Robot fostering techniques for sensory-motor development of humanoid robots
- Тип контента: Научная статья
- Номер документа: 7636
- Название документа: Robot fostering techniques for sensory-motor development of humanoid robots
- Номер (DOI, IBSN, Патент): Не заполнено
- Изобретатель/автор: Adrian Stoica
- Правопреемник/учебное заведение: Jet Propulsion Laboratory, California Institute of Technology, 4800 Oak Grove Drive, Pasadena
- Дата публикации документа: 2001-12-31
- Страна опубликовавшая документ: США
- Язык документа: Английский
- Наименование изделия: Не заполнено
- Источник: Robotics and Autonomous Systems 37 (2001) 127–143
- Вложения: Да
- Аналитик: Глаголева Елена
 The research efforts addressing the control of robot behavior have been polarized; most robots are either fully guided through “strong” programming, or given a few learning algorithms and left alone to explore the world. This paper explores the area in-between, looking at robot fostering, referring to techniques by which skills can be transferred to robots through a close interaction with humans. While robot fostering can be the basis of interaction with a variety of robotic shapes, it is most natural and human-friendly when the robot apprentices are anthropomorphic/humanoid. Fostering techniques discussed here include teaching/learning by imitation, teaching by description/explanation, reinforcement, aid and collaboration. The paper illustrates an experiment in teaching/learning by imitation. The human fosters the robot by first imitating its uncoordinated arm movements, thus helping the robot develop its sensory-motor associative system. The human then shows arm movements and the robot visually tracks them; consecutively, the robot is able to learn arm movements by imitation. Fostering techniques,in addition to robot learning/acquisition techniques and more efficient man–machine interaction are considered key elements contributing to the nascence of a new research field, develop-mental robotics, which would focus on the robotics counterpart of human cognitive and motor development.
The research efforts addressing the control of robot behavior have been polarized; most robots are either fully guided through “strong” programming, or given a few learning algorithms and left alone to explore the world. This paper explores the area in-between, looking at robot fostering, referring to techniques by which skills can be transferred to robots through a close interaction with humans. While robot fostering can be the basis of interaction with a variety of robotic shapes, it is most natural and human-friendly when the robot apprentices are anthropomorphic/humanoid. Fostering techniques discussed here include teaching/learning by imitation, teaching by description/explanation, reinforcement, aid and collaboration. The paper illustrates an experiment in teaching/learning by imitation. The human fosters the robot by first imitating its uncoordinated arm movements, thus helping the robot develop its sensory-motor associative system. The human then shows arm movements and the robot visually tracks them; consecutively, the robot is able to learn arm movements by imitation. Fostering techniques,in addition to robot learning/acquisition techniques and more efficient man–machine interaction are considered key elements contributing to the nascence of a new research field, develop-mental robotics, which would focus on the robotics counterpart of human cognitive and motor development.
Категория: Научные статьи | Нет комментариев »
Комментарии
Статистика
	
	Категорий: 179
Статей всего: 2,003
По типу:
 Видео: 36
 Выдержка с форума: 1
 Контактные данные: 12
 Научная статья: 1388
 Не заполнено: 5
 Новостная статья: 317
 Обзор технологии: 42
 Патент: 219
 Тех.подробности: 34
 Тип: 1
Комментариев: 8,740
Изображений: 3,005	
	Подробней...
	
ТОР 10 аналитиков
- 
	Глаголева Елена - 591
Дмитрий Соловьев - 459
Helix - 218
Ридна Украина))) - 85
Наталья Черкасова - 81
max-orduan - 29
Елена Токай - 15
Роман Михайлов - 9
Мансур Жигануров - 4
Дуванова Татьяна - 3
Календарь
Авторизация
Ошибка в тексте?
Выдели её мышкой!
И нажми Ctrl+Enter

