Adapting human motion for the control of a humanoid robot

Pollard, Nancy S.; Hodgins, Jessica K.; Riley, Marcia; Atkeson, Christopher G.

doi:10.1109/robot.2002.1014737

Cited by 259 publications

(142 citation statements)

References 7 publications

Supporting

Mentioning

138

Contrasting

Unclassified

Order By: Relevance

“…Some studies have been also done in order to generate human-like motion by imitating human arm motion as closely as possible. In most of these studies, the human motion is measured using a motion capture system and then converted to motion for a humanoid robot arm [24]. In [13], a method was proposed to convert the captured marker data of human arm motions to robot motion using an optimization scheme.…”

Section: Bio-inspired Methods To Resolve Redundancymentioning

confidence: 99%

See 1 more Smart Citation

Closed-Form Inverse Kinematic Solution for Anthropomorphic Motion in Redundant Robot Arms

Artemiadis

2013

Adv Robot Autom

View full text Add to dashboard Cite

As robots are increasingly migrating out of factories and research laboratories and into our everyday lives, they should move and act in environments designed for humans.For this reason, the need of anthropomorphic movements is of utmost importance. The objective of this thesis is to solve the inverse kinematics problem of redundant robot arms that results to anthropomorphic configurations. The swivel angle of the elbow was used as a human arm motion parameter for the robot arm to mimic. The swivel angle is defined as the rotation angle of the plane defined by the upper and lower arm around a virtual axis that connects the shoulder and wrist joints. Using kinematic data recorded from human subjects during every-day life tasks, the linear sensorimotor transformation model was validated and used to estimate the swivel angle, given the desired end-effector position. Defining the desired swivel angle simplifies the kinematic redundancy of the robot arm. The proposed method was tested with an anthropomorphic redundant robot arm and the computed motion profiles were compared to the ones of the human subjects. This thesis shows that the method computes anthropomorphic configurations for the robot arm, even if the robot arm has different link lengths than the human arm and starts its motion at random configura-

show abstract

Section: Bio-inspired Methods To Resolve Redundancymentioning

confidence: 99%

“…There have been efforts to generate human-like motion by imitating the human arm as closely as possible [13]. Similarly, some works are based on minimizing posture differences between the robot and human arm, using a specific recorded data set [3,24]. Therefore, the robot configurations are exclusively based on the recorded data set.…”

Section: Introductionmentioning

confidence: 99%

Closed-Form Inverse Kinematic Solution for Anthropomorphic Motion in Redundant Robot Arms

Artemiadis

2013

Adv Robot Autom

View full text Add to dashboard Cite

show abstract

“…The motion is studied regardless to what produced it. In robotics kinematics analysis are needed to plan a robot motion with respect to the work space geometric configuration and satisfying angular and geometric constraints that the system could be subject to (Pollard et al, 2002). Kinematics is forward or inverse: In forward kinematics the mechanism motions are known while the end effectors positions need to be computed.…”

Section: Inverse Kinematicsmentioning

confidence: 99%

“…Due to these reasons, it is easier to plan motion in the Cartesian frame, since it is the physical frame of the environment. Then an inverse transformation is needed to compute the needed displacements in the joints frames prior to control (Pollard et al, 2002;Rokbani et al, 2007), such a technique is also used in 3D character animation or gaming applications. In humanoid robotics and 3D humanoids simulations, the human motion analysis was a key source of inspirations for walking gaits, arms motions, grasping (Wang and Popović, 2009;Tolani et al, 2000), body postures and biped walking (Azevedo et al, 2004;Ammar et al, 2013).…”

Section: Introductionmentioning

confidence: 99%

IK-FA, a New Heuristic Inverse Kinematics Solver Using Firefly Algorithm

Rokbani

Casals

Alimi

2014

Studies in Computational Intelligence

View full text Add to dashboard Cite

In this paper, a heuristic method based on Firefly Algorithm is proposed for inverse kinematics problems in articulated robotics, the proposal is called, IK-FA. Solving inverse kinematics, IK, consists in finding a set of jointpositions allowing a specific point of the system to achieve a target position. In IK-FA, the Fireflies positions are assumed to be a possible solution for joints elementary motions. For a robotic system with a known forward kinematic model, IK-Fireflies, is used to generate iteratively a set of joint motions, then the forward kinematic model of the system is used to compute the relative Cartesian positions of a specific end-segment, and to compare it to the needed target position. This is a heuristic approach for solving inverse kinematics without computing the inverse model. IK-FA tends to minimize the distance to a target position, the fitness function could be established as the distance between the obtained forward positions and the desired one, it is subject to minimization. In this paper IK-FA is tested over a 2 links and 3 links articulated planar system, the evaluation is based on statistical analysis of the convergence and the solution quality for 100 tests. The impact of key FA parameters is also investigated with a focus on the impact of the number of fireflies, the impact of the maximum iteration number and also the impact of (α, β, γ, δ) parameters. For a given set of valuable parameters, the heuristic converges to a static fitness value within a fix maximum number of iterations. IK-FA has a fair convergence time, for the tested configuration, the average was about (2.3394 3 10 − ) seconds with a position error around (3.116 8 10 − ) for 100 tests. The algorithm showed also evidence of robustness over the target position, since for all conducted tests with a random target position IK-FA achieved a solution with a position error lower or equal to 5.4722 9 10 − .

show abstract

“…For instance, gesture replication by Gaertner et al [16] employed non-linear optimization to satisfy mechanical limits of the robot and desired hand positions and maximize angular similarity between human and a robot. Pollard et al [17] scaled each joint's angular trajectory locally in order to satisfy joint limits of the robot. Ott et al [18] achieved motion imitation by using Cartesian tracking.…”

Section: Introductionmentioning

confidence: 99%