Computer Vision-Based Pose Estimation of Tensegrity Robots Using Fiducial Markers

Moldagalieva, Akmaral; Fadeyev, Denis; Kuzdeuov, Askat; Khan, Valeriya; Alimzhanov, Bexultan; Varol, Hüseyin Atakan

doi:10.1109/sii.2019.8700452

Cited by 6 publications

(4 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In fact, Baron and Angeles [46] were the first to propose using a camera that is mounted on the fixed base platform in addition to the six length sensors to solve the direct kinematics problem of the Stewart-Gough platform. In 2019, Moldagalieva et al [47] used the improvements in visual fiducial tags in terms of recognition and pose detection to estimate the pose of a tensegrity manipulator. Using tag sizes of 5.6 cm and a distance between the camera and the tags of 1.5 m, Moldagalieva et al [47] realized a RMS position error of 2.3 cm with a standard deviation of 1.4 cm and a RMS orientation error of 7.5 • with a standard deviation of 3.14 • .…”

Section: Direct Image-based Pose Calculationmentioning

confidence: 99%

“…In 2019, Moldagalieva et al [47] used the improvements in visual fiducial tags in terms of recognition and pose detection to estimate the pose of a tensegrity manipulator. Using tag sizes of 5.6 cm and a distance between the camera and the tags of 1.5 m, Moldagalieva et al [47] realized a RMS position error of 2.3 cm with a standard deviation of 1.4 cm and a RMS orientation error of 7.5 • with a standard deviation of 3.14 • . Kuzdeuov et al [48] further improved this concept by adding a feed-forward neural network and a sensor fusion concept.…”

Section: Direct Image-based Pose Calculationmentioning

confidence: 99%

“…For localization purposes, however, the robots usually have working ranges of several centimeters or even meters, so that smaller errors in the micro-or nanometer range are not significant in these applications or do not significantly affect the results of the pose detection. In fact, the sizes of the visual fiducial tags range from 5.6 cm (in [47]) to 0.7 m (in [54]) in the previously mentioned applications, while the distance between camera and object range from 0.4 m (in [58]) to 30 m (in [54]).…”

Section: Direct Image-based Pose Calculationmentioning

confidence: 99%

See 2 more Smart Citations

High-Precision Absolute Pose Sensing for Parallel Mechanisms

Schempp

Schulz

2022

Sensors

View full text Add to dashboard Cite

A parallel mechanism’s pose is usually obtained indirectly from the active joints’ coordinates by solving the direct kinematics problem. Its accuracy mainly depends on the accuracy of the measured active joints’ coordinates, the tolerances in the active and passive joints, possible backlash, axes misalignment, limb deformations due to stress or temperature, the initial pose estimate that is used for the numerical method, and the accuracy of the kinematic model itself. Backlash and temperature deformations in the active joints especially hinder high-precision applications as they usually cannot be observed. By implementing a camera module on the base platform and an array of fiducial tags on the moveable manipulator platform of a parallel mechanism, a highly accurate, direct, and absolute pose measurement system can be obtained that can overcome those limitations. In this paper, such a measurement system is proposed, designed, and its accuracy is investigated on a state-of-the-art H-811.I2 6-axis miniature hexapod by Physik Instrumente (PI) GmbH & Co. KG.

show abstract

Section: Direct Image-based Pose Calculationmentioning

confidence: 99%

Section: Direct Image-based Pose Calculationmentioning

confidence: 99%

Section: Direct Image-based Pose Calculationmentioning

confidence: 99%

See 1 more Smart Citation

High-Precision Absolute Pose Sensing for Parallel Mechanisms

Schempp

Schulz

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…More recently, Moldagalieva et al [16] proposed the first vision-based method to estimate the pose of a tensegrity robot using fiducial markers. In particular, a hemispherical camera module was attached to the base of their robot, so as to track the fiducial markers printed on a triangle-shaped plate fixed at the upper part of the robot.…”

Section: Related Workmentioning

confidence: 99%

6N-DoF Pose Tracking for Tensegrity Robots

Lu¹,

Johnson²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Tensegrity robots, which are composed of rigid compressive elements (rods) and flexible tensile elements (e.g., cables), have a variety of advantages, including flexibility, light weight, and resistance to mechanical impact. Nevertheless, the hybrid soft-rigid nature of these robots also complicates the ability to localize and track their state. This work aims to address what has been recognized as a grand challenge in this domain, i.e., the pose tracking of tensegrity robots through a marker-less, vision-based method, as well as novel, on-board sensors that can measure the length of the robot's cables. In particular, an iterative optimization process is proposed to estimate the 6-DoF poses of each rigid element of a tensegrity robot from an RGB-D video as well as endcap distance measurements from the cable sensors. To ensure the pose estimates of rigid elements are physically feasible, i.e., they are not resulting in collisions between rods or with the environment, physical constraints are introduced during the optimization. Real-world experiments are performed with a 3-bar tensegrity robot, which performs locomotion gaits. Given ground truth data from a motion capture system, the proposed method achieves less than 1 cm translation error and 3 degrees rotation error, which significantly outperforms alternatives. At the same time, the approach can provide pose estimates throughout the robot's motion, while motion capture often fails due to occlusions.

show abstract