Model-Based Real-Time Motion Tracking using Dynamical Inverse Kinematics

  title={Model-Based Real-Time Motion Tracking using Dynamical Inverse Kinematics},
  author={Lorenzo Rapetti and Yeshasvi Tirupachuri and Kourosh Darvish and Claudia Latella and Daniele Pucci},
This paper contributes towards the development of motion tracking algorithms for time-critical applications, proposing an infrastructure for solving dynamically the inverse kinematics of highly articulate systems such as humans. We present a method based on the integration of differential kinematics using distance measurement on SO(3) for which the convergence is proved using Lyapunov analysis. An experimental scenario, where the motion of a human subject is tracked in static and dynamic… 

Figures from this paper

Whole-Body Geometric Retargeting for Humanoid Robots
This paper presents a framework for teleoperation of humanoid robots using a novel approach for motion retargeting through inverse kinematics over the robot model, which enhances scalability for Retargeting and enables an intuitive and natural interaction between the human operator and the humanoid robot at the configuration space level.
Partner-Aware Humanoid Robot Control: from Robot-Robot collaboration to Human-Robot Collaboration and Ergonomy Control
The success of robots in real-world applications is largely dependent on their ability to physically interact with the environment. A robotic agent should be endowed with the capabilities that
A Human Perception System for Robot Collaborative Tasks
Today’s humans need to collaborate with robots more and more frequently by sharing a common task space. The cooperation often translates into a physical collaboration, i.e., a context in which a
Enabling Human-Robot Collaboration via Holistic Human Perception and Partner-Aware Control
This thesis attempts to address some of the research challenges in enabling human-robot collaboration by methodically defining what constitutes assistance from a human partner and proposing partner-aware robot control strategies to endow robots with the capacity to meaningfully engage in a collaborative task.
Recent Advances in Human-Robot Collaboration Towards Joint Action
This article draws from the experience as roboticists in Human-Robot Collaboration with humanoid robots and presents some of the recent advances made towards realizing intuitive robot behaviors and partner-aware control involving physical interactions.
Whole-Body Human Kinematics Estimation using Dynamical Inverse Kinematics and Contact-Aided Lie Group Kalman Filter
—Full body motion estimation of a human through wearable sensing technologies is challenging in the absence of position sensors. This paper contributes to the development of a model-based whole-body
ADHERENT: Learning Human-like Trajectory Generators for Whole-body Control of Humanoid Robots
ADHERENT is presented, a system architecture integrating machine-learning methods used in computer graphics with whole-body control methods employed in robotics to generate and stabilize human-like trajectories for humanoid robots to be robust to varying step sizes and walking speeds.
Simultaneous Human Action and Motion Prediction
This paper presents a novel approach to solve simultaneously the problems of human whole-body motion prediction and action recognition for real-time applications using the notion of mixture of experts from deep learning literature.
The Human Wearable Perception System: a Human-Robot Collaboration Application
During the HRC, robots can make the human ergonomics better by embodying the human estimated quantities and adjusting their collaborative interaction strategy by adopting the human joint torques for the task ergonomy control.


Real-Time Inverse Kinematics Techniques for Anthropomorphic Limbs
A combination of analytical and numerical methods to solve generalized inverse kinematics problems including position, orientation, and aiming constraints suitable for an anthropomorphic arm or leg.
Survey of Motion Tracking Methods Based on Inertial Sensors: A Focus on Upper Limb Human Motion
Five techniques for motion reconstruction were selected and compared to reconstruct a human arm motion and results show that all but one of the selected models perform similarly (about 35 mm average position estimation error).
Motion capture with constrained inverse kinematics for real-time hand tracking
  • A. Aristidou, Joan Lasenby
  • Computer Science
    2010 4th International Symposium on Communications, Control and Signal Processing (ISCCSP)
  • 2010
A simple and efficient methodology for tracking and reconstructing 3d hand poses using a markered optical motion capture system that is real-time implementable and the results are promising, even with a low frame rate.
A solution algorithm to the inverse kinematic problem for redundant manipulators
Based on a recently proposed algorithmic solution technique, the inverse kinematic problem for redundant manipulators is solved. The kinematics of the manipulator is appropriately augmented to
A complete generalized solution to the inverse kinematics of robots
An iterative solution is presented that is suitable for any class of robots having rotary or prismatic joints, with any arbitrary number of degrees of freedom, including both standard and kinematically redundant robots.
FABRIK: A fast, iterative solver for the Inverse Kinematics problem
Online and markerless motion retargeting with kinematic constraints
An online task space control theoretic retargeting formulation to generate robot joint motions that adhere to the robotpsilas joint limit constraints, self-collision constraints, and balance constraints is presented.
Methods of Numerical Integration