Pub Date : 2017-09-01DOI: 10.1109/IROS.2017.8205950
Alexandre Ambiehl, S. Garnier, Kévin Subrin, B. Furet
In order to be able to perform complex and arduous tasks, stiffness articular identification of industrial robots is a current approach to predict the deflection under static or dynamic loading. Manufacturers propose new features to take the loading into account and a new generation of industrial robot equiped with double encoding systems are proposed. However, current methods brings some drawbacks when the ratio between the stiffness arm and the wrist one is too high. In this paper, we propose a new approach to take this aspect into account by decoupling the arm identification and the wrist one. We compare then our method regarding two current methods and applied it on this new industrial robot. The results highligh the stability and the quality of the stiffness articular estimation with and without activating the double encoding system. On our data, we are able to take into account 84% of the global deflection.
{"title":"New method for decoupling the articular stiffness identification: Application to an industrial robot with double encoding system on its 3 first axis","authors":"Alexandre Ambiehl, S. Garnier, Kévin Subrin, B. Furet","doi":"10.1109/IROS.2017.8205950","DOIUrl":"https://doi.org/10.1109/IROS.2017.8205950","url":null,"abstract":"In order to be able to perform complex and arduous tasks, stiffness articular identification of industrial robots is a current approach to predict the deflection under static or dynamic loading. Manufacturers propose new features to take the loading into account and a new generation of industrial robot equiped with double encoding systems are proposed. However, current methods brings some drawbacks when the ratio between the stiffness arm and the wrist one is too high. In this paper, we propose a new approach to take this aspect into account by decoupling the arm identification and the wrist one. We compare then our method regarding two current methods and applied it on this new industrial robot. The results highligh the stability and the quality of the stiffness articular estimation with and without activating the double encoding system. On our data, we are able to take into account 84% of the global deflection.","PeriodicalId":6658,"journal":{"name":"2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","volume":"22 1","pages":"1478-1483"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78301955","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 : 2017-09-01DOI: 10.1109/IROS.2017.8206268
G. Bledt, Patrick M. Wensing, Sangbae Kim
This paper introduces a new policy-regularized model-predictive control (PR-MPC) approach to automatically generate and stabilize a diverse set of quadrupedal gaits. Model-predictive methods offer great promise to address balance in dynamic robots, yet require the solution of challenging nonlinear optimization problems when applied to legged systems. The new proposed PR-MPC approach aims to improve the conditioning of these problems by adding regularization based on heuristic reference policies. With this approach, a unified MPC formulation is shown to generate and stabilize trotting, bounding, and galloping without retuning any cost-function parameters. Intuitively, the added regularization biases the solution of the MPC towards common heuristics from the literature that are based on simple physics. Simulation results show that PR-MPC improves the computation time and closed-loop outcomes of applying MPC to stabilize quadrupedal gaits.
{"title":"Policy-regularized model predictive control to stabilize diverse quadrupedal gaits for the MIT cheetah","authors":"G. Bledt, Patrick M. Wensing, Sangbae Kim","doi":"10.1109/IROS.2017.8206268","DOIUrl":"https://doi.org/10.1109/IROS.2017.8206268","url":null,"abstract":"This paper introduces a new policy-regularized model-predictive control (PR-MPC) approach to automatically generate and stabilize a diverse set of quadrupedal gaits. Model-predictive methods offer great promise to address balance in dynamic robots, yet require the solution of challenging nonlinear optimization problems when applied to legged systems. The new proposed PR-MPC approach aims to improve the conditioning of these problems by adding regularization based on heuristic reference policies. With this approach, a unified MPC formulation is shown to generate and stabilize trotting, bounding, and galloping without retuning any cost-function parameters. Intuitively, the added regularization biases the solution of the MPC towards common heuristics from the literature that are based on simple physics. Simulation results show that PR-MPC improves the computation time and closed-loop outcomes of applying MPC to stabilize quadrupedal gaits.","PeriodicalId":6658,"journal":{"name":"2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","volume":"15 1","pages":"4102-4109"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78320529","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 : 2017-09-01DOI: 10.1109/IROS.2017.8206215
Bai Li, Youmin Zhang, Yuming Ge, Zhijiang Shao, Pu Li
This work formulates the multi-vehicle lane change motion planning task as a centralized optimal control problem, which is beneficial in being generic and complete. However, a direct solution to this optimal control problem is numerically intractable due to the dimensionality of the collision-avoidance constraints and nonlinearity of the vehicle kinematics. A progressively constrained dynamic optimization (PCDO) method is proposed to facilitate the numerical solving process of this complicated problem. PCDO guarantees to efficiently obtain an optimum to the original optimal control problem via solving a sequence of simplified problems which gradually judge and reserve only the active collision-avoidance constraints. A first-regularization-then-action strategy, together with the look-up table technique, is developed for online solutions. At the regularization stage, the vehicles form a standard formation by linear acceleration/deceleration only. At the action stage, the vehicles execute lane change motions computed offline and recorded in the look-up table. This makes online motion planning feasible because 1) the computational complexity at the regularization stage scales linearly rather than exponentially with the vehicle number; and 2) online computation at the action stage is fully avoided through data extraction from the look-up table.
{"title":"Optimal control-based online motion planning for cooperative lane changes of connected and automated vehicles","authors":"Bai Li, Youmin Zhang, Yuming Ge, Zhijiang Shao, Pu Li","doi":"10.1109/IROS.2017.8206215","DOIUrl":"https://doi.org/10.1109/IROS.2017.8206215","url":null,"abstract":"This work formulates the multi-vehicle lane change motion planning task as a centralized optimal control problem, which is beneficial in being generic and complete. However, a direct solution to this optimal control problem is numerically intractable due to the dimensionality of the collision-avoidance constraints and nonlinearity of the vehicle kinematics. A progressively constrained dynamic optimization (PCDO) method is proposed to facilitate the numerical solving process of this complicated problem. PCDO guarantees to efficiently obtain an optimum to the original optimal control problem via solving a sequence of simplified problems which gradually judge and reserve only the active collision-avoidance constraints. A first-regularization-then-action strategy, together with the look-up table technique, is developed for online solutions. At the regularization stage, the vehicles form a standard formation by linear acceleration/deceleration only. At the action stage, the vehicles execute lane change motions computed offline and recorded in the look-up table. This makes online motion planning feasible because 1) the computational complexity at the regularization stage scales linearly rather than exponentially with the vehicle number; and 2) online computation at the action stage is fully avoided through data extraction from the look-up table.","PeriodicalId":6658,"journal":{"name":"2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","volume":"8 12 1","pages":"3689-3694"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78490415","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}
Accurate specification and rigorous analysis of Jacobian matrix are indispensable to guarantee correct evaluation on the manipulator kinematics performance. In this paper, a formal analysis method of the Jacobian matrix in the screw theory is presented by using the higher-order logic theorem prover HOL4. Formalizations of twists and the forward kinematics are characterized with the product of exponential formula and the theory of functional matrices. To the best of our knowledge, this work is the first to formally reason about the spatial Jacobian using theorem proving. The formal modeling and analysis of a 3-DOF planar manipulator substantiate the effectiveness and applicability of the proposed approach to formally verify the kinematics properties of manipulator.
{"title":"Formalization and analysis of jacobian matrix in screw theory and its application in kinematic singularity","authors":"Aixuan Wu, Zhiping Shi, Xiumei Yang, Yong Guan, Yongdong Li, Xiaoyu Song","doi":"10.1109/IROS.2017.8206115","DOIUrl":"https://doi.org/10.1109/IROS.2017.8206115","url":null,"abstract":"Accurate specification and rigorous analysis of Jacobian matrix are indispensable to guarantee correct evaluation on the manipulator kinematics performance. In this paper, a formal analysis method of the Jacobian matrix in the screw theory is presented by using the higher-order logic theorem prover HOL4. Formalizations of twists and the forward kinematics are characterized with the product of exponential formula and the theory of functional matrices. To the best of our knowledge, this work is the first to formally reason about the spatial Jacobian using theorem proving. The formal modeling and analysis of a 3-DOF planar manipulator substantiate the effectiveness and applicability of the proposed approach to formally verify the kinematics properties of manipulator.","PeriodicalId":6658,"journal":{"name":"2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","volume":"589 1","pages":"2835-2842"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77825924","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 : 2017-09-01DOI: 10.1109/IROS.2017.8202273
Kenta Murakami, S. John, Mayumi Komatsu, S. Adachi
In this paper, we control the walking direction of a subject using an assistive robotic device for the first time, using the internal/external rotation hip torque generated by our cross-wire assist suit to induce turning gait. The cross-wire assist device is a soft exosuit with four independently controllable actuators located around at hip joint, and selective actuation allows for the generation of internal/external rotational torque. Turning was most effectively induced using external rotation for the inside leg and internal rotation for the outside leg, which is a combination of human step turning strategy and ‘ipsilateral crossover’ spin turning strategy. The degree of turning increased with applied force level, and multi-subject testing showed that the walking direction all subjects were capable of being modified (average 16.2 degree/m for 80 N); however, there was large variation between subjects.
{"title":"External control of walking direction, using cross-wire mobile assist suit","authors":"Kenta Murakami, S. John, Mayumi Komatsu, S. Adachi","doi":"10.1109/IROS.2017.8202273","DOIUrl":"https://doi.org/10.1109/IROS.2017.8202273","url":null,"abstract":"In this paper, we control the walking direction of a subject using an assistive robotic device for the first time, using the internal/external rotation hip torque generated by our cross-wire assist suit to induce turning gait. The cross-wire assist device is a soft exosuit with four independently controllable actuators located around at hip joint, and selective actuation allows for the generation of internal/external rotational torque. Turning was most effectively induced using external rotation for the inside leg and internal rotation for the outside leg, which is a combination of human step turning strategy and ‘ipsilateral crossover’ spin turning strategy. The degree of turning increased with applied force level, and multi-subject testing showed that the walking direction all subjects were capable of being modified (average 16.2 degree/m for 80 N); however, there was large variation between subjects.","PeriodicalId":6658,"journal":{"name":"2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","volume":"33 Suppl 1 1","pages":"1046-1051"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77927288","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 : 2017-09-01DOI: 10.1109/IROS.2017.8206496
M. Abdeetedal, M. Kermani
This paper deals with the problem of purposefully failing or yielding an object by a robotic gripper. We propose a grasp quality measure fabricated for robotic harvesting in which picking a crop from its stem is desired. The proposed metric characterizes a suitable grasp configuration for systematically controlling the failure behavior of an object to break it at the desired location while avoiding damage on other areas. Our approach is based on failure task information and gripper wrench insertion capability. Failure task definition is accomplished using failure theories. Gripper wrench insertion capability is formulated by modeling the friction between the object and gripper. A new method inspired by human pre-manipulation process is introduced to utilize gripper itself as a friction measurement device. The provided friction model is capable of handling the anisotropic behavior of materials which is the case for fruits and vegetables. The evaluation method is formulated as a quasistatic grasp problem. Additionally, the general case of both fully-actuated and under-actuated grippers are considered. As a validation of the proposed evaluation method, experimental results for failing parts using Kuka Light-Weight Robot IV robot are presented.
{"title":"Grasp evaluation method for applying static loads leading to beam failure","authors":"M. Abdeetedal, M. Kermani","doi":"10.1109/IROS.2017.8206496","DOIUrl":"https://doi.org/10.1109/IROS.2017.8206496","url":null,"abstract":"This paper deals with the problem of purposefully failing or yielding an object by a robotic gripper. We propose a grasp quality measure fabricated for robotic harvesting in which picking a crop from its stem is desired. The proposed metric characterizes a suitable grasp configuration for systematically controlling the failure behavior of an object to break it at the desired location while avoiding damage on other areas. Our approach is based on failure task information and gripper wrench insertion capability. Failure task definition is accomplished using failure theories. Gripper wrench insertion capability is formulated by modeling the friction between the object and gripper. A new method inspired by human pre-manipulation process is introduced to utilize gripper itself as a friction measurement device. The provided friction model is capable of handling the anisotropic behavior of materials which is the case for fruits and vegetables. The evaluation method is formulated as a quasistatic grasp problem. Additionally, the general case of both fully-actuated and under-actuated grippers are considered. As a validation of the proposed evaluation method, experimental results for failing parts using Kuka Light-Weight Robot IV robot are presented.","PeriodicalId":6658,"journal":{"name":"2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","volume":"4 1","pages":"5999-6004"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73175479","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 : 2017-09-01DOI: 10.1109/IROS.2017.8206512
Hafez Farazi, Sven Behnke
Collaborative robots working on a common task are necessary for many applications. One of the challenges for achieving collaboration in a team of robots is mutual tracking and identification. We present a novel pipeline for online vision-based detection, tracking and identification of robots with a known and identical appearance. Our method runs in realtime on the limited hardware of the observer robot. Unlike previous works addressing robot tracking and identification, we use a data-driven approach based on recurrent neural networks to learn relations between sequential inputs and outputs. We formulate the data association problem as multiple classification problems. A deep LSTM network was trained on a simulated dataset and fine-tuned on small set of real data. Experiments on two challenging datasets, one synthetic and one real, which include long-term occlusions, show promising results.
{"title":"Online visual robot tracking and identification using deep LSTM networks","authors":"Hafez Farazi, Sven Behnke","doi":"10.1109/IROS.2017.8206512","DOIUrl":"https://doi.org/10.1109/IROS.2017.8206512","url":null,"abstract":"Collaborative robots working on a common task are necessary for many applications. One of the challenges for achieving collaboration in a team of robots is mutual tracking and identification. We present a novel pipeline for online vision-based detection, tracking and identification of robots with a known and identical appearance. Our method runs in realtime on the limited hardware of the observer robot. Unlike previous works addressing robot tracking and identification, we use a data-driven approach based on recurrent neural networks to learn relations between sequential inputs and outputs. We formulate the data association problem as multiple classification problems. A deep LSTM network was trained on a simulated dataset and fine-tuned on small set of real data. Experiments on two challenging datasets, one synthetic and one real, which include long-term occlusions, show promising results.","PeriodicalId":6658,"journal":{"name":"2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","volume":"13 1","pages":"6118-6125"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73415589","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 : 2017-09-01DOI: 10.1109/IROS.2017.8206469
L. Porzi, Adrián Peñate Sánchez, E. Ricci, F. Moreno-Noguer
Most recent approaches to 3D pose estimation from RGB-D images address the problem in a two-stage pipeline. First, they learn a classifier-typically a random forest-to predict the position of each input pixel on the object surface. These estimates are then used to define an energy function that is minimized w.r.t. the object pose. In this paper, we focus on the first stage of the problem and propose a novel classifier based on a depth-aware Convolutional Neural Network. This classifier is able to learn a scale-adaptive regression model that yields very accurate pixel-level predictions, allowing to finally estimate the pose using a simple RANSAC-based scheme, with no need to optimize complex ad hoc energy functions. Our experiments on publicly available datasets show that our approach achieves remarkable improvements over state-of-the-art methods.
{"title":"Depth-aware convolutional neural networks for accurate 3D pose estimation in RGB-D images","authors":"L. Porzi, Adrián Peñate Sánchez, E. Ricci, F. Moreno-Noguer","doi":"10.1109/IROS.2017.8206469","DOIUrl":"https://doi.org/10.1109/IROS.2017.8206469","url":null,"abstract":"Most recent approaches to 3D pose estimation from RGB-D images address the problem in a two-stage pipeline. First, they learn a classifier-typically a random forest-to predict the position of each input pixel on the object surface. These estimates are then used to define an energy function that is minimized w.r.t. the object pose. In this paper, we focus on the first stage of the problem and propose a novel classifier based on a depth-aware Convolutional Neural Network. This classifier is able to learn a scale-adaptive regression model that yields very accurate pixel-level predictions, allowing to finally estimate the pose using a simple RANSAC-based scheme, with no need to optimize complex ad hoc energy functions. Our experiments on publicly available datasets show that our approach achieves remarkable improvements over state-of-the-art methods.","PeriodicalId":6658,"journal":{"name":"2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","volume":"1 1","pages":"5777-5783"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76709434","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 : 2017-09-01DOI: 10.1109/IROS.2017.8206265
R. Inoue, V. Guizilini, M. Terra, F. Ramos
Visual-Inertial SLAM methods have become a very important technology for several applications in robotics. This kind of approach usually is composed by sensors as rate gyros, accelerometers and monocular cameras. Magnetometers and GPS modules generally used for outdoors are absent in the SLAM system observation, since the magnetometer measurements deteriorate in the presence of ferromagnetic materials and the GPS module signals are unavailable indoors or in urban environments. In order to make use of all these sensors, we propose Markovian jump linear systems (MJLS) to model the modes of operation of the navigation system based on available sensors and their reliability. An extended Kalman filter for MJLS fuses the sensor data and estimates the motion using the best mode of operation for each particular time instant. Experimental results are presented to show the effectiveness of the proposed method, in situations that would pose a challenge for standard data fusion techniques.
{"title":"Markovian jump linear systems-based filtering for visual and GPS aided inertial navigation system","authors":"R. Inoue, V. Guizilini, M. Terra, F. Ramos","doi":"10.1109/IROS.2017.8206265","DOIUrl":"https://doi.org/10.1109/IROS.2017.8206265","url":null,"abstract":"Visual-Inertial SLAM methods have become a very important technology for several applications in robotics. This kind of approach usually is composed by sensors as rate gyros, accelerometers and monocular cameras. Magnetometers and GPS modules generally used for outdoors are absent in the SLAM system observation, since the magnetometer measurements deteriorate in the presence of ferromagnetic materials and the GPS module signals are unavailable indoors or in urban environments. In order to make use of all these sensors, we propose Markovian jump linear systems (MJLS) to model the modes of operation of the navigation system based on available sensors and their reliability. An extended Kalman filter for MJLS fuses the sensor data and estimates the motion using the best mode of operation for each particular time instant. Experimental results are presented to show the effectiveness of the proposed method, in situations that would pose a challenge for standard data fusion techniques.","PeriodicalId":6658,"journal":{"name":"2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","volume":"26 1","pages":"4083-4089"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76727491","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 : 2017-09-01DOI: 10.1109/IROS.2017.8206609
Tolga Birdal, Slobodan Ilic
We present a 3D mesh re-sampling algorithm, carefully tailored for 3D object detection using point pair features (PPF). Computing a sparse representation of objects is critical for the success of state-of-the-art object detection, recognition and pose estimation methods. Yet, sparsity needs to preserve fidelity. To this end, we develop a simple, yet very effective point sampling strategy for detection of any CAD model through geometric hashing. Our approach relies on rendering the object coordinates from a set of views evenly distributed on a sphere. Actual sampling takes place on 2D domain over these renderings; the resulting samples are efficiently merged in 3D with the aid of a special voxel structure and relaxed with Lloyd iterations. The generated vertices are not concentrated only on critical points, as in many keypoint extraction algorithms, and there is even spacing between selected vertices. This is valuable for quantization based detection methods, such as geometric hashing of point pair features. The algorithm is fast and can easily handle the elongated/acute triangles and sharp edges typically existent in industrial CAD models, while automatically pruning the invisible structures. We do not introduce structural changes such as smoothing or interpolation and sample the normals on the original CAD model, achieving the maximum fidelity. We demonstrate the strength of this approach on 3D object detection in comparison to similar sampling algorithms.
{"title":"A point sampling algorithm for 3D matching of irregular geometries","authors":"Tolga Birdal, Slobodan Ilic","doi":"10.1109/IROS.2017.8206609","DOIUrl":"https://doi.org/10.1109/IROS.2017.8206609","url":null,"abstract":"We present a 3D mesh re-sampling algorithm, carefully tailored for 3D object detection using point pair features (PPF). Computing a sparse representation of objects is critical for the success of state-of-the-art object detection, recognition and pose estimation methods. Yet, sparsity needs to preserve fidelity. To this end, we develop a simple, yet very effective point sampling strategy for detection of any CAD model through geometric hashing. Our approach relies on rendering the object coordinates from a set of views evenly distributed on a sphere. Actual sampling takes place on 2D domain over these renderings; the resulting samples are efficiently merged in 3D with the aid of a special voxel structure and relaxed with Lloyd iterations. The generated vertices are not concentrated only on critical points, as in many keypoint extraction algorithms, and there is even spacing between selected vertices. This is valuable for quantization based detection methods, such as geometric hashing of point pair features. The algorithm is fast and can easily handle the elongated/acute triangles and sharp edges typically existent in industrial CAD models, while automatically pruning the invisible structures. We do not introduce structural changes such as smoothing or interpolation and sample the normals on the original CAD model, achieving the maximum fidelity. We demonstrate the strength of this approach on 3D object detection in comparison to similar sampling algorithms.","PeriodicalId":6658,"journal":{"name":"2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","volume":"80 1","pages":"6871-6878"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77120782","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：