Pub Date : 2021-01-01DOI: 10.5220/0010607505140522
A. Yousaf, G. D. Caro
We consider scenarios where a mobile multi-robot system is used for mapping a spatial field. Gaussian processes are a widely employed regression model for this type of tasks. For the sake of generality, scalability, and robustness, we assume that planning and control are fully distributed and that robots can only communicate via range-limited channels. In such scenarios, one core challenge is how to let the robots efficiently coordinate in order to maintain a shared view of the mapping process, and, accordingly, make plans minimizing overlaps and optimizing joint information gain from obtained measurements. A simple approach of sharing and utilizing all the sampled data would not scale to large teams, neither for computation nor for communication (assuming a general ad hoc robot network). Building on previous work where robots adaptively plan where to sample data by selecting convex containment regions, we propose a data sharing and assimilation strategy which aims to minimize the impact on communication and computation while minimizing the loss on accuracy in map estimation. The strategy exploits convexity of the regions to create compact meta-data that are locally shared. Submodularity of information processes and properties of GPs are used by the robots to create highly informative summaries of the sampled regions, that are shared on-demand based on the meta-data. In turn, a received summary is assimilated by a robot into its local GP only if/when needed. We perform a number of studies in simulation using real data from bathymetric maps to show the efficacy of the strategy for supporting scalability of computations and communications while guaranteeing learning accurate maps.
{"title":"Data Sharing and Assimilation in Multi-Robot Systems for Environment Mapping","authors":"A. Yousaf, G. D. Caro","doi":"10.5220/0010607505140522","DOIUrl":"https://doi.org/10.5220/0010607505140522","url":null,"abstract":"We consider scenarios where a mobile multi-robot system is used for mapping a spatial field. Gaussian processes are a widely employed regression model for this type of tasks. For the sake of generality, scalability, and robustness, we assume that planning and control are fully distributed and that robots can only communicate via range-limited channels. In such scenarios, one core challenge is how to let the robots efficiently coordinate in order to maintain a shared view of the mapping process, and, accordingly, make plans minimizing overlaps and optimizing joint information gain from obtained measurements. A simple approach of sharing and utilizing all the sampled data would not scale to large teams, neither for computation nor for communication (assuming a general ad hoc robot network). Building on previous work where robots adaptively plan where to sample data by selecting convex containment regions, we propose a data sharing and assimilation strategy which aims to minimize the impact on communication and computation while minimizing the loss on accuracy in map estimation. The strategy exploits convexity of the regions to create compact meta-data that are locally shared. Submodularity of information processes and properties of GPs are used by the robots to create highly informative summaries of the sampled regions, that are shared on-demand based on the meta-data. In turn, a received summary is assimilated by a robot into its local GP only if/when needed. We perform a number of studies in simulation using real data from bathymetric maps to show the efficacy of the strategy for supporting scalability of computations and communications while guaranteeing learning accurate maps.","PeriodicalId":6436,"journal":{"name":"2010 2nd International Asia Conference on Informatics in Control, Automation and Robotics (CAR 2010)","volume":"10 1","pages":"514-522"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80840859","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 : 2021-01-01DOI: 10.5220/0010581600900098
Lukas Markolf, O. Stursberg
This work considers (deep) artificial feed-forward neural networks as parametric approximators in optimal control of discrete-time switched linear systems with controlled switching. The proposed approach is based on approximate dynamic programming and allows the fast computation of (sub-)optimal discrete and continuous control inputs, either by approximating the optimal cost-to-go functions or by approximating the optimal discrete and continuous input policies. An important property of the approach is the satisfaction of polytopic state and input constraints, which is crucial for ensuring safety, as required in many control applications. A numeric example is provided for illustration and evaluation of the approaches.
{"title":"Learning-based Optimal Control of Constrained Switched Linear Systems using Neural Networks","authors":"Lukas Markolf, O. Stursberg","doi":"10.5220/0010581600900098","DOIUrl":"https://doi.org/10.5220/0010581600900098","url":null,"abstract":"This work considers (deep) artificial feed-forward neural networks as parametric approximators in optimal control of discrete-time switched linear systems with controlled switching. The proposed approach is based on approximate dynamic programming and allows the fast computation of (sub-)optimal discrete and continuous control inputs, either by approximating the optimal cost-to-go functions or by approximating the optimal discrete and continuous input policies. An important property of the approach is the satisfaction of polytopic state and input constraints, which is crucial for ensuring safety, as required in many control applications. A numeric example is provided for illustration and evaluation of the approaches.","PeriodicalId":6436,"journal":{"name":"2010 2nd International Asia Conference on Informatics in Control, Automation and Robotics (CAR 2010)","volume":"4 1","pages":"90-98"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88716198","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 : 2021-01-01DOI: 10.5220/0010543106610668
Yasmine Sheila Antille, Etienne Gubler, J. Gruber
: In this paper a Ground Speed Measuring System which can measure the ground speed over the ground in three dimensions is proposed. The system uses two Kalman filters to compute the final ground speed based on the readings from its various sensors. The proposed solution combines state of the art techniques from different fields of sensor technology and will be incorporated into the high-performance driverless vehicle after completion of this project. The findings and learnings of developing this system are discussed and an evaluation of the module is presented. In the end, the system can accurately estimate a test vehicle’s ground speed during system field tests.
{"title":"Ground Speed Measuring System for Autonomous Vehicles","authors":"Yasmine Sheila Antille, Etienne Gubler, J. Gruber","doi":"10.5220/0010543106610668","DOIUrl":"https://doi.org/10.5220/0010543106610668","url":null,"abstract":": In this paper a Ground Speed Measuring System which can measure the ground speed over the ground in three dimensions is proposed. The system uses two Kalman filters to compute the final ground speed based on the readings from its various sensors. The proposed solution combines state of the art techniques from different fields of sensor technology and will be incorporated into the high-performance driverless vehicle after completion of this project. The findings and learnings of developing this system are discussed and an evaluation of the module is presented. In the end, the system can accurately estimate a test vehicle’s ground speed during system field tests.","PeriodicalId":6436,"journal":{"name":"2010 2nd International Asia Conference on Informatics in Control, Automation and Robotics (CAR 2010)","volume":"35 1","pages":"661-668"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85357857","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 : 2021-01-01DOI: 10.5220/0010572905920599
P. Giesl, S. Hafstein, I. Mehrabinezhad
We study contraction metrics computed for dynamical systems with periodic orbits using generalized interpolation with radial basis functions. The robustness of the metric with respect to perturbations of the system is proved and demonstrated for two examples from the literature.
{"title":"Robustness of Contraction Metrics Computed by Radial Basis Functions","authors":"P. Giesl, S. Hafstein, I. Mehrabinezhad","doi":"10.5220/0010572905920599","DOIUrl":"https://doi.org/10.5220/0010572905920599","url":null,"abstract":"We study contraction metrics computed for dynamical systems with periodic orbits using generalized interpolation with radial basis functions. The robustness of the metric with respect to perturbations of the system is proved and demonstrated for two examples from the literature.","PeriodicalId":6436,"journal":{"name":"2010 2nd International Asia Conference on Informatics in Control, Automation and Robotics (CAR 2010)","volume":"1 1","pages":"592-599"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89229564","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 : 2021-01-01DOI: 10.5220/0010616405370544
Aguirre Santiago, L. Solaque, Alexandra Velasco
: Crop disease detection in precision agriculture has an important impact on farming, improving production, and reducing economic losses. This is why some efforts have been done in this direction. This paper compares 4 object detection algorithms based on deep learning to detect diseases in strawberry crops. Here, we present a step towards detecting the most common diseases to prevent economical losses. The main purpose is to detect mainly three diseases of the strawberry crops, i.e. Botrytis cinerea, Leaf scorch, and Powdery mildew, to take further actions if the crops are unhealthy. We have chosen these three diseases because these are frequent and unpredictable issues, and the risk of infection is high. For this, we trained four algorithms, two based on Single Shot MultiBox Detector and two based on EfficientDet algorithm. We focus the analysis on the two best results based on the mean average precision. We have used Google colab for training, then a Core i5 host computer and an Nvidia Jetson nano were used for testing. We have achieved a detection network with a mean average precision of 81% in the best case, in detecting the three proposed classes. While using an NVIDIA Jetson nano, the accuracy increases up to 86% due to the dedicated GPU that processes Convolutional Neural Networks(CNN).
{"title":"Strawberry Disease Detection in Precision Agriculture","authors":"Aguirre Santiago, L. Solaque, Alexandra Velasco","doi":"10.5220/0010616405370544","DOIUrl":"https://doi.org/10.5220/0010616405370544","url":null,"abstract":": Crop disease detection in precision agriculture has an important impact on farming, improving production, and reducing economic losses. This is why some efforts have been done in this direction. This paper compares 4 object detection algorithms based on deep learning to detect diseases in strawberry crops. Here, we present a step towards detecting the most common diseases to prevent economical losses. The main purpose is to detect mainly three diseases of the strawberry crops, i.e. Botrytis cinerea, Leaf scorch, and Powdery mildew, to take further actions if the crops are unhealthy. We have chosen these three diseases because these are frequent and unpredictable issues, and the risk of infection is high. For this, we trained four algorithms, two based on Single Shot MultiBox Detector and two based on EfficientDet algorithm. We focus the analysis on the two best results based on the mean average precision. We have used Google colab for training, then a Core i5 host computer and an Nvidia Jetson nano were used for testing. We have achieved a detection network with a mean average precision of 81% in the best case, in detecting the three proposed classes. While using an NVIDIA Jetson nano, the accuracy increases up to 86% due to the dedicated GPU that processes Convolutional Neural Networks(CNN).","PeriodicalId":6436,"journal":{"name":"2010 2nd International Asia Conference on Informatics in Control, Automation and Robotics (CAR 2010)","volume":"62 1","pages":"537-544"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77920260","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 : 2021-01-01DOI: 10.5220/0010548304030409
Mattia Antonelli, E. Digo, S. Pastorelli, L. Gastaldi
The automation of human gestures is gaining increasing importance in manufacturing. Indeed, robots support operators by simplifying their tasks in a shared workspace. However, human-robot collaboration can be improved by identifying human actions and then developing adaptive control algorithms for the robot. Accordingly, the aim of this study was to classify industrial tasks based on accelerations signals of human upper limbs. Two magnetic inertial measurement units (MIMUs) on the upper limb of ten healthy young subjects acquired pick and place gestures at three different heights. Peaks were detected from MIMUs accelerations and were adopted to classify gestures through a Linear Discriminant Analysis. The method was applied firstly including two MIMUs and then one at a time. Results demonstrated that the placement of at least one MIMU on the upper arm or forearm is suitable to achieve good recognition performances. Overall, features extracted from MIMUs signals can be used to define and train a prediction algorithm reliable for the context of collaborative robotics.
{"title":"Wearable MIMUs for the Identification of Upper Limbs Motion in an Industrial Context of Human-Robot Interaction","authors":"Mattia Antonelli, E. Digo, S. Pastorelli, L. Gastaldi","doi":"10.5220/0010548304030409","DOIUrl":"https://doi.org/10.5220/0010548304030409","url":null,"abstract":"The automation of human gestures is gaining increasing importance in manufacturing. Indeed, robots support operators by simplifying their tasks in a shared workspace. However, human-robot collaboration can be improved by identifying human actions and then developing adaptive control algorithms for the robot. Accordingly, the aim of this study was to classify industrial tasks based on accelerations signals of human upper limbs. Two magnetic inertial measurement units (MIMUs) on the upper limb of ten healthy young subjects acquired pick and place gestures at three different heights. Peaks were detected from MIMUs accelerations and were adopted to classify gestures through a Linear Discriminant Analysis. The method was applied firstly including two MIMUs and then one at a time. Results demonstrated that the placement of at least one MIMU on the upper arm or forearm is suitable to achieve good recognition performances. Overall, features extracted from MIMUs signals can be used to define and train a prediction algorithm reliable for the context of collaborative robotics.","PeriodicalId":6436,"journal":{"name":"2010 2nd International Asia Conference on Informatics in Control, Automation and Robotics (CAR 2010)","volume":"559 1","pages":"403-409"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74712191","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 : 2021-01-01DOI: 10.5220/0010639100110023
M. Broucke
We survey recent results on the use of regulator theory in neuroscience, particularly to model the contribution of the cerebellum to motor systems. Based on our study of the slow eye movement systems as well as visuomotor adaptation, several themes emerge, including a promising structural model of the cerebellum, and insights on how the cerebellum may enable and disable internal models. Implications for robotics are discussed at the
{"title":"On the Use of Regulator Theory in Neuroscience with Implications for Robotics","authors":"M. Broucke","doi":"10.5220/0010639100110023","DOIUrl":"https://doi.org/10.5220/0010639100110023","url":null,"abstract":"We survey recent results on the use of regulator theory in neuroscience, particularly to model the contribution of the cerebellum to motor systems. Based on our study of the slow eye movement systems as well as visuomotor adaptation, several themes emerge, including a promising structural model of the cerebellum, and insights on how the cerebellum may enable and disable internal models. Implications for robotics are discussed at the","PeriodicalId":6436,"journal":{"name":"2010 2nd International Asia Conference on Informatics in Control, Automation and Robotics (CAR 2010)","volume":"127 1","pages":"11-23"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85398297","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 : 2021-01-01DOI: 10.5220/0010518303830387
Youssef Bouaziz, E. Royer, Guillaume Bresson, M. Dhome
This paper presents a new challenging dataset for autonomous driving applications: Institut Pascal Long-Term — IPLT — Dataset which was collected over two years and it contains, at the moment, 127 sequences and it still growing. This dataset has been captured in a parking lot where our experimental vehicle has followed the same path with slight lateral and angular deviations while we made sure to incorporate various environmental conditions caused by luminance, weather, seasonal changes.
{"title":"Over Two Years of Challenging Environmental Conditions for Localization: The IPLT Dataset","authors":"Youssef Bouaziz, E. Royer, Guillaume Bresson, M. Dhome","doi":"10.5220/0010518303830387","DOIUrl":"https://doi.org/10.5220/0010518303830387","url":null,"abstract":"This paper presents a new challenging dataset for autonomous driving applications: Institut Pascal Long-Term — IPLT — Dataset which was collected over two years and it contains, at the moment, 127 sequences and it still growing. This dataset has been captured in a parking lot where our experimental vehicle has followed the same path with slight lateral and angular deviations while we made sure to incorporate various environmental conditions caused by luminance, weather, seasonal changes.","PeriodicalId":6436,"journal":{"name":"2010 2nd International Asia Conference on Informatics in Control, Automation and Robotics (CAR 2010)","volume":"36 1","pages":"383-387"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81563467","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 : 2021-01-01DOI: 10.5220/0010559602900300
Anderson Mozart, Gabriel Moraes, Rânik Guidolini, Vinicius B. Cardoso, Thiago Oliveira-Santos, A. D. Souza, C. Badue
We present a path planner for unstructured urban environments (PPUE) for self-driving cars. PPUE receives initial and goal poses as input, as well as maps of the environment. It employs a hybrid A* algorithm with two heuristics for generating paths, which are smoothed using Conjugate Gradient optimization. Different from previous works, PPUE uses: (i) an obstacle distance grid-map, instead of an occupancy grid-map, for representing the environment; and (ii) an accurate but simple collision model of the car. We have examined PPUE’s performance experimentally in simulated and real world scenarios. Our results show that PPUE computes smooth and safe paths, which follow the kinematic constraints of the vehicle, fast enough for suitable real world operation. * Senior Member, IEEE
{"title":"Path Planning in Unstructured Urban Environments for Self-driving Cars","authors":"Anderson Mozart, Gabriel Moraes, Rânik Guidolini, Vinicius B. Cardoso, Thiago Oliveira-Santos, A. D. Souza, C. Badue","doi":"10.5220/0010559602900300","DOIUrl":"https://doi.org/10.5220/0010559602900300","url":null,"abstract":"We present a path planner for unstructured urban environments (PPUE) for self-driving cars. PPUE receives initial and goal poses as input, as well as maps of the environment. It employs a hybrid A* algorithm with two heuristics for generating paths, which are smoothed using Conjugate Gradient optimization. Different from previous works, PPUE uses: (i) an obstacle distance grid-map, instead of an occupancy grid-map, for representing the environment; and (ii) an accurate but simple collision model of the car. We have examined PPUE’s performance experimentally in simulated and real world scenarios. Our results show that PPUE computes smooth and safe paths, which follow the kinematic constraints of the vehicle, fast enough for suitable real world operation. * Senior Member, IEEE","PeriodicalId":6436,"journal":{"name":"2010 2nd International Asia Conference on Informatics in Control, Automation and Robotics (CAR 2010)","volume":"12 1","pages":"290-300"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82413642","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：