| 1. |
|
|
| 2. |
- De Farias, Cristiana, et al.
(author)
-
Simultaneous Tactile Exploration and Grasp Refinement
- 2022
-
Conference paper (other academic/artistic)abstract
- In this work, we present a method for simultaneous exploration and grasping of unknown objects by combining tactile and visual information. In many robotic applications, visual data is incomplete due to occlusions. We show how Gaussian processes implicit surfaces (GPIS) can be used to model an initial representation of shape from visual information. This perceived partial model can then be augmented from tactile glances obtained during grasp attempts. Finally, grasp planning is done by means of a bi-objective optimisation method, in which we simultaneously optimise the grasp probability of success and improve the object’s shape representation during the execution of successive grasps. Experimental results in simulation demonstrate the efficiency of our approach.
|
|
| 3. |
- De Farias, Cristiana, et al.
(author)
-
Simultaneous Tactile Exploration and Grasp Refinement for Unknown Objects
- 2021
-
In: IEEE Robotics and Automation Letters. - 2377-3766. ; 6:2, s. 3349-3356
-
Journal article (peer-reviewed)abstract
- This letter addresses the problem of simultaneously exploring an unknown object to model its shape, using tactile sensors on robotic fingers, while also improving finger placement to optimise grasp stability. In many situations, a robot will have only a partial camera view of the near side of an observed object, for which the far side remains occluded. We show how an initial grasp attempt, based on an initial guess of the overall object shape, yields tactile glances of the far side of the object which enable the shape estimate and consequently the successive grasps to be improved. We propose a grasp exploration approach using a probabilistic representation of shape, based on Gaussian Process Implicit Surfaces. This representation enables initial partial vision data to be augmented with additional data from successive tactile glances. This is combined with a probabilistic estimate of grasp quality to refine grasp configurations. When choosing the next set of finger placements, a bi-objective optimisation method is used to mutually maximise grasp quality and improve shape representation during successive grasp attempts. Experimental results show that the proposed approach yields stable grasp configurations more efficiently than a baseline method, while also yielding improved shape estimate of the grasped object.
|
|
| 4. |
- De Farias, Cristiana, et al.
(author)
-
Simultaneous Tactile Exploration and Grasp Refinement for Unknown Objects
- 2022
-
In: Proceedings - IEEE International Conference on Robotics and Automation. - 1050-4729.
-
Conference paper (peer-reviewed)abstract
- This letter addresses the problem of simultaneously exploring an unknown object to model its shape, using tactile sensors on robotic fingers, while also improving finger placement to optimise grasp stability. In many situations, a robot will have only a partial camera view of the near side of an observed object, for which the far side remains occluded. We show how an initial grasp attempt, based on an initial guess of the overall object shape, yields tactile glances of the far side of the object which enable the shape estimate and consequently the successive grasps to be improved. We propose a grasp exploration approach using a probabilistic representation of shape, based on Gaussian Process Implicit Surfaces. This representation enables initial partial vision data to be augmented with additional data from successive tactile glances. This is combined with a probabilistic estimate of grasp quality to refine grasp configurations. When choosing the next set of finger placements, a bi-objective optimisation method is used to mutually maximise grasp quality and improve shape representation during successive grasp attempts. Experimental results show that the proposed approach yields stable grasp configurations more efficiently than a baseline method, while also yielding improved shape estimate of the grasped object.
|
|
| 5. |
- Gandler, Gabriela Zarzar, et al.
(author)
-
Object shape estimation and modeling, based on sparse Gaussian process implicit surfaces, combining visual data and tactile exploration
- 2020
-
In: Robotics and Autonomous Systems. - : ELSEVIER. - 0921-8890 .- 1872-793X. ; 126
-
Journal article (peer-reviewed)abstract
- Inferring and representing three-dimensional shapes is an important part of robotic perception. However, it is challenging to build accurate models of novel objects based on real sensory data, because observed data is typically incomplete and noisy. Furthermore, imperfect sensory data suggests that uncertainty about shapes should be explicitly modeled during shape estimation. Such uncertainty models can usefully enable exploratory action planning for maximum information gain and efficient use of data. This paper presents a probabilistic approach for acquiring object models, based on visual and tactile data. We study Gaussian Process Implicit Surface (GPIS) representation. GPIS enables a non-parametric probabilistic reconstruction of object surfaces from 3D data points, while also providing a principled approach to encode the uncertainty associated with each region of the reconstruction. We investigate different configurations for GPIS, and interpret an object surface as the level-set of an underlying sparse GP. Experiments are performed on both synthetic data, and also real data sets obtained from two different robots physically interacting with objects. We evaluate performance by assessing how close the reconstructed surfaces are to ground-truth object models. We also evaluate how well objects from different categories are clustered, based on the reconstructed surface shapes. Results show that sparse GPs enable a reliable approximation to the full GP solution, and the proposed method yields adequate surface representations to distinguish objects. Additionally the presented approach is shown to provide computational efficiency, and also efficient use of the robot's exploratory actions.
|
|
| 6. |
- Kristan, Matej, et al.
(author)
-
The Visual Object Tracking VOT2013 challenge results
- 2013
-
In: 2013 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW). - : IEEE. - 9781479930227 ; , s. 98-111
-
Conference paper (peer-reviewed)abstract
- Visual tracking has attracted a significant attention in the last few decades. The recent surge in the number of publications on tracking-related problems have made it almost impossible to follow the developments in the field. One of the reasons is that there is a lack of commonly accepted annotated data-sets and standardized evaluation protocols that would allow objective comparison of different tracking methods. To address this issue, the Visual Object Tracking (VOT) workshop was organized in conjunction with ICCV2013. Researchers from academia as well as industry were invited to participate in the first VOT2013 challenge which aimed at single-object visual trackers that do not apply pre-learned models of object appearance (model-free). Presented here is the VOT2013 benchmark dataset for evaluation of single-object visual trackers as well as the results obtained by the trackers competing in the challenge. In contrast to related attempts in tracker benchmarking, the dataset is labeled per-frame by visual attributes that indicate occlusion, illumination change, motion change, size change and camera motion, offering a more systematic comparison of the trackers. Furthermore, we have designed an automated system for performing and evaluating the experiments. We present the evaluation protocol of the VOT2013 challenge and the results of a comparison of 27 trackers on the benchmark dataset. The dataset, the evaluation tools and the tracker rankings are publicly available from the challenge website(1).
|
|
| 7. |
- Kristan, Matej, et al.
(author)
-
The Visual Object Tracking VOT2016 Challenge Results
- 2016
-
In: COMPUTER VISION - ECCV 2016 WORKSHOPS, PT II. - Cham : SPRINGER INT PUBLISHING AG. - 9783319488813 - 9783319488806 ; , s. 777-823
-
Conference paper (peer-reviewed)abstract
- The Visual Object Tracking challenge VOT2016 aims at comparing short-term single-object visual trackers that do not apply pre-learned models of object appearance. Results of 70 trackers are presented, with a large number of trackers being published at major computer vision conferences and journals in the recent years. The number of tested state-of-the-art trackers makes the VOT 2016 the largest and most challenging benchmark on short-term tracking to date. For each participating tracker, a short description is provided in the Appendix. The VOT2016 goes beyond its predecessors by (i) introducing a new semi-automatic ground truth bounding box annotation methodology and (ii) extending the evaluation system with the no-reset experiment.
|
|
| 8. |
- Marturi, Naresh, et al.
(author)
-
Towards advanced robotic manipulation for nuclear decommissioning
- 2017
-
In: Robots Operating in Hazardous Environments, InTechOpen. - : InTech.
-
Book chapter (other academic/artistic)abstract
- Despite enormous remote handling requirements, remarkably very few robots are being used by the nuclear industry. Most of the remote handling tasks are still performed manually, using conventional mechanical master‐slave devices. The few robotic manipulators deployed are directly tele‐operated in rudimentary ways, with almost no autonomy or even a pre‐programmed motion. In addition, majority of these robots are under‐sensored (i.e. with no proprioception), which prevents them to use for automatic tasks. In this context, primarily this chapter discusses the human operator performance in accomplishing heavy‐duty remote handling tasks in hazardous environments such as nuclear decommissioning. Multiple factors are evaluated to analyse the human operators’ performance and workload. Also, direct human tele‐operation is compared against human‐supervised semi‐autonomous control exploiting computer vision. Secondarily, a vision‐guided solution towards enabling advanced control and automating the under‐sensored robots is presented. Maintaining the coherence with real nuclear scenario, the experiments are conducted in the lab environment and results are discussed.
|
|
| 9. |
- Marturi, Naresh, et al.
(author)
-
Towards advanced robotic manipulation for nuclear decommissioning: A pilot study on tele-operation and autonomy
- 2016
-
In: IEEE International Conference on Robotics and Automation for Humanitarian Applications (RAHA). - 9781509052035
-
Conference paper (peer-reviewed)abstract
- We present early pilot-studies of a new international project, developing advanced robotics to handle nuclear waste. Despite enormous remote handling requirements, there has been remarkably little use of robots by the nuclear industry. The few robots deployed have been directly teleoperated in rudimentary ways, with no advanced control methods or autonomy. Most remote handling is still done by an aging workforce of highly skilled experts, using 1960s style mechanical Master-Slave devices. In contrast, this paper explores how novice human operators can rapidly learn to control modern robots to perform basic manipulation tasks; also how autonomous robotics techniques can be used for operator assistance, to increase throughput rates, decrease errors, and enhance safety. We compare humans directly teleoperating a robot arm, against human-supervised semi-autonomous control exploiting computer vision, visual servoing and autonomous grasping algorithms. We show how novice operators rapidly improve their performance with training; suggest how training needs might scale with task complexity; and demonstrate how advanced autonomous robotics techniques can help human operators improve their overall task performance. An additional contribution of this paper is to show how rigorous experimental and analytical methods from human factors research, can be applied to perform principled scientific evaluations of human test-subjects controlling robots to perform practical manipulative tasks.
|
|
| 10. |
|
|
