[PDF][PDF] Robot manipulation of human tools: Autonomous detection and control of task relevant features
CC Kemp, A Edsinger - Proc. of the Fifth Intl. Conference on …, 2006 - people.csail.mit.edu
The efficient acquisition and generalization of skills for manual tasks requires that a robot be
able to perceive and control the important aspects of an object while ignoring irrelevant …
able to perceive and control the important aspects of an object while ignoring irrelevant …
Using probabilistic reasoning over time to self-recognize
Using the probabilistic methods outlined in this paper, a robot can learn to recognize its own
motor-controlled body parts, or their mirror reflections, without prior knowledge of their …
motor-controlled body parts, or their mirror reflections, without prior knowledge of their …
Robot manipulation in human environments
A Edsinger - 2007 - dspace.mit.edu
Human environments present special challenges for robot manipulation. They are often
dynamic, difficult to predict, and beyond the control of a robot engineer. Fortunately, many …
dynamic, difficult to predict, and beyond the control of a robot engineer. Fortunately, many …
Learning acceptable windows of contingency
By learning a range of possible times over which the effect of an action can take place, a
robot can reason more effectively about causal and contingent relationships in the world. An …
robot can reason more effectively about causal and contingent relationships in the world. An …
[PDF][PDF] Visual tool tip detection and position estimation for robotic manipulation of unknown human tools
CC Kemp, A Edsinger - Computer Science and Artificial …, 2005 - people.csail.mit.edu
Robots that use human tools could more easily work with people, perform tasks that are
important to people, and benefit from human strategies for accomplishing these tasks. For a …
important to people, and benefit from human strategies for accomplishing these tasks. For a …
[PDF][PDF] Toward robot learning of tool manipulation from human demonstration
A Edsinger, CC Kemp - Citeseer, Tech. Rep., 2007 - Citeseer
Robots that manipulate everyday tools in unstruc-tured, human settings could more easily
work with people and perform tasks that are important to people. Task demonstration could …
work with people and perform tasks that are important to people. Task demonstration could …
Using context and sensory data to learn first and second person pronouns
We present a method of grounded word learning that can learn the meanings of first and
second person pronouns. The model selectively associates new words with agents in the …
second person pronouns. The model selectively associates new words with agents in the …
[BOOK][B] Using sentence context and implicit contrast to learn sensor-grounded meanings for relational and deictic words: The TWIG system
K Gold - 2008 - search.proquest.com
This thesis describes a novel system that allows a robot to infer the meanings of new words
from their usage in context. TWIG (Transportable Word Intension Generator) can parse …
from their usage in context. TWIG (Transportable Word Intension Generator) can parse …
[PDF][PDF] Developmentally guided ego-exo force discrimination for a humanoid robot
A Edsinger-Gonzales - Fifth International Workshop on …, 2005 - people.csail.mit.edu
We present an approach for discriminating between forces a humanoid robot induces on
itself (ego) and forces arising from its interaction with the environment (exo). The method …
itself (ego) and forces arising from its interaction with the environment (exo). The method …
[PDF][PDF] Developmentally Guided Ego-Exo Force Discrimination for a Humanoid Robot
We present an approach for discriminating between forces a humanoid robot induces on
itself (ego) and forces arising from its interaction with the environment (exo). The method …
itself (ego) and forces arising from its interaction with the environment (exo). The method …