysis of the results obtained.
{"title":"Performance comparison of Wave Variable Transformation and Time Domain Passivity Approaches for time-delayed teleoperation: Preliminary results","authors":"R. Balachandran, J. Artigas, U. Mehmood, J. Ryu","doi":"10.1109/IROS.2016.7759087","DOIUrl":"https://doi.org/10.1109/IROS.2016.7759087","url":null,"abstract":"This paper presents initial results of a set of experiments to compare time-delayed teleoperation performance of selected architectures based on two popular passivity based methods, namely, Wave Variables Transformation (WVT) and Time Domain Passivity Approach (TDPA). Five different architectures widely used and available in literature are selected: 2-channel and 3-channel for both WV and TDPA, and 4-channel based on TDPA. An empirical approach for measuring transparency is proposed, which presents three main qualities: 1) Controller independency 2) Frequency dependency of performance and 3) Removal of the human operator out of the loop. In order to achieve this, the human operator is replaced by a linear actuator equipped with a force sensor. Deterministic interactions between the simulated operator and the rest of the system can thus be easily implemented and registered. Therefore, this approach allows to isolate pure effects of any control method and perform a proper analysis in terms of selected attributes for a desired metrics. In this article, these are chosen to be effective impedance and position tracking error, both in the frequency domain. In addition to the quantitative results, a qualitative analysis is presented which underlines practical implications of each architecture and control method. The comparison sample presented contains five different delays, varying from 0 to 200 milliseconds, five different environmental impedances and 5 bilateral control architectures along with an analysis of the results obtained.","PeriodicalId":296337,"journal":{"name":"2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133233120","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}
Pub Date : 2016-12-20DOI: 10.1109/IROS.2016.7759143
Min Jun Kim, Woongyong Lee, C. Ott, W. Chung
Admittance control is a well-established and popular control strategy in modern robotics. However, the standard admittance controller has several limitations. First, the passivity can be guaranteed by finding a set of control parameters that makes the admittance function positive real. However, this approach cannot be applied to multi degrees-of-freedom robot because it requires transfer function analysis. Second, standard admittance controller is not suitable when the system is exposed to unexpected environmental interaction (of which interaction force is not measured) due to the wall sticking effect. To overcome these limitations, this paper proposes an admittance controller of which structure can be constructed by feedback interconnection of passive subsystems. The proposed approach was verified using experiments and simulations.
{"title":"A passivity-based admittance control design using feedback interconnections","authors":"Min Jun Kim, Woongyong Lee, C. Ott, W. Chung","doi":"10.1109/IROS.2016.7759143","DOIUrl":"https://doi.org/10.1109/IROS.2016.7759143","url":null,"abstract":"Admittance control is a well-established and popular control strategy in modern robotics. However, the standard admittance controller has several limitations. First, the passivity can be guaranteed by finding a set of control parameters that makes the admittance function positive real. However, this approach cannot be applied to multi degrees-of-freedom robot because it requires transfer function analysis. Second, standard admittance controller is not suitable when the system is exposed to unexpected environmental interaction (of which interaction force is not measured) due to the wall sticking effect. To overcome these limitations, this paper proposes an admittance controller of which structure can be constructed by feedback interconnection of passive subsystems. The proposed approach was verified using experiments and simulations.","PeriodicalId":296337,"journal":{"name":"2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130359640","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}
Pub Date : 2016-12-01DOI: 10.1109/IROS.2016.7759525
V. Ortenzi, Naresh Marturi, R. Stolkin, J. Kuo, M. Mistry
This paper presents a vision-based approach for estimating the configuration of, and providing control signals for, an under-sensored robot manipulator using a single monocular camera. Some remote manipulators, used for decommissioning tasks in the nuclear industry, lack proprioceptive sensors because electronics are vulnerable to radiation. Additionally, even if proprioceptive joint sensors could be retrofitted, such heavy-duty manipulators are often deployed on mobile vehicle platforms, which are significantly and erratically perturbed when powerful hydraulic drilling or cutting tools are deployed at the end-effector. In these scenarios, it would be beneficial to use external sensory information, e.g. vision, for estimating the robot configuration with respect to the scene or task. Conventional visual servoing methods typically rely on joint encoder values for controlling the robot. In contrast, our framework assumes that no joint encoders are available, and estimates the robot configuration by visually tracking several parts of the robot, and then enforcing equality between a set of transformation matrices which relate the frames of the camera, world and tracked robot parts. To accomplish this, we propose two alternative methods based on optimisation. We evaluate the performance of our developed framework by visually tracking the pose of a conventional robot arm, where the joint encoders are used to provide ground-truth for evaluating the precision of the vision system. Additionally, we evaluate the precision with which visual feedback can be used to control the robot's end-effector to follow a desired trajectory.
{"title":"Vision-guided state estimation and control of robotic manipulators which lack proprioceptive sensors","authors":"V. Ortenzi, Naresh Marturi, R. Stolkin, J. Kuo, M. Mistry","doi":"10.1109/IROS.2016.7759525","DOIUrl":"https://doi.org/10.1109/IROS.2016.7759525","url":null,"abstract":"This paper presents a vision-based approach for estimating the configuration of, and providing control signals for, an under-sensored robot manipulator using a single monocular camera. Some remote manipulators, used for decommissioning tasks in the nuclear industry, lack proprioceptive sensors because electronics are vulnerable to radiation. Additionally, even if proprioceptive joint sensors could be retrofitted, such heavy-duty manipulators are often deployed on mobile vehicle platforms, which are significantly and erratically perturbed when powerful hydraulic drilling or cutting tools are deployed at the end-effector. In these scenarios, it would be beneficial to use external sensory information, e.g. vision, for estimating the robot configuration with respect to the scene or task. Conventional visual servoing methods typically rely on joint encoder values for controlling the robot. In contrast, our framework assumes that no joint encoders are available, and estimates the robot configuration by visually tracking several parts of the robot, and then enforcing equality between a set of transformation matrices which relate the frames of the camera, world and tracked robot parts. To accomplish this, we propose two alternative methods based on optimisation. We evaluate the performance of our developed framework by visually tracking the pose of a conventional robot arm, where the joint encoders are used to provide ground-truth for evaluating the precision of the vision system. Additionally, we evaluate the precision with which visual feedback can be used to control the robot's end-effector to follow a desired trajectory.","PeriodicalId":296337,"journal":{"name":"2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","volume":"278 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127759776","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}
Pub Date : 2016-12-01DOI: 10.1109/IROS.2016.7759647
Yixing Gao, H. Chang, Y. Demiris
We propose an online iterative path optimisation method to enable a Baxter humanoid robot to assist human users to dress. The robot searches for the optimal personalised dressing path using vision and force sensor information: vision information is used to recognise the human pose and model the movement space of upper-body joints; force sensor information is used for the robot to detect external force resistance and to locally adjust its motion. We propose a new stochastic path optimisation method based on adaptive moment estimation. We first compare the proposed method with other path optimisation algorithms on synthetic data. Experimental results show that the performance of the method achieves the smallest error with fewer iterations and less computation time. We also evaluate real-world data by enabling the Baxter robot to assist real human users with their dressing.
{"title":"Iterative path optimisation for personalised dressing assistance using vision and force information","authors":"Yixing Gao, H. Chang, Y. Demiris","doi":"10.1109/IROS.2016.7759647","DOIUrl":"https://doi.org/10.1109/IROS.2016.7759647","url":null,"abstract":"We propose an online iterative path optimisation method to enable a Baxter humanoid robot to assist human users to dress. The robot searches for the optimal personalised dressing path using vision and force sensor information: vision information is used to recognise the human pose and model the movement space of upper-body joints; force sensor information is used for the robot to detect external force resistance and to locally adjust its motion. We propose a new stochastic path optimisation method based on adaptive moment estimation. We first compare the proposed method with other path optimisation algorithms on synthetic data. Experimental results show that the performance of the method achieves the smallest error with fewer iterations and less computation time. We also evaluate real-world data by enabling the Baxter robot to assist real human users with their dressing.","PeriodicalId":296337,"journal":{"name":"2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117216405","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}
Pub Date : 2016-12-01DOI: 10.1109/IROS.2017.8206147
Philippe LeBel, C. Gosselin, A. Campeau-Lecours
This paper presents an anticipative robot kinematic limitation avoidance algorithm for collaborative robots. The main objective is to improve the performance and the intuitivity of the physical human-robot interaction. One obstacle to achieve this goal is the management of limitations such as joint position limitation, singularities and collisions with the environment. Indeed, in addition to performing a given principal task, human users must pay a close attention to the manipulator configuration in order to handle the kinematic limitations. The proposed anticipative algorithm aims at relieving the human user from having to deal with such limitations. The algorithm is first presented and detailed for each individual limitation of a planar RR serial robot. The framework developed to manage several limitations occurring simultaneously is then presented. Finally, experiments are performed in order to assess the performance of the algorithm.
{"title":"An anticipative kinematic limitation avoidance algorithm for collaborative robots: Two-dimensional case","authors":"Philippe LeBel, C. Gosselin, A. Campeau-Lecours","doi":"10.1109/IROS.2017.8206147","DOIUrl":"https://doi.org/10.1109/IROS.2017.8206147","url":null,"abstract":"This paper presents an anticipative robot kinematic limitation avoidance algorithm for collaborative robots. The main objective is to improve the performance and the intuitivity of the physical human-robot interaction. One obstacle to achieve this goal is the management of limitations such as joint position limitation, singularities and collisions with the environment. Indeed, in addition to performing a given principal task, human users must pay a close attention to the manipulator configuration in order to handle the kinematic limitations. The proposed anticipative algorithm aims at relieving the human user from having to deal with such limitations. The algorithm is first presented and detailed for each individual limitation of a planar RR serial robot. The framework developed to manage several limitations occurring simultaneously is then presented. Finally, experiments are performed in order to assess the performance of the algorithm.","PeriodicalId":296337,"journal":{"name":"2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129710738","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}
Pub Date : 2016-12-01DOI: 10.1109/IROS.2016.7759107
Pengcheng Liu, Hongnian Yu, S. Cang
This paper studies modelling and dynamic analysis of underactuated capsule systems exhibiting friction-induced hysteresis. The motion mechanism is novel in utilizing internal centripetal torques generated by a vibration micro-motor mounted on the platform. Up to now, most investigations in frictional interactions towards capsule systems were confined into static or quasi-dynamic circumstance, where it is difficult to facilitate online use and control. It is the first time the dynamic frictional characteristics (non-reversible drooping and hysteresis) are studied towards these systems. An analytical study is primarily conducted to reveal the non-reversible characteristic for the static friction, the pre-sliding regime as well as the pure sliding regime, and the frictional limit boundaries are identified. Subsequently, the studies are mainly focused on dynamic analysis, including friction-driven vibrational responses and qualitative changes induced by control parameter (mass ratio) in capsule dynamics. It is found that the models predict periodic responses for the parameters considered and the average capsule velocity can be controlled through proper tuning of the control parameter around identified control points. The results demonstrate good captions of experimentally observed frictional characteristics, quenching of friction-induced vibrations and satisfaction of energy requirements.
{"title":"Modelling and dynamic analysis of underactuated capsule systems with friction-induced hysteresis","authors":"Pengcheng Liu, Hongnian Yu, S. Cang","doi":"10.1109/IROS.2016.7759107","DOIUrl":"https://doi.org/10.1109/IROS.2016.7759107","url":null,"abstract":"This paper studies modelling and dynamic analysis of underactuated capsule systems exhibiting friction-induced hysteresis. The motion mechanism is novel in utilizing internal centripetal torques generated by a vibration micro-motor mounted on the platform. Up to now, most investigations in frictional interactions towards capsule systems were confined into static or quasi-dynamic circumstance, where it is difficult to facilitate online use and control. It is the first time the dynamic frictional characteristics (non-reversible drooping and hysteresis) are studied towards these systems. An analytical study is primarily conducted to reveal the non-reversible characteristic for the static friction, the pre-sliding regime as well as the pure sliding regime, and the frictional limit boundaries are identified. Subsequently, the studies are mainly focused on dynamic analysis, including friction-driven vibrational responses and qualitative changes induced by control parameter (mass ratio) in capsule dynamics. It is found that the models predict periodic responses for the parameters considered and the average capsule velocity can be controlled through proper tuning of the control parameter around identified control points. The results demonstrate good captions of experimentally observed frictional characteristics, quenching of friction-induced vibrations and satisfaction of energy requirements.","PeriodicalId":296337,"journal":{"name":"2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123857160","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}
Pub Date : 2016-12-01DOI: 10.1109/IROS.2016.7759347
José Cano, Alejandro Bordallo, V. Nagarajan, S. Ramamoorthy, S. Vijayakumar
The performance of a ROS application is a function of the individual performance of its constituent nodes. Since ROS nodes are typically configurable (parameterised), the specific parameter values adopted will determine the level of performance generated. In addition, ROS applications may be distributed across multiple computation devices, thus providing different options for node allocation. We address two configuration problems that the typical ROS user is confronted with: i) Determining parameter values and node allocations for maximising performance; ii) Determining node allocations for minimising hardware resources that can guarantee the desired performance. We formalise these problems with a mathematical model, a constrained form of a multiple-choice multiple knapsack problem. We propose a greedy algorithm for optimising each problem, using linear regression for predicting the performance of an individual ROS node over a continuum set of parameter combinations. We evaluate the algorithms through simulation and we validate them in a real ROS scenario, showing that the expected performance levels only deviate from the real measurements by an average of 2.5%.
{"title":"Automatic configuration of ROS applications for near-optimal performance","authors":"José Cano, Alejandro Bordallo, V. Nagarajan, S. Ramamoorthy, S. Vijayakumar","doi":"10.1109/IROS.2016.7759347","DOIUrl":"https://doi.org/10.1109/IROS.2016.7759347","url":null,"abstract":"The performance of a ROS application is a function of the individual performance of its constituent nodes. Since ROS nodes are typically configurable (parameterised), the specific parameter values adopted will determine the level of performance generated. In addition, ROS applications may be distributed across multiple computation devices, thus providing different options for node allocation. We address two configuration problems that the typical ROS user is confronted with: i) Determining parameter values and node allocations for maximising performance; ii) Determining node allocations for minimising hardware resources that can guarantee the desired performance. We formalise these problems with a mathematical model, a constrained form of a multiple-choice multiple knapsack problem. We propose a greedy algorithm for optimising each problem, using linear regression for predicting the performance of an individual ROS node over a continuum set of parameter combinations. We evaluate the algorithms through simulation and we validate them in a real ROS scenario, showing that the expected performance levels only deviate from the real measurements by an average of 2.5%.","PeriodicalId":296337,"journal":{"name":"2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131122333","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}
Pub Date : 2016-12-01DOI: 10.1109/IROS.2016.7759752
E. Avci, Guang-Zhong Yang
In this paper, we propose manipulation ability extension of the optical tweezers by developing microhands, which are to use as end-effectors of the laser beam. First, three different 3D micro-scale handles are designed, then manufactured by the two-photon polymerization method with nano-scale resolution of 100 nm. Second, printed microhands are manipulated by multi-spot laser beam which traps and manipulates numerous objects simultaneously. Third, where direct trapping of the target object is not possible due to target objects' features such as size, shape, material, index of refraction, etc., indirect manipulation of the target microobjects is achieved by using the microhands as an extension of optical tweezers. Finally, three different microhand designs are compared in terms of speed and success rate. Furthermore, suitability of different shapes of microhandles against common usage of spherical shape is discussed.
{"title":"Development of a microhand using direct laser writing for indirect optical manipulation","authors":"E. Avci, Guang-Zhong Yang","doi":"10.1109/IROS.2016.7759752","DOIUrl":"https://doi.org/10.1109/IROS.2016.7759752","url":null,"abstract":"In this paper, we propose manipulation ability extension of the optical tweezers by developing microhands, which are to use as end-effectors of the laser beam. First, three different 3D micro-scale handles are designed, then manufactured by the two-photon polymerization method with nano-scale resolution of 100 nm. Second, printed microhands are manipulated by multi-spot laser beam which traps and manipulates numerous objects simultaneously. Third, where direct trapping of the target object is not possible due to target objects' features such as size, shape, material, index of refraction, etc., indirect manipulation of the target microobjects is achieved by using the microhands as an extension of optical tweezers. Finally, three different microhand designs are compared in terms of speed and success rate. Furthermore, suitability of different shapes of microhandles against common usage of spherical shape is discussed.","PeriodicalId":296337,"journal":{"name":"2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133270142","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}
Pub Date : 2016-12-01DOI: 10.1109/IROS.2016.7759582
Martina Zambelli, Y. Demiris
Although many tasks intrinsically involve multiple modalities, often only data from a single modality are used to improve complex robots acquisition of new skills. We present a method to equip robots with multimodal learning skills to achieve multimodal imitation on-the-fly on multiple concurrent task spaces, including vision, touch and proprioception, only using self-learned multimodal sensorimotor relations, without the need of solving inverse kinematic problems or explicit analytical models formulation. We evaluate the proposed method on a humanoid iCub robot learning to interact with a piano keyboard and imitating a human demonstration. Since no assumptions are made on the kinematic structure of the robot, the method can be also applied to different robotic platforms.
{"title":"Multimodal imitation using self-learned sensorimotor representations","authors":"Martina Zambelli, Y. Demiris","doi":"10.1109/IROS.2016.7759582","DOIUrl":"https://doi.org/10.1109/IROS.2016.7759582","url":null,"abstract":"Although many tasks intrinsically involve multiple modalities, often only data from a single modality are used to improve complex robots acquisition of new skills. We present a method to equip robots with multimodal learning skills to achieve multimodal imitation on-the-fly on multiple concurrent task spaces, including vision, touch and proprioception, only using self-learned multimodal sensorimotor relations, without the need of solving inverse kinematic problems or explicit analytical models formulation. We evaluate the proposed method on a humanoid iCub robot learning to interact with a piano keyboard and imitating a human demonstration. Since no assumptions are made on the kinematic structure of the robot, the method can be also applied to different robotic platforms.","PeriodicalId":296337,"journal":{"name":"2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133011782","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}
Pub Date : 2016-12-01DOI: 10.1109/IROS.2016.7759507
Johannes Wienke, S. Wrede
We present a novel fault detection method for application in component-based robotic systems. In contrast to existing work, our method specifically addresses faults in the software system of the robot using a data-driven methodology which exploits the inter-process communication of the system. This enables an application of the approach without expert knowledge or availability of complex software models. We specifically focus on performance bugs, which slowly degrade the performance of the system and are thereby harder to detect but also most valuable for automatic recovery. Using a data set recorded on a RoboCup@Home platform we demonstrate the performance and applicability of our method and analyze the types of faults that can be detected by the method.
{"title":"Autonomous fault detection for performance bugs in component-based robotic systems","authors":"Johannes Wienke, S. Wrede","doi":"10.1109/IROS.2016.7759507","DOIUrl":"https://doi.org/10.1109/IROS.2016.7759507","url":null,"abstract":"We present a novel fault detection method for application in component-based robotic systems. In contrast to existing work, our method specifically addresses faults in the software system of the robot using a data-driven methodology which exploits the inter-process communication of the system. This enables an application of the approach without expert knowledge or availability of complex software models. We specifically focus on performance bugs, which slowly degrade the performance of the system and are thereby harder to detect but also most valuable for automatic recovery. Using a data set recorded on a RoboCup@Home platform we demonstrate the performance and applicability of our method and analyze the types of faults that can be detected by the method.","PeriodicalId":296337,"journal":{"name":"2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125338708","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：