Memory Unscented Particle Filter for 6-DOF Tactile Localization

Vezzani, Giulia; Pattacini, Ugo; Battistelli, Giorgio; Chisci, Luigi; Natale, Lorenzo

doi:10.1109/tro.2017.2707092

Cited by 37 publications

(23 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to sense the object’s feature, the first step is to search and localize the object. As showed in Table 3 , the reviewed approaches are classified into three categories, which are image-based approaches [ 107 , 108 ], point cloud-based approaches [ 109 ], and tactile perception-based approaches [ 110 , 111 , 112 ]. The first two approaches are relatively mature and could deal with the problem of multi-object search in a cluttered environment.…”

Section: Discussionmentioning

confidence: 99%

“…In contrast, the tactile perception-based approach obtains the realistic position information of unknown objects through the sense of touch, as humans do. The decision-theoretic approach [ 110 ] guides robotic actions by tactile feedback to search the object, while the Bayesian-based approach [ 111 ] can solve the 6DoFs localization problem by the measurement of contact points. Moreover, the active approach proposed in [ 112 ] enables the robot to explore the whole workspace and calculates the 3D minimum bounding box of the object.…”

Section: Discussionmentioning

confidence: 99%

“…The robotic actions are guided by tactile feedback to search the object and localizes the object by selection among the parameterized set of trajectories. Vezzani et al [ 111 ] introduced an effective Bayesian-based algorithm named Memory Unscented Particle Filter. This algorithm recursively solves the 6DoFs localizing problem in a timely way by the measurement of contact points.…”

Section: Unknown Objectsmentioning

confidence: 99%

See 2 more Smart Citations

Feature Sensing and Robotic Grasping of Objects with Uncertain Information: A Review

Wang

Zhang

Zang

et al. 2020

Sensors

View full text Add to dashboard Cite

As there come to be more applications of intelligent robots, their task object is becoming more varied. However, it is still a challenge for a robot to handle unfamiliar objects. We review the recent work on the feature sensing and robotic grasping of objects with uncertain information. In particular, we focus on how the robot perceives the features of an object, so as to reduce the uncertainty of objects, and how the robot completes object grasping through the learning-based approach when the traditional approach fails. The uncertain information is classified into geometric information and physical information. Based on the type of uncertain information, the object is further classified into three categories, which are geometric-uncertain objects, physical-uncertain objects, and unknown objects. Furthermore, the approaches to the feature sensing and robotic grasping of these objects are presented based on the varied characteristics of each type of object. Finally, we summarize the reviewed approaches for uncertain objects and provide some interesting issues to be more investigated in the future. It is found that the object’s features, such as material and compactness, are difficult to be sensed, and the object grasping approach based on learning networks plays a more important role when the unknown degree of the task object increases.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Unknown Objectsmentioning

confidence: 99%

See 1 more Smart Citation

Feature Sensing and Robotic Grasping of Objects with Uncertain Information: A Review

Wang

Zhang

Zang

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…where p(y k χ i k ) is the likelihood probability similar to measurement noise and p(χ i k y 1:k−1 ) is the prior probability. Usually, resampling is necessary for standard particle filters to avoid the degeneracy problem [37], but over resampling will result in particle diversity degradation [38]. Therefore, the unscented Kalman filter (UKF) is introduced into the standard particle filter for providing the proposal distribution q(χ k y 1:k ) .…”

Section: Misalignmentmentioning

confidence: 99%

A Fault-tolerant Steering Prototype for X-rudder Underwater Vehicles

Wang

Chen

Xia

et al. 2020

Sensors

View full text Add to dashboard Cite

The X-rudder concept has been applied to more and more autonomous underwater vehicles (AUVs) in recent years, since it shows better maneuverability and robustness against rudder failure compared to the traditional cruciform rudder. Aiming at the fault-tolerant control of the X-rudder AUV (hereinafter abbreviated as xAUV), a fault-tolerant steering prototype system which can realize dynamics control, autonomous rudder fault detection and fault-tolerant control is presented in this paper. The steering prototype system is deployed on a verification platform, an xAUV, in which the monitor software is developed based on the factory method and the onboard software is developed based on the finite state machine (FSM). Dual-loop increment feedback control (DIFC) is first introduced to obtain smooth virtual rudder commands considering actuator’s limitations. Then the virtual rudder commands are transformed into X-rudder commands based on the mapping theory. In rudder fault diagnosis, an optimized particle filter is proposed for estimating rudder effect deduction, with proposal distribution derived from unscented Kalman filter (UKF). Then the fault type can be determined by analyzing indicators related to the deduction. Fault-tolerant control is addressed by dealing with nonlinear programming (NLP) problem, where minimization of allocation errors and control efforts are set as the optimization objectives, and rudder failure, saturation and actuators limitations are considered as constraints. The fixed-point iteration method is utilized to solve this optimization problem. Many field tests have been conducted in towing tank. The experimental results demonstrate that the proposed steering prototype system is able to detect rudder faults and is robust against rudder failure.

show abstract

“…Their measurements were collected by making repeated contact with the object using a single end-eector. [Vezzani et al, 2017] proposed the Memory Unscented Particle Filter that combines a modied particle lter and the unscented Kalman lter.…”

Section: Related Workmentioning

confidence: 99%

Contributions to robotic manipulation under uncertainty : calibration, estimation, motion planning

Nguyễn¹

View full text Add to dashboard Cite

This thesis is the culmination of my journey of PhD which was just like climbing a high peak step by step accompanied with encouragement, hardship, trust, and frustration. At this moment of accomplishment, I realized though only my name appears on the cover of this dissertation, a great many people including my family members, my friends, colleagues and many more have contributed to accomplishing this journey. First and foremost, I would like to thank my supervisor Quang-Cuong Pham, who has gone above and beyond anything I could have expected from an advisor. I am thankful for his support, guidance in life and research during these years. Thanks to the good friends I have here in CRI group-Puttichai Lertkultanon, Francisco Suarez-Ruiz, Ahmad Bin Anwar, Tien Hung Pham and many more. You made my experience in the lab special and unforgettable. We have had a lot of great discussions about both research and non-research. I cherish all the good times that we have spent together. Also thanks to all Vietnamese friends I have here in NTU for the stimulating discussions, for all the badminton matches and for all the fun we have had in the last four years. Last but not least, I am eternally grateful to my Mom, Dad, Brother and my beloved in-laws for always believing in me and encouraging me to follow my dreams. Most importantly, a very special thanks to my loving wife, Chau Phan, for your unconditional, persistent love, for your support and understanding during my pursuit of PhD degree that made the completion of thesis possible. You were always around at times I thought that it was impossible to continue, you helped me to keep things in perspective. Without you, I would not have come this far.

show abstract

Memory Unscented Particle Filter for 6-DOF Tactile Localization

Cited by 37 publications

References 30 publications

Feature Sensing and Robotic Grasping of Objects with Uncertain Information: A Review

Feature Sensing and Robotic Grasping of Objects with Uncertain Information: A Review

A Fault-tolerant Steering Prototype for X-rudder Underwater Vehicles

Contributions to robotic manipulation under uncertainty : calibration, estimation, motion planning

Contact Info

Product

Resources

About