Developmental Robotics: Theory and Experiments

By J. Weng. 2004

171 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Control and Systems Engineering, Mechanical Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Control and Systems Engineering

In Mechanical Engineering

Citations in the corpus

Active learning of inverse models with intrinsically motivated goal exploration in robots (2013, positive): “Second, we will use a heuristic inspired by observations of infants who sometimes prepare their reaching movements by starting from a same rest position [81], by resetting the robot to such a rest position, which allows reducing the set of starting states used to perform a task.”
Ieee Transactions on Evolutionary Computation Intrinsic Motivation Systems for Autonomous Mental Development (unknown): “On the contrary, the domain that real robots shall investigate is the real unconstrained world, which is a highly complicated and " muddy " structure as pointed out by Weng ([34]) full of very different kinds of intertwined non-gaussian inhomogeneous noise.”
A Foundational Architecture for Artificial General Intelligence (2007, background): “Let’s assume, as we must ([22], [23], [24], [25], [9], [10]), that learning via a developmental period must be an integral part of the life cycle of any AGI.”
Online Learning with Stochastic Recurrent Neural Networks using Intrinsic Motivation Signals (2017, background): “1 Introduction The idea of developmental robots [1, 2, 3, 4, 5] that adapt autonomously through lifelong-learning is still one of the big challenges in robotics.”
DREAM Architecture: a Developmental Approach to Open-Ended Learning in Robotics (2020, methodology): “equire speciﬁc processes that are not necessarily task-oriented. As human infants, the proposed approach needs to face the challenges of understanding the robot’s environment and its own capabilities [34,35,36,37]. In this context, the robot behavior can be described by three loops: (1) Operational,”
The role of intersensory redundancy in early perceptual, cognitive, and social development (2012, background): “Developmental robots “develop” their perceptual, cognitive, and behavioral skills incrementally through real-time explorations and interactions with their environment (Weng, 2004).”
Artificial curiosity with planning for autonomous perceptual and cognitive development (2011, background): “The developmental agent here is composed of three parts [23]: (1) the sensory or perceptual map, for encoding raw observations, (2) the cognitive map, used to predict subsequent states in the encoded space, and (3) the value system, which assigns values to the immediately available actions.”
A Survey of Artificial Cognitive Systems: Implications for the Autonomous Development of Mental Capabilities in Computational Agents (2007, methodology): “The general SASE schema, including the associated concept of autonomous mental development (AMD), has been developed and validated in the context of two autonomous developmental robotics systems, SAIL and DAV [153], [154], [156], [157] , [158]–[162] have developed a series of robot platforms called ”