On Ambiguity in Robot Learning from Demonstration
نویسنده
چکیده
An overlooked problem in Learning From Demonstration is the ambiguity that arises, for instance, when the robot is equipped with more sensors than necessary for a certain task. Simply trying to repeat all aspects of a demonstration is seldom what the human teacher wants, and without additional information, it is hard for the robot to know which features are relevant and which should be ignored. This means that a single demonstration maps to several different behaviours the teacher might have intended. This one-to-many (or many-to-many) mapping from a demonstration (or several demonstrations) into possible intended behaviours is the ambiguity that is the topic of this paper. Ambiguity is defined as the size of the current hypothesis space. We investigate the nature of the ambiguity for different kinds of hypothesis spaces and how it is reduced by a new concept learning algorithm.
منابع مشابه
Workspace Boundary Avoidance in Robot Teaching by Demonstration Using Fuzzy Impedance Control
The present paper investigates an intuitive way of robot path planning, called robot teaching by demonstration. In this method, an operator holds the robot end-effector and moves it through a number of positions and orientations in order to teach it a desired task. The presented control architecture applies impedance control in such a way that the end-effector follows the operator’s hand with d...
متن کاملGeneration of a Task Model by Integrating Multiple Observations of Human Demonstrations
This paper describes a new approach on how to teach a robot everyday manipulation tasks under the “Learning from Observation” framework. Most of the approaches so far assume that a demonstration can be well understood from a single demonstration. But a single demonstration contains ambiguity, in that interactions which are essential to complete a task can’t be discerned without prior task depen...
متن کاملA Q-learning Based Continuous Tuning of Fuzzy Wall Tracking
A simple easy to implement algorithm is proposed to address wall tracking task of an autonomous robot. The robot should navigate in unknown environments, find the nearest wall, and track it solely based on locally sensed data. The proposed method benefits from coupling fuzzy logic and Q-learning to meet requirements of autonomous navigations. Fuzzy if-then rules provide a reliable decision maki...
متن کاملLearning Tasks From A Single Demonstration - Robotics and Automation, 1997. Proceedings., 1997 IEEE International Conference on
Learning a complex dynamic robot maneuver from a single human demonstration is difficult. This paper explores an approach to learning from demonstration based on learning an optimization criterion from the demonstration and a task model from repeated attempts to perform the task, and using the learned criterion and model to compute an appropriate robot movement. A preliminary version of the app...
متن کاملConfidence-Based Multi-Robot Learning from Demonstration
Learning from demonstration algorithms enable a robot to learn a new policy based on demonstrations provided by a teacher. In this article, we explore a novel research direction, multi-robot learning from demonstration, which extends demonstration based learning methods to collaborative multi-robot domains. Specifically, we study the problem of enabling a single person to teach individual polic...
متن کامل