2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2017
DOI: 10.1109/iros.2017.8206164
|View full text |Cite
|
Sign up to set email alerts
|

SUM: Sequential scene understanding and manipulation

Abstract: In order to perform autonomous sequential manipulation tasks, perception in cluttered scenes remains a critical challenge for robots. In this paper, we propose a probabilistic approach for robust sequential scene estimation and manipulation -Sequential Scene Understanding and Manipulation (SUM). SUM considers uncertainty due to discriminative object detection and recognition in the generative estimation of the most likely object poses maintained over time to achieve a robust estimation of the scene under heavy… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
27
0

Year Published

2019
2019
2022
2022

Publication Types

Select...
7
2

Relationship

1
8

Authors

Journals

citations
Cited by 36 publications
(27 citation statements)
references
References 36 publications
0
27
0
Order By: Relevance
“…However, some limitations occur regularly, including framing the segmentation problem in 2D or 2.5D space [13] (i.e. not estimating full volumetric occupancy), relying on pre-specified [14] or simple geometric models [15] in the scene, or restricting the belief about the scene to a unimodal representation, even if tracking is performed in a multimodal fashion [16]. Working in 3D, as opposed to 2D or 2.5D, is particularly important, as it allows us to construct and retain object geometry estimates in the presence of occlusion, which is frequent in cluttered scenes.…”
Section: Related Workmentioning
confidence: 99%
See 1 more Smart Citation
“…However, some limitations occur regularly, including framing the segmentation problem in 2D or 2.5D space [13] (i.e. not estimating full volumetric occupancy), relying on pre-specified [14] or simple geometric models [15] in the scene, or restricting the belief about the scene to a unimodal representation, even if tracking is performed in a multimodal fashion [16]. Working in 3D, as opposed to 2D or 2.5D, is particularly important, as it allows us to construct and retain object geometry estimates in the presence of occlusion, which is frequent in cluttered scenes.…”
Section: Related Workmentioning
confidence: 99%
“…Related work in sensor fusion via particle filter, which has been commonly used for non-linear state estimation, has seen various improvements on sampling sufficient valid states and avoiding degeneracy of the proposal distribution [33], [34]. Although these probabilistic methods have been used in manipulation [13], [14], they either only produce 2D estimates, or require prior knowledge of object models.…”
Section: Related Workmentioning
confidence: 99%
“…Discriminative-generative algorithms [25], [24], [12] offer a promising avenue for robust perception and action. Such methods combine inference by deep learning with sampling and probabilistic inference models, and the ability to represent actual and counterfactual experiments to achieve robust and adaptive understanding.…”
Section: Introductionmentioning
confidence: 99%
“…Generative-discriminative algorithms [7], [8] offer a promising avenue for robust perception. Such methods combine inference by deep learning (or other discriminative techniques) with sampling and probabilistic inference models to achieve robust and adaptive perception in adversarial environments.…”
Section: Introductionmentioning
confidence: 99%