Hybrid linguistic/numeric control of deburring robots based on human skills

Yang, Boo-Ho; Asada, H. Harry

doi:10.1109/robot.1992.220144

Cited by 19 publications

(6 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The principle of transferring human manipulation skill has been developed in the papers of Asada and coworkers [15], [14], [17], [16], [389]. The approach is based on the acquisition of manipulation skills and strategies from human experts and subsequent transfer of these skills to robot controllers.…”

Section: Hybrid Genetic Approaches In Roboticsmentioning

confidence: 99%

Intelligent Control of Robotic Systems

Katić¹,

Vukobratović²

2003

View full text Add to dashboard Cite

Section: Hybrid Genetic Approaches In Roboticsmentioning

confidence: 99%

Intelligent Control of Robotic Systems

Katić¹,

Vukobratović²

2003

View full text Add to dashboard Cite

“…OL can overcome the problems related to interviewing experts [4] without the long and drawn-out interaction with the knowledgeable human to inquire about his/her tactics. Experts often cannot easily articulate how they perform a specific action [5], as they have been taught to not think about reflex responses [6]. OL is the pure form of capturing and imitating human behavior and has been applied to learning skills for many human tasks [7][8][9][10].…”

Section: Introductionmentioning

confidence: 99%

Combining NEAT and PSO for learning tactical human behavior

Stein

González

Barham

2014

Neural Comput & Applic

View full text Add to dashboard Cite

This article presents and discusses a machine learning algorithm called PIGEON used to build agents capable of displaying tactical behavior in various domains. Such tactical behavior can be relevant in military simulations and video games, as well as in everyday tasks in the physical world, such as driving an automobile. Furthermore, PIGEON displays good performance across two different approaches to learning (observational and experiential) and across multiple domains. PIGEON is a hybrid algorithm, combining NEAT and PSO in two different manners. The investigation described in this paper compares the performance of the two versions of PIGEON to each other as well as to NEAT and to PSO individually. These four machine learning algorithms are applied in two different approaches to learning-through observation of human performance and through experience, as well as in three distinct domain testbeds. The criteria used to compare them were high proficiency in task completion and rapid learning. Results indicate that overall, PIGEON worked best when NEAT and PSO are applied in an alternating manner. This combination was called PIGEON-Alternate, or simply Alternate. The two versions of the PIGEON algorithm, the tests conducted, the results obtained and the conclusions are described in detail.

show abstract

“…However, the demand for automating these processes is rising due to the necessity of coping with the problem of aging skilled workers and to strengthen cost-competitiveness. Six-axis control robots were selected from the viewpoint of required processing accuracy, degree of freedom and equipment cost and technology has been developed to automate deburring and finishing works with robots [1,2]. However, there are many problems to be solved concerning the robot and the robot teaching processing technology so the automation work has not necessarily been successful in the past [3].…”

Section: Introductionmentioning

confidence: 99%

Development of robot teaching support devices to automate deburring and finishing works in casting

Sugita

Itaya

Takeuchi

2004

The International Journal of Advanced Manufacturing Technology

View full text Add to dashboard Cite

Concerning robot teaching, an online teaching method has conventionally been carried out by skilled workers using a teaching pendant. However, the teaching pendant is different with every robot manufacture and requires a large number of man-hours to assign a large number of points in defining the tool path for deburring. In recent years, use of an offline teaching method that utililises a three-dimensional robot simulation system has begun to spread, however, this is not necessarily easy to introduce in medium-and small-sized businesses. Thus two kinds of teaching support devices were developed from actual workpieces and deburring tools to prepare the tool path, considering the volume of investment for equipment and training of operators. One is a three-wire type teaching support device, and the other an arm type one. The former consists of tension wires supported at three points like a kite, and the latter consists of two arms and six connecting axes. Each device can measure the position and posture of a dummy tool in the deviceÕs coordinates. From the experiments, the arm-type teaching support device shows enough precision capability as a teaching support device, as opposed to the three-wire type teaching support device, which is cost-effective.

show abstract

Hybrid linguistic/numeric control of deburring robots based on human skills

Cited by 19 publications

References 5 publications

Intelligent Control of Robotic Systems

Intelligent Control of Robotic Systems

Combining NEAT and PSO for learning tactical human behavior

Development of robot teaching support devices to automate deburring and finishing works in casting

Contact Info

Product

Resources

About