Teaching of grasp/graspless manipulation for industrial robots by human demonstration

Maeda, Yusuke; Ishido, Nanako; Kikuchi, Haruka; Arai, Tamio

doi:10.1109/irds.2002.1043971

Cited by 28 publications

(12 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is intuitive and natural because it enables a robot to learn through interaction with a human. Maeda et al [11] let a robot learn the moving path of objects by demonstrating a manipulation of an object, which had a marker for tracking. Ekvall et al [12,13] classified ten grasp types by observing the hand trajectory, hand rotations, and postures of a human hand via a data glove.…”

Section: Related Workmentioning

confidence: 99%

“…Since the ability of current service robots is much lower than that of a human in grasping task, it is challenging for a robot to grasp an object like human. Instead, if a robot observes a human's demonstration for grasping task, we may teach the robot the correlation between grasp types and the states of objects more naturally and intuitively [11][12][13][14].…”

mentioning

confidence: 99%

See 1 more Smart Citation

Towards cognitive grasping: modeling of unknown objects and its corresponding grasp types

Kim

Han

You

et al. 2011

Intel Serv Robotics

View full text Add to dashboard Cite

This paper describes an intuitive approach for a cognitive grasp of a robot. The cognitive grasp means the chain of processes that make a robot to learn and execute a grasping method for unknown objects like a human. In the learning step, a robot looks around a target object to estimate the 3D shape and understands the grasp type for the object through a human demonstration. In the execution step, the robot correlates an unknown object to one of known grasp types by comparing the shape similarity of the target object based on previously learned models. For this cognitive grasp, we mainly deal with two functionalities such as reconstructing an unknown 3D object and classifying the object by grasp types. In the experiment, we evaluate the performance of object classification according to the grasp types for 20 objects via human demonstration.

show abstract

Section: Related Workmentioning

confidence: 99%

mentioning

confidence: 99%

Towards cognitive grasping: modeling of unknown objects and its corresponding grasp types

Kim

Han

You

et al. 2011

Intel Serv Robotics

View full text Add to dashboard Cite

show abstract

“…1. In this study, definitions are given which show that the robot can treat the tasks achieved by (2) and (3) because it is difficult for the robot to manipulate industrial tools or flexible objects. In addition, non-position-controlled motions in motions (1) are also out of scope.…”

Section: Assumptionsmentioning

confidence: 99%

“…an object has disappeared, which means an object was picked up). Maeda et al [2] have extracted pushing motion and pick-and-place motion by three-dimensional Hough transformation. Takamatsu et al [3] have extracted transitions of contact configurations between two blocks.…”

Section: Introductionmentioning

confidence: 99%

Reasoning of abstract motion of a target object through task order with natural language — pre-knowledge of object-handling-task programming for a service robot

Katsuki

Siegwart²,

Ota³

et al. 2006

Advanced Robotics

View full text Add to dashboard Cite

Abstract-In this paper, an attempt is made to reason an abstract motion of a target object when the object is manipulated through a task order. The reasoning algorithm is used as a function in the system that navigates layman's robot programming. The task order consists of two words: Task and Target (e.g., 'switch on' and 'light'). There are three kinds of motions: Linear, Circular and Point-To-Point motion. The system chooses a suitable motion. In the reasoning, it is important to be able to reason from various input words using a limited knowledge base. Therefore, a knowledge base is proposed that consists of a thesaurus and minimum knowledge. The knowledge defines only words that directly stand for the motions (e.g., 'turn' means Circular motion). The knowledge is propagated through hypernyms and hyponyms in the thesaurus. A motion is reasoned using the propagated knowledge in Task and Target. Moreover, learning, which results from on-site updating of the knowledge from the user, achieves reinforcement/customization of the knowledge base. The system successfully reasoned motions from various task orders. Moreover, for the robot programming of a door-opening task, a robot with the reasoning system reasoned a motion of the door and realized the task.

show abstract

“…In industrial automation, the complexity of predicting the effects of selecting objects for manipulation is addressed with known, and well engineered environments [1,2]. However, a reliable prediction of the outcome of removing an object from chaotically stacked piles is more challenging due to issues that real-world environments pose for autonomous systems.…”

Section: Introductionmentioning

confidence: 99%

Support relation analysis and decision making for safe robotic manipulation tasks

Mojtahedzadeh

Bouguerra

Schaffernicht

et al. 2015

Robotics and Autonomous Systems

View full text Add to dashboard Cite

Teaching of grasp/graspless manipulation for industrial robots by human demonstration

Cited by 28 publications

References 14 publications

Towards cognitive grasping: modeling of unknown objects and its corresponding grasp types

Towards cognitive grasping: modeling of unknown objects and its corresponding grasp types

Reasoning of abstract motion of a target object through task order with natural language — pre-knowledge of object-handling-task programming for a service robot

Support relation analysis and decision making for safe robotic manipulation tasks

Contact Info

Product

Resources

About