A hand-designed internal representation of the world cannot deal with unknown or uncontrolled environments. Motivated by human cognitive and behavioral development, this paper presents a theory, an architecture, and some experimental results for developmental robotics. By a developmental robot, we mean that the robot generates its “brain ” (or “central nervous system, ” including the information processor and controller) through online, real-time interactions with its environment (including humans). A new Self-Aware Self-Effecting (SASE) agent concept is proposed, based on our SAIL and Dav developmental robots. The manual and autonomous development paradigms are formulated along with a theory of representation suited for autonomous development. Unlike traditional robot learning, the tasks that a developmental robot ends up learning are unknown during the programming time so that the task-specific representation must be generated and updated through real-time “living ” experiences. Experimental results with SAIL and Dav developmental robots are presented, including visual attention selection, autonomous navigation, developmental speech learning, range-based obstacle avoidance, and scaffolding through transfer and chaining.

Abstract — We propose a system that gives a mobile robot the ability to separate simultaneous sound sources. A microphone array is used along with a real-time dedicated implementation of Geometric Source Separation and a postfilter that gives us a further reduction of interferences from other sources. We present results and comparisons for separation of multiple non-stationary speech sources combined with noise sources. The main advantage of our approach for mobile robots resides in the fact that both the frequencydomain Geometric Source Separation algorithm and the post-filter are able to adapt rapidly to new sources and non-stationarity. Separation results are presented for three simultaneous interfering speakers in the presence of noise. A reduction of log spectral distortion (LSD) and increase of signal-to-noise ratio (SNR) of approximately 10 dB and 14 dB are observed. I.

The hearing sense on a mobile robot is important because it is omnidirectional and it does not require direct line-of-sight with the sound source. Such capabilities can nicely complement vision to help localize a person or an interesting event in the environment. To do so the robot auditory system must be able to work in noisy, unknown and diverse environmental conditions. In this paper we present a robust sound source localization method in three-dimensional space using an array of 8 microphones. The method is based on time delay of arrival estimation. Results show that a mobile robot can localize in real time different types of sound sources over a range of 3 meters and with a precision of 3°.

This paper introduces a theory about mentally developing robots. The limitation of the traditional agent model is raised and a new SASE agent is proposed, based on our SAIL developmental robot. We formulate the manual development paradigm and autonomous development paradigm. The performance of a developmental robot is then formulated as reaching the norm of a human age group. The framework of autonomously generating brain 1 representation is investigated in mathematical terms. Some techniques of such a representation are provided based on our SAIL-2 developmental algorithm. We establish the conceptual limitation of symbolic representation and from the limitation we propose that no developmental robot can use a symbolic representation. Finally, the completeness of developmental robot is investigated conditioned on five factors.

Mobile robots in real-life settings would benefit from being able to localize sound sources. Such a capability can nicely complement vision to help localize a person or an interesting event in the environment, and also to provide enhanced processing for other capabilities such as speech recognition. In this paper we present a robust sound source localization method in three-dimensional space using an array of 8 microphones. The method is based on a frequency-domain implementation of a steered beamformer along with a probabilistic post-processor. Results show that a mobile robot can localize in real time multiple moving sources of different types over a range of 5 meters with a response time of 200 ms.

It has been proved to be extremely challenging for humans to program a robot to such a sufficient degree that it acts properly in a typical unknown human environment. This is especially true for a humanoid robot due to the very large number of redundant degrees of freedom and a large number of sensors that are required for a humanoid to work safely and effectively in the human environment.

Abstract—Scaffolding is a process of transferring learned skills to new and more complex tasks through arranged experience in open-ended development. In this paper, we propose a developmental learning architecture that enables a robot to transfer skills acquired in early learning settings to later more complex task settings. We show that a basic mechanism that enables this transfer is sequential priming combined with attention, which is also the driving mechanism for classical conditioning, secondary conditioning, and instrumental conditioning in animal learning. A major challenge of this work is that training and testing must be conducted in the same program operational mode through online, real-time interactions between the agent and the trainers. In contrast with former modeling studies, the proposed architecture does not require the programmer to know the tasks to be learned and the environment is uncontrolled. All possible perceptions and actions, including the actual number of classes, are not available until the programming is finished and the robot starts to learn in the real world. Thus, a predesigned task-specific symbolic representation is not suited for such an open-ended developmental process. Experimental results on a robot are reported in which the trainer shaped the behaviors of the agent interactively, continuously, and incrementally through verbal commands and other sensory signals so that the robot learns new and more complex sensorimotor tasks by transferring sensorimotor skills learned in earlier periods of open-ended development. Index Terms—Attention, classical conditioning, incremental learning, instrumental conditioning, mental architecture, mental development, multitask learning, online learning, scaffolding, skill transfer. I.

This paper presents a computational theory of developmental mental architectures for artificial and natural systems, motivated by neuroscience. The work is an attempt to approximately model biological mental architectures using mathematical tools. Six types of architecture are presented, beginning with the observation-driven Markov decision process as Type-1. From Type-1 to Type-6, the architecture progressively becomes more complete toward the necessary functions of autonomous mental development. Properties of each type are presented. Experiments are discussed with emphasis on their architectures. r 2007 Published by Elsevier B.V.

Human developmental learning is capable of dealing with the dynamic visual world, speechbased dialogue, and their complex real-time association. However, the architecture that realizes this for robotic cognitive development has not been reported in the past. This paper takes up this challenge. The proposed architecture does not require a strict coupling between visual and auditory stimuli. Two major operations contribute to the “abstraction ” process: multiscale temporal priming and high-dimensional numeric abstraction through internal responses with reduced variance. As a basic principle of developmental learning, the programmer does not know the nature of the world events at the time of programming and, thus, hand-designed task-specific representation is not possible. We successfully tested the architecture on the SAIL robot under an unprecedented challenging multimodal interaction mode: use real-time speech dialogue as a teaching source for simultaneous and incremental visual learning and language acquisition, while the robot is viewing a dynamic world that contains a rotating object to which the dialogue is referring. 1.

What “constraints” are exactly wired into the human developmental program? What “constraints ” are minimally necessary for a developmental robot? These are open questions. In this paper, we propose a mechanism of developing experiencebased priming – predicting the future contexts including sensation and action based on the previous experience – as a powerful “constraint” for developmental robots. We present an architecture that develops this priming capability through realtime online interactions with the environment. We report how our SAIL robot developed a sense of novelty in a well-known “drawbridge ” experiment which sheds light on the controversial issue of “Object Permanence ” in psychology. We further show how the proposed priming mechanism enabled SAIL to deal with a very challenging online learning setting: learning the name and property (e.g., size) of dynamically rotating objects through