Adaptive predictive gaze control of a redundant humanoid robot head

Abstract

A general concept for the gaze control of a redundant humanoid robot head is presented. It is based on an adaptive Kalman filter that predicts the next state of the moving target, processing the position information provided by a head-mounted stereo camera. The trajectory tracking control at the task level combines a proportional feedback and a feedforward term. The gains of both control actions are adapted in order to provide optimal dynamic response for unknown arbitrary target trajectories. Inverse differential kinematics is evaluated so that human-like joint motions are achieved. To exploit kinematic redundancy, a weighted pseudoinverse is realized that takes into account different optimization criteria. Additional self-motions of the head are also considered. Experimental results on the head of the humanoid robot ARMAR-III are presented. © 2011 IEEE

Head-eyes system and gaze analysis of the humanoid robot Romeo

“…(e-mail: alain.berthoz@college-de-france.fr). ARMAR robot developed by [8] where the work is targeted on gaze control [9]. Apart from the full robots mentioned above, half a robot accompanied with a head that the authors are aware of, is the BARTHOC system [10] with 3 DOF for the eyes and 4 DOF for the head.…”

Multimodal saliency-based attention: A lazy robot's approach

“…For the ARMAR-III robot head, a gaze control concept is implemented that uses differential kinematics, which allows the visual tracking of moving targets with unknown and arbitrary trajectory. Additionally, a natural human-like behavior is obtained by specifically applying all available degrees of freedom (DoF) of the robot head (see [3]). …”

“…The audio data is processed at a sampling rate of 48 kHz. The ARMAR-III head provides 7 degrees of freedom (DoF) and uses a cycle time of T =30 ms to control them (see [3]). The pan-tilt unit has 2 DoF and is mounted on a tripod such that the cameras are roughly on eye height of an averagely tall human in order to reflect a humanoid view of the scene.…”

“…de We extend our previous work described in [2], which introduced a multimodal attention system for object-based audio-visual scene exploration and analysis. In this contribution, we integrated adaptive predictive gaze control [3] to control a kinematically redundant robot head, i.e. the ARMAR-III humanoid head, generate natural-looking head motion patterns, and take advantage of a new visual saliency algorithm that now also integrates the important influence of motion saliency (see [4]).…”

Multimodal gaze stabilization of a humanoid robot based on reafferences

“…Different representations of the task space were proposed for gaze stabilization. Milighetti used the line of sight orientation (pan and tilt) [4]. Roncone built a kinematic model of the fixation point described as the intersection of the lines of sight of both eyes [5].…”