Learning Viewpoint Planning in Active Recognition on a Small Sampling Budget: A Kriging Approach

Defretin, Joseph; Marzat, Julien; Piet-Lahanier, Hélène

doi:10.1109/icmla.2010.32

Cited by 4 publications

(7 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Variations around EGO can be found in [10][11][12], and convergence results in [13]. Many successful applications of EGO in engineering have been reported, e.g., in [11,[14][15][16][17]. Kriging and EGO will serve as a basis for the study presented here.…”

Section: Introductionmentioning

confidence: 99%

Worst-case global optimization of black-box functions through Kriging and relaxation

Marzat

Walter²,

Piet-Lahanier

2012

J Glob Optim

Self Cite

View full text Add to dashboard Cite

International audienceA new algorithm is proposed to deal with the worst-case optimization of black-box functions evaluated through costly computer simulations. The input variables of these computer experiments are assumed to be of two types. Control variables must be tuned while environmental variables have an undesirable effect, to which the design of the control variables should be robust. The algorithm to be proposed searches for a minimax solution, i.e., values of the control variables that minimize the maximum of the objective function with respect to the environmental variables. The problem is particularly difficult when the control and environmental variables live in continuous spaces. Combining a relaxation procedure with Kriging-based optimization makes it possible to deal with the continuity of the variables and the fact that no analytical expression of the objective function is available in most real-case problems. Numerical experiments are conducted to assess the accuracy and efficiency of the algorithm, both on analytical test functions with known results and on an engineering application

show abstract

Section: Introductionmentioning

confidence: 99%

Worst-case global optimization of black-box functions through Kriging and relaxation

Marzat

Walter²,

Piet-Lahanier

2012

J Glob Optim

Self Cite

View full text Add to dashboard Cite

show abstract

“…Learning techniques are also utilized for active object recognition, in which a policy that maps states to actions is learned for increasing the discriminative information. A very common way of learning this policy is via reinforcement learning algorithms [25][26][27]. While designing our viewpoint optimization strategy for grasp synthesis, we applied a similar framework to [27] with the following differences:…”

Section: Related Workmentioning

confidence: 99%

“…In this way, even brief motions can provide the required information for a good grasp. This approach requires a different state description than [27].…”

Section: Related Workmentioning

confidence: 99%

Viewpoint optimization for aiding grasp synthesis algorithms using reinforcement learning

et al. 2018

View full text Add to dashboard Cite

Grasp synthesis for unknown objects is a challenging problem as the algorithms are expected to cope with missing object shape information. This missing information is a function of the vision sensor viewpoint. The majority of the grasp synthesis algorithms in literature synthesize a grasp by using one single image of the target object and making assumptions on the missing shape information. On the contrary, this paper proposes the use of robot's depth sensor actively: we propose an active vision methodology that optimizes the viewpoint of the sensor for increasing the quality of the synthesized grasp over time. By this way we aim to relax the assumptions on the sensor's viewpoint and boost the success rates of the grasp synthesis algorithms. A reinforcement learning technique is employed to obtain a viewpoint optimization policy, and a training process and automated training data generation procedure are presented. The methodology is applied to a simple force-moment balance-based grasp synthesis algorithm, and a thousand simulations with five objects are conducted with random initial poses in which the grasp synthesis algorithm was not able to obtain a good grasp with the initial viewpoint. In 94% of these cases, the policy achieved to find a successful grasp.

show abstract

“…In the active object recognition, the duty of the active vision algorithm is to alter the sensor viewpoint for maximizing the recognition rate. The algorithms in the literature (e.g., [3] and [14]- [16]) rely on offline training data for conducting viewpoint optimization, which makes them sensitive to structured noise (e.g., occlusions, extreme lighting conditions). In addition, most of these algorithms employ discrete search techniques, and do not utilize the data between the way points.…”

Section: Introductionmentioning

confidence: 99%

Active Vision via Extremum Seeking for Robots in Unstructured Environments: Applications in Object Recognition and Manipulation

Çallı

Caarls

Wisse

et al. 2018

IEEE Trans. Automat. Sci. Eng.

View full text Add to dashboard Cite

In this paper, a novel active vision strategy is proposed for optimizing the viewpoint of a robot's vision sensor for a given success criterion. The strategy is based on extremum seeking control (ESC), which introduces two main advantages: 1) Our approach is model free: It does not require an explicit objective function or any other task model to calculate the gradient direction for viewpoint optimization. This brings new possibilities for the use of active vision in unstructured environments, since a priori knowledge of the surroundings and the target objects is not required. 2) ESC conducts continuous optimization backed up with mechanisms to escape from local maxima. This enables an efficient execution of an active vision task. We demonstrate our approach with two applications in the object recognition and manipulation fields, where the modelfree approach brings various benefits: for object recognition, our framework removes the dependence on offline training data for viewpoint optimization, and provides robustness of the system to occlusions and changing lighting conditions. In object manipulation, the model-free approach allows us to increase the success rate of a grasp synthesis algorithm without the need of an object model; the algorithm only uses continuous measurements of the objective value, i.e., the grasp quality. Our experiments show that continuous viewpoint optimization can efficiently increase the data quality for the underlying algorithm, while maintaining the robustness. Note to Practitioners-Vision sensors provide robots flexibility and robustness both in industrial and domestic settings by supplying required data to analyze the surroundings and the state of the task. However, the quality of these data can be very high or poor depending on the viewing angle of the vision sensor.

show abstract

Learning Viewpoint Planning in Active Recognition on a Small Sampling Budget: A Kriging Approach

Cited by 4 publications

References 15 publications

Worst-case global optimization of black-box functions through Kriging and relaxation

Worst-case global optimization of black-box functions through Kriging and relaxation

Viewpoint optimization for aiding grasp synthesis algorithms using reinforcement learning

Active Vision via Extremum Seeking for Robots in Unstructured Environments: Applications in Object Recognition and Manipulation

Contact Info

Product

Resources

About