Human arm motion planning against a joint constraint

Moon, Hyosang; Hoang, Nguyen H.; Robson, Nina; Langari, Reza

doi:10.1109/biorob.2012.6290923

Cited by 10 publications

(5 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As an extension of previous works (see [2,10]), this paper focuses on the governing strategies of a constrained arm posture selection in human arm reaching from an experimental observation approach. The novelty of this work is at the imposed kinematic constraint on the elbow joint DOF.…”

Section: Introductionmentioning

confidence: 99%

An experimental study on redundancy resolution scheme of postural configuration in human arm reaching with an elbow joint kinematic constraint

Moon

Robson

Langari

et al. 2014

2nd Middle East Conference on Biomedical Engineering

Self Cite

View full text Add to dashboard Cite

This paper studies the redundancy resolution strategy of the central nervous system (CNS) in selecting an arm posture during reaching motions. Based on the assumption that such governing rules are preserved against any joint constraint condition, an elbow joint DOF was fixed during the experiments with a light weight elbow brace. Two different coordinate systems are defined to interpret kinematics and dynamics of motion in a task-oriented space and an internal body space. The kinematic and dynamic contributions of the internal body frame on the task frame, is quantified by mappings. The experimental results show that the core principle of the CNS to determine the arm posture is to minimize the kinetic energy cost.

show abstract

Section: Introductionmentioning

confidence: 99%

An experimental study on redundancy resolution scheme of postural configuration in human arm reaching with an elbow joint kinematic constraint

Moon

Robson

Langari

et al. 2014

2nd Middle East Conference on Biomedical Engineering

Self Cite

View full text Add to dashboard Cite

show abstract

“…In these cases, individuals tend to take the path that minimizes the distance and energy required for the movement. This has been observed in different studies (Moon et al 2012;Klein et al 2022). Therefore, we resort to learning-fromdemonstration (LfD) to build a model of robot motions, a technique in which the skill model is learned by encapsulating motion patterns from human demonstrations (Osa et al 2018).…”

Section: Introductionmentioning

confidence: 99%

Reactive motion generation on learned Riemannian manifolds

Beik-Mohammadi,

Hauberg,

Arvanitidis

et al. 2023

The International Journal of Robotics Research

View full text Add to dashboard Cite

In recent decades, advancements in motion learning have enabled robots to acquire new skills and adapt to unseen conditions in both structured and unstructured environments. In practice, motion learning methods capture relevant patterns and adjust them to new conditions such as dynamic obstacle avoidance or variable targets. In this paper, we investigate the robot motion learning paradigm from a Riemannian-manifold perspective. We argue that Riemannian manifolds may be learned via human demonstrations in which geodesics are natural motion skills. The geodesics are generated using a learned Riemannian metric produced by our novel variational autoencoder (VAE), which is intended to recover full-pose end-effector states and joint-space configurations. In addition, we propose a technique for facilitating on-the-fly end-effector/multiple-limb obstacle avoidance by reshaping the learned manifold using an obstacle-aware ambient metric. The motion generated using these geodesics may naturally result in multiple-solution tasks that have not been explicitly demonstrated previously. We extensively tested our approach in task-space and joint-space scenarios using a 7-DoF robotic manipulator. We demonstrate that our method is capable of learning and generating motion skills based on complicated motion patterns demonstrated by a human operator. Additionally, we assess several obstacle-avoidance strategies and generate trajectories in multiple-mode settings.

show abstract

“…However, despite significant advances in recent decades, existing assistive devices are constrained by limited portability, safety, ergonomics, autonomy, and cost. This is partly due to the attempts in aligning each robotic joint axis with its human counterpart (e.g., a hinge joint for the elbow and knee Figure 1 (a)) [5][6][7]. As the axis must be external to the human joint, it may add complexity and weight to the design.…”

Section: Introductionmentioning

confidence: 99%

Design of a Novel Task-Based Knee Rehabilitation Exoskeleton Device

Adhikari

Yihun

Lankarani

2018

2018 Design of Medical Devices Conference

View full text Add to dashboard Cite

This study is aimed at the design of a novel task-based knee rehabilitation device. The desired trajectories of the knee have been obtained through a vision-based motion capture system. The collected experimental kinematic data has been used as an input to a spatial mechanism synthesis procedure. Parallel mechanisms with single degree-of-freedom (DOF) have been considered to generate the complex 3D motions of the lower leg. An exact workspace synthesis approach is utilized, in which the parameterized forward kinematics equations of each serial chains of the parallel mechanisms are to be converted into implicit equations via elimination. The implicit description of the workspace is made to be a function of the structural parameters of the serial chain, making it easy to relate those parameters to the desired trajectory. The selected mechanism has been verified for the accuracy of its trajectory through CAD modeling and simulations. This design approach reduces alignment and fitting challenges in an exoskeleton as the mechanism does not require alignment of each robotic joint axis with its human counterpart.

show abstract

Human arm motion planning against a joint constraint

Cited by 10 publications

References 16 publications

An experimental study on redundancy resolution scheme of postural configuration in human arm reaching with an elbow joint kinematic constraint

An experimental study on redundancy resolution scheme of postural configuration in human arm reaching with an elbow joint kinematic constraint

Reactive motion generation on learned Riemannian manifolds

Design of a Novel Task-Based Knee Rehabilitation Exoskeleton Device

Contact Info

Product

Resources

About