Initial Experiments on Learning Based Randomized Bin-Picking Allowing Finger...Kensuke Harada
This paper proposes a novel method for randomized bin-picking based on learning. When a two-fingered gripper tries to pick an object from the pile, a finger often contacts a neighboring object. Even if a finger contacts a neighboring object, the target object will be successfully picked depending on the configuration of neighboring objects. In our proposed method, we use the visual information on neighboring objects to train the discriminator. Corresponding to a grasping posture of an object, the discriminator
predicts whether or not the pick will be successful even if a finger contacts a neighboring object. We examine two learning algorithms, the linear support vector machine (SVM) and the random forest (RF) approaches. By using both methods, we demonstrate
that the picking success rate is higher than with conventional methods without learning.
Initial Experiments on Learning Based Randomized Bin-Picking Allowing Finger...Kensuke Harada
This paper proposes a novel method for randomized bin-picking based on learning. When a two-fingered gripper tries to pick an object from the pile, a finger often contacts a neighboring object. Even if a finger contacts a neighboring object, the target object will be successfully picked depending on the configuration of neighboring objects. In our proposed method, we use the visual information on neighboring objects to train the discriminator. Corresponding to a grasping posture of an object, the discriminator
predicts whether or not the pick will be successful even if a finger contacts a neighboring object. We examine two learning algorithms, the linear support vector machine (SVM) and the random forest (RF) approaches. By using both methods, we demonstrate
that the picking success rate is higher than with conventional methods without learning.
Intergrated Single-arm Assembly and Manipulation Planning using Dynamic Regra...Kensuke Harada
This paper presents an integrated single-arm assembly
and motion planning algorithm to recursively find how
to assemble two objects with the help of a plenary surface
as the supporting fixture. The algorithm is done in both
assembly level and motion level. In the assembly level, the
algorithm checks all combinations of the assembly and gets
a set of candidate assembly orders. For each assembly order,
it performs motion planning to pick-and-place the base object
and assemble the other object to the base. In the motion level,
the algorithm integrates the orders computed in the assembly
level incrementally and recursively with graph searching and
motion planning, and finds a motion sequence to finish assembly
tasks. The proposed algorithm can find a feasible solution to
assemble two objects with completeness. It is practical and is
ready to be integrated with force control to perform real-world
assembly tasks.
Iterative Visual Recognition for Learning Based Randomized Bin-pickingKensuke Harada
This paper proposes a iterative visual recognition system
for learning based randomized bin-picking. Since the configuration on randomly stacked objects while executing the current picking trial is just partially different from the configuration while executing the previous picking trial, we consider detecting the poses of objects just by using a part of visual image taken at the current picking trial where it is different from the visual image taken at the previous picking trial. By using this method, we do not need to try to detect the poses of all objects included in the pile at every picking trial.
Assuming the 3D vision sensor attached at the wrist of a manipulator, we first explain a method to determine the pose of a 3D vision sensor maximizing the visibility of randomly stacked objects. Then, we explain a method for detecting the poses of randomly stacked objects. Effectiveness of our proposed approach is confirmed by experiments using a dual-arm manipulator where a 3D vision sensor and the two-fingered hand attached at the right and the left wrists, respectively.
History, definition, need, attributes, applications of data warehousing ; difference between data mining, big data, database and data warehouse ; future scope
2014 IEEE Int. Conf. on Robotics and Automation : A Manipulation Motion Plann...Kensuke Harada
In this paper, we propose a general manipulation
planner for dual-arm industrial manipulators. According to the context, the planner automatically determines whether both arms have to be used simultaneously or not. The approach is based on (i) the extension of an object placement algorithm previously developed, and (ii) the introduction of several types of re-grasping motions dedicated to dual-arm manipulators. Such motions induce a special topological structure in the manipulation space that can be captured into a manipulation graph. The graph is then used to solve the manipulation problem by a simple graph search algorithm. After searching for a solution path, we further consider optimizing the path by minimizing the number of re-grasps. The effectiveness of the approach is demonstrated on the dual-arm manipulator HiroNX working in a realistic factory environment.
Intergrated Single-arm Assembly and Manipulation Planning using Dynamic Regra...Kensuke Harada
This paper presents an integrated single-arm assembly
and motion planning algorithm to recursively find how
to assemble two objects with the help of a plenary surface
as the supporting fixture. The algorithm is done in both
assembly level and motion level. In the assembly level, the
algorithm checks all combinations of the assembly and gets
a set of candidate assembly orders. For each assembly order,
it performs motion planning to pick-and-place the base object
and assemble the other object to the base. In the motion level,
the algorithm integrates the orders computed in the assembly
level incrementally and recursively with graph searching and
motion planning, and finds a motion sequence to finish assembly
tasks. The proposed algorithm can find a feasible solution to
assemble two objects with completeness. It is practical and is
ready to be integrated with force control to perform real-world
assembly tasks.
Iterative Visual Recognition for Learning Based Randomized Bin-pickingKensuke Harada
This paper proposes a iterative visual recognition system
for learning based randomized bin-picking. Since the configuration on randomly stacked objects while executing the current picking trial is just partially different from the configuration while executing the previous picking trial, we consider detecting the poses of objects just by using a part of visual image taken at the current picking trial where it is different from the visual image taken at the previous picking trial. By using this method, we do not need to try to detect the poses of all objects included in the pile at every picking trial.
Assuming the 3D vision sensor attached at the wrist of a manipulator, we first explain a method to determine the pose of a 3D vision sensor maximizing the visibility of randomly stacked objects. Then, we explain a method for detecting the poses of randomly stacked objects. Effectiveness of our proposed approach is confirmed by experiments using a dual-arm manipulator where a 3D vision sensor and the two-fingered hand attached at the right and the left wrists, respectively.
History, definition, need, attributes, applications of data warehousing ; difference between data mining, big data, database and data warehouse ; future scope
2014 IEEE Int. Conf. on Robotics and Automation : A Manipulation Motion Plann...Kensuke Harada
In this paper, we propose a general manipulation
planner for dual-arm industrial manipulators. According to the context, the planner automatically determines whether both arms have to be used simultaneously or not. The approach is based on (i) the extension of an object placement algorithm previously developed, and (ii) the introduction of several types of re-grasping motions dedicated to dual-arm manipulators. Such motions induce a special topological structure in the manipulation space that can be captured into a manipulation graph. The graph is then used to solve the manipulation problem by a simple graph search algorithm. After searching for a solution path, we further consider optimizing the path by minimizing the number of re-grasps. The effectiveness of the approach is demonstrated on the dual-arm manipulator HiroNX working in a realistic factory environment.