Humanoid push recovery using sensory reweighting

Abstract In this paper we propose a novel system that uses sensory input from both vision and inertial sensors for an improved perception of the robot current status of equilibrium. We use MonoSLAM vision odometry as a basis for the visual perception and a gyro for angular velocity measurements; and we devise a reweighting method within a Kalman filter framework. Moreover, our approach is designed to be robust against visual and measurement noise such as blur, poor lighting conditions, and faulty sensory output. The novelty in this work is a robust humanoid fall avoidance system, which relies on the fusion of sensory input, mainly gyroscope and visual odometry, taking into account changes in the environment. The fusion of the mentioned sensors in addition to the image quality assessment, ensure a more human-like fall avoidance in comparison to currently existing systems. We implement our method on the NAO humanoid, where seven sets of experiments are performed to assess the effectiveness of our approach. The fusion of camera and gyro information not only enables a more human-like behavior, but also provides more humanoid stability and faster recovery, and thus leads to more robust fall avoidance.

[1]  Patrick J. Loughlin,et al.  Sensory adaptation in human balance control: Lessons for biomimetic robotic bipeds , 2008, Neural Networks.

[2]  Jerry E. Pratt,et al.  Learning Capture Points for humanoid push recovery , 2007, 2007 7th IEEE-RAS International Conference on Humanoid Robots.

[3]  Mohammad-Ali Nikouei Mahani,et al.  A novel approach for humanoid push recovery using stereopsis , 2014, Robotica.

[4]  Roland Siegwart,et al.  Monocular‐SLAM–based navigation for autonomous micro helicopters in GPS‐denied environments , 2011, J. Field Robotics.

[5]  F. Horak.  Postural orientation and equilibrium: what do we need to know about neural control of balance to prevent falls? , 2006, Age and ageing.

[6]  Sukyung Park,et al.  Perturbation-dependent selection of postural feedback gain and its scaling. , 2012, Journal of biomechanics.

[7]  Tomomichi Sugihara,et al.  COM motion estimation of a Humanoid robot based on a fusion of dynamics and kinematics information , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[8]  N. G. Tsagarakis,et al.  A compact model for the compliant humanoid robot COMAN , 2012, 2012 4th IEEE RAS & EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob).

[9]  Tim Kiemel,et al.  Navigating sensory conflict in dynamic environments using adaptive state estimation , 2011, Biological Cybernetics.

[10]  C. Oatis,et al.  Kinesiology: The Mechanics and Pathomechanics of Human Movement , 2003 .

[11]  Patricia Ladret,et al.  The blur effect: perception and estimation with a new no-reference perceptual blur metric , 2007, Electronic Imaging.

[12]  Tatsuo Arai,et al.  Emergent stop for Humanoid Robots , 2006, 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[13]  B. E. Maki,et al.  The role of limb movements in maintaining upright stance: the "change-in-support" strategy. , 1997, Physical therapy.

[14]  Masahiro Fujita,et al.  A small biped entertainment robot exploring attractive applications , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[15]  Miomir Vukobratovic,et al.  Zero-Moment Point - Thirty Five Years of its Life , 2004, Int. J. Humanoid Robotics.

[16]  David A. Winter,et al.  Human balance and posture control during standing and walking , 1995 .

[17]  R. Peterka.  Sensorimotor integration in human postural control. , 2002, Journal of neurophysiology.

[18]  William H Paloski,et al.  Sensorimotor posture control in the blind: superior ankle proprioceptive acuity does not compensate for vision loss. , 2013, Gait & posture.

[19]  M. Nardini,et al.  The development of multisensory balance, locomotion, orientation and navigation. , 2012 .

[20]  F. Horak,et al.  Postural feedback responses scale with biomechanical constraints in human standing , 2004, Experimental Brain Research.

[21]  Benjamin J. Stephens,et al.  Humanoid push recovery , 2007, 2007 7th IEEE-RAS International Conference on Humanoid Robots.

[22]  Benjamin J. Stephens.  State estimation for force-controlled humanoid balance using simple models in the presence of modeling error , 2011, 2011 IEEE International Conference on Robotics and Automation.

[23]  Karim A. Tahboub.  Biologically-inspired humanoid postural control , 2009, Journal of Physiology-Paris.

[24]  Imad H. Elhajj,et al.  A hybrid ankle/hip preemptive falling scheme for humanoid robots , 2011, 2011 IEEE International Conference on Robotics and Automation.

[25]  Angelo M. Sabatini,et al.  Extended Kalman Filter-Based Methods for Pose Estimation Using Visual, Inertial and Magnetic Sensors: Comparative Analysis and Performance Evaluation , 2013, Sensors.

[26]  Olivier Stasse,et al.  MonoSLAM: Real-Time Single Camera SLAM , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[27]  Seth J. Teller,et al.  Drift-free humanoid state estimation fusing kinematic, inertial and LIDAR sensing , 2014, 2014 IEEE-RAS International Conference on Humanoid Robots.

[28]  Onder Tutsoy,et al.  Learning to balance an NAO robot using reinforcement learning with symbolic inverse kinematic , 2017 .

[29]  Önder Tutsoy,et al.  Cpg Based RL Algorithm Learns to Control of a humanoid robot leg , 2015, Int. J. Robotics Autom..

[30]  Christopher G. Atkeson,et al.  State estimation of a walking humanoid robot , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[31]  Roland Siegwart,et al.  Fusion of IMU and Vision for Absolute Scale Estimation in Monocular SLAM , 2011, J. Intell. Robotic Syst..

[32]  Sung-Nam Oh,et al.  Balance control for biped walking robots using only zero-moment-point position signal , 2012 .