Omnidirectional visual control of mobile robots based on the 1D trifocal tensor

Becerra, Héctor M.; López‐Nicolás, Gonzalo; Sagüés, Carlos

doi:10.1016/j.robot.2010.02.011

Cited by 32 publications

(25 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, the tensor elements are a function of the current camera-robot state x. Details about the expression of each element of the 1-D TT can be verified in [16] and [8]. It is worth mentioning that, in practice, it is necessary to normalize the tensor elements in order to fix a scale, which means to divide each element by a nonnull factor.…”

Section: B 1-d Tt As Visual Measurementmentioning

confidence: 99%

“…The 2-D TT has been introduced for visual control of mobile robots using an overconstrained controller, which may suffer from local minima problems [7]. This is overcome in [8] by defining a square control system and by using direct feedback of the elements of the 1-D TT in a two-step switching control law. The use of more than two views in VS provides robustness as well as enough information to correct depth from visual feedback, which is not possible from two views.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Exploiting the Trifocal Tensor in Dynamic Pose Estimation for Visual Control

Becerra

Sagüés

2013

IEEE Trans. Contr. Syst. Technol.

View full text Add to dashboard Cite

Image-based approaches for visual control are memoryless, and they depend on the information extracted from the image plane. We propose the use of dynamic pose estimation in the task of driving a mobile robot to a desired location specified by a target image. This approach reduces the dependence of the control on the quality of current visual data and facilitates the planning of complex tasks. The pose estimation exploits the 1-D trifocal tensor (TT) as measurement, which allows us to obtain a semicalibrated estimation scheme that is valid for any visual sensor obeying a central projection model. The contribution of this brief is a novel observability analysis of the estimation problem from the 1-D TT using nonlinear tools, as well as the demonstration of the validity of closed-loop control from the estimated pose by showing a separation principle in our nonlinear framework. The overall position-based scheme drives the robot to a desired pose through smooth velocities without the need of a target model, either scene reconstruction or depth information. The effectiveness of the approach is evaluated via real-world experiments.

show abstract

Section: B 1-d Tt As Visual Measurementmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Exploiting the Trifocal Tensor in Dynamic Pose Estimation for Visual Control

Becerra

Sagüés

2013

IEEE Trans. Contr. Syst. Technol.

View full text Add to dashboard Cite

show abstract

“…37 From the information provided by the 1D trifocal tensor entries, we can obtain the distance to the target location as follows:…”

Section: One-dimensional Trifocal Tensor-based Depth Correctionmentioning

confidence: 99%

Sinusoidal input-based visual control for nonholonomic vehicles

2013

Self Cite

View full text Add to dashboard Cite

This paper proposes a new visual control approach based on sinusoidal inputs to be used on a nonholonomic robot. We present several contributions: In our method, developed considering a unicycle kinematic model, sinusoids are used in such a way that the generated vehicle trajectories are feasible, smooth and versatile. Our technique improves previous sinusoidal-based control works in terms of efficiency and flexibility. As further contributions, we present analytical expressions for the evolution of the robot's state, and propose a new state-feedback control law based on these expressions. All the information used in the control scheme is obtained from omnidirectional vision by means of the onedimensional trifocal tensor. Stability analysis of the proposed approach is presented, and its performance is illustrated through experiments.

show abstract

“…Note that there are many other works aimed at the visual homing problem, but using different strategies such as [15] and later [16], which relied on the 1D trifocal tensor from the omnidirectional camera. Further, [17] used a sliding-mode control law to exploit the epipolar geometry; [18] directly calculates the homographies from raw images and so on.…”

Section: Related Workmentioning

confidence: 99%

Scale-only visual homing from an omnidirectional camera

Liu

Pradalier

Pomerleau

et al. 2012

2012 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

Abstract-Visual Homing is the process by which a mobile robot moves to a Home position using only information extracted from visual data. The approach we present in this paper uses image keypoints (e.g. SIFT) extracted from omnidirectional images and matches the current set of keypoints with the set recorded at the Home location. In this paper, we first formulate three different visual homing problems using uncalibrated omnidirectional camera within the Image Based Visual Servoing (IBVS) framework; then we propose a novel simplified homing approach, which is inspired by IBVS, based only on the scale information of the SIFT features, with its computational cost linear to the number of features.This paper reports on the application of our method on a commonly cited indoor database where it outperforms other approaches. We also briefly present results on a real robot and allude on the integration into a topological navigation framework.

show abstract

Omnidirectional visual control of mobile robots based on the 1D trifocal tensor

Cited by 32 publications

References 22 publications

Exploiting the Trifocal Tensor in Dynamic Pose Estimation for Visual Control

Exploiting the Trifocal Tensor in Dynamic Pose Estimation for Visual Control

Sinusoidal input-based visual control for nonholonomic vehicles

Scale-only visual homing from an omnidirectional camera

Contact Info

Product

Resources

About