Abstract. To explore issues of developmental structure, physical embodiment, integration of multiple sensory and motor systems, and social interaction, we have constructed an upper-torso humanoid robot called Cog. The robot has twenty-one degrees of freedom and a variety of sensory systems, including visual, auditory, vestibular, kinesthetic, and tactile senses. This chapter gives a background on the methodology that we have used in our investigations, highlights the research issues that have been raised during this project, and provides a summary of both the current state of the project and our long-term goals. We report on a variety of implemented visual-motor routines (smooth-pursuit tracking, saccades, binocular vergence, and vestibular-ocular and opto-kinetic reflexes), orientation behaviors, motor control techniques, and social behaviors (pointing to a visual target, recognizing joint attention through face and eye finding, imitation of head nods, and regulating interaction through expressive feedback). We further outline a number of areas for future research that will be necessary to build a complete embodied system. 1

This paper reports on an experiment in evolving the morphology of an artificial compound eye with 16 light sensors on a robot. A special robot was designed and constructed that is able to autonomously modify the angular positions of the individual light sensors within the compound eye. The task of the robot was to employ motion parallax to estimate a critical distance to obstacles. This task was achieved by adapting the morphology of the compound eye by an evolutionary algorithm while using a fixed neural network to control the robot. 1

Oculomotor control in a humanoid robot faces similar problems as biological oculomotor systems, i.e., the stabilization of gaze in face of unknown perturbations of the body, selective attention, stereo vision, and dealing with large information processing delays. Given the nonlinearities of the geometry of binocular vision as well as the possible nonlinearities of the oculomotor plant, it is desirable to accomplish accurate control of these behaviors through learning approaches. This paper develops a learning control system for the phylogenetically oldest behaviors of oculomotor control, the stabilization reflexes of gaze. In a step-wise procedure, we demonstrate how control theoretic reasonable choices of control components result in an oculomotor control system that resembles the known functional anatomy of the primate oculomotor system. The core of the learning system is derived from the biologically inspired principle of feedbackerror learning combined with a state-of-the-art nonparametric statistical learning network. With this circuitry, we demonstrate that our humanoid robot is able to acquire high performance visual stabilization reflexes after about 40 seconds of learning despite significant nonlinearities and processing delays in the system. 1

Stabilization of gaze is a major functional prerequisite for robots exploring the environment. The main reason for a “steady-image” requirement is to prevent the robot’s own motion to compromise its “visual functions”. In this paper we present an artificial system, the LIRA robot head, capable of controlling its cameras/eyes to stabilize gaze. The system features a stabilization mechanism relying on principles exploited by natural systems: an inertial sensory apparatus and images of space-variant resolution. The inertial device measures angular velocities and linear acceleration along the vertical and horizontal fronto-parallel axes. The space-variant image geometry facilitates real-time computation of optic flow and the extraction of first-order motion parameters. Experiments which describe the performance of the LIRA robot head are presented. The results show that the stabilization mechanism improves the reactivity of the system to changes occurring suddenly at new spotted locations.

Abstract not found

Abstract not found

One major problem of underwater observation with an automatic engine is the instability of image acquisition and visualization. Indeed, small engines of this kind are subjected to low-frequency motions due to weak friction and water currents. In this paper, we propose to maintain stabilization in the image by controlling the pan and tilt motions of the camera attached to the engine, using techniques for target tracking by visual servoing. The main idea behind approach lies in the fact that, since it is very difficult to track a point in the images of an unknown and complex scene using geometrical tools, the position of a virtual point can be retrieved by the integration of its 2D motion. The motion estimation method we have used, called the RMR algorithm, provides the parameters of a selected motion model (for the task considered here, a constant one) and is perfectly suitable for real-time constraints and the complexity of an undersea image sequence. Our approach has been validated on a dry setup using two different sequences of underwater images. c ○ 2000 Academic Press Key Words: image stabilization; visual servoing; 2D motion; underwater vision. 1.

Abstract—Robotic implementations of gaze control and image stabilization have been previously proposed, that rely on fusing inertial and visual sensing modalities. They are bioinspired in the sense that human and biological system also combine the two sensing modalities for the same goal. In this work we build upon these previous results and, with the contribution of psychophysical studies, attempt a more biomimetic approach to the robotic implementation. Since Bayesian models have been successfully used to explain psychophysical experimental findings, we propose a robotic implementation using Bayesian inference. I.

We present a binocular robot that learns compensatory camera movements for image stabilization purposes. Most essential in achieving satisfactory image stabilization performance is the exploitation/integration of different self-motion information. In our robot, self-motion is measured inertially through an artificial vestibular apparatus and visually using basic motion detection algorithms. The first sensory system codes rotations and translations of the robot's head, the second, the shift of the visual world across the image plane. An adaptive neural network learns to map these sensory signals to motor commands, transforming non homogeneous self-motion information into compensatory camera movements. We describe the network architecture, the convergence of the learning scheme and the performance of the stabilization reflex evaluated quantitatively by means of direct measurements on the image plane. 1.

Abstract not found