Autonomous Mental Development by Robots and Animals

By J. Weng, James L. McClelland, Alex Pentland, Olaf Sporns, I. Stockman, Mriganka Sur, E. Thelen. 2001

713 citations recorded by the source corpus.

The scope of mental development includes cognitive, behavioral, emotional, and all other mental capabilities that are exhibited by humans, higher animals, and artificial systems. Computational principles of autonomous mental development in humans and the synthesis of developmental programs for robots and other artificial systems are beginning to be actively studied. Robots that develop their mental skills autonomously represent a fundamental change from the traditional paradigm for constructing intelligent machines. Support for this new field should lead to advances in science, engineering, economy, and understanding of the mind.

Subfields: Management Science and Operations Research, Safety, Risk, Reliability and Quality, Statistics and Probability, Robotics & Control

How researchers see this paper

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

In Management Science and Operations Research

In Safety, Risk, Reliability and Quality

In Statistics and Probability

In Robotics & Control

Citations in the corpus

Continual Learning for Robotics (2019, background): “The concept of learning continually from experience has always been present in artificial intelligence and robotics since their birth (Turing, 2009; Weng et al., 2001).”
Novelty and Reinforcement Learning in the Value System of Developmental Robots (2002, background): “Motivated by studies of developmental psychology and neuroscience (Piaget, 1952) (Flavell et al., 1993) (Sur et al., 1999), computation studies about autonomous mental development has drawn increased attention (Weng et al., 2000) (Almassy et al., 1998) (Ogmen, 1997).”
R-IAC: Robust Intrinsically Motivated Exploration and Active Learning (2009, background): “I. INTRINSICALLY MOTIVATED EXPLORATION AND LEARNING D EVELOPMENTAL robotics approaches are studyingmechanisms that may allow a robot to continuously discover and learn new skills in unknown environments and in a life long time scale [1], [2].”
Ieee Transactions on Evolutionary Computation Intrinsic Motivation Systems for Autonomous Mental Development (neutral): “Building such a robot is one of the greatest challenges to robotics today, and is the long-term goal of the growing field of developmental robotics ([1], [2]).”
Guest Editorial Active Learning and Intrinsically Motivated Exploration in Robots: Advances and Challenges (2010, background): “This challenge is at the center of the developmental robotics ﬁeld [7], [35]–[37].”
Practical Recommendations for Replay-based Continual Learning Methods (2022, background): “The problem of learning from a sequence of tasks was posed since the origin of artiﬁcial intelligence [29, 30].”
Curiosity driven reinforcement learning for motion planning on humanoids (2014, background): “Developmental Robotics (Lungarella et al., 2003) seeks to enable robots to learn to do things in a general and adaptive way, by trial-and-error, and it is thus closely related to AMD and the work on curiosity-driven RL, described in the previous section.”
Building a mechanistic model of the development and function of the primary visual cortex. (2012, positive): “In the long run, to account for more complex aspects of visual system development such as visual object recognition and optic flow processing, it will be necessary to implement the models as embodied, situated agents (Pylyshyn, 2000; Weng et al., 2001) embedded in the real world or in realistic 3D v”
An intrinsic value system for developing multiple invariant representations with incremental slowness learning (2013, methodology): “Related to CD-MISFA in terms of having similar motivations and being based in developmental principles [67] are the biologically-constrained intrinsic motivation model, and robotic implementation, of Baldassarre et al. [3] 1 , and the Qualitative Learner of Action and Perception (QLAP; [33]).”
Neuromodulation in a learning robot: interactions between neural plasticity and behavior (2003, neutral): “Future work will focus on the development of appropriate behavioral and neural measures that, in combination, characterize mental and cognitive development [14].”