Multi Robot Object-Based SLAM

Choudhary, Siddharth; Carlone, Luca; Nieto, Carlos; Rogers, John G.; Liu, Zhen; Christensen, Henrik I.; Dellaert, Frank

doi:10.1007/978-3-319-50115-4_63

Cited by 23 publications

(19 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cloud computing is a key enabler for solving these challenges. The idea is to design and create the architecture in which the multi-robot system uses the benefits of converged infrastructure and the resources of the cloud (information, memory, communication, and other) [32][33][34][35][36]. In practice, this usually means that on the cloud level gathering of information and their processing is performed, while the robots, as cloud service users, obtain only data and commands necessary for a direct execution of the allocated tasks.…”

Section: System Overviewmentioning

confidence: 99%

Cloud-Based Multi-Robot Path Planning in Complex and Crowded Environment with Multi-Criteria Decision Making Using Full Consistency Method

2019

View full text Add to dashboard Cite

The progress in the research of various areas of robotics, artificial intelligence, and other similar scientific disciplines enabled the application of multi-robot systems in different complex environments and situations. It is necessary to elaborate the strategies regarding the path planning and paths coordination well in order to efficiently execute a global mission in common environment, prior to everything. This paper considers the multi-robot system based on the cloud technology with a high level of autonomy, which is intended for execution of tasks in a complex and crowded environment. Cloud approach shifts computation load from agents to the cloud and provides powerful processing capabilities to the multi-robot system. The proposed concept uses a multi-robot path planning algorithm that can operate in an environment that is unknown in advance. With the aim of improving the efficiency of path planning, the implementation of Multi-criteria decision making (MCDM) while using Full consistency method (FUCOM) is proposed. FUCOM guarantees the consistent determination of the weights of factors affecting the robots motion to be symmetric or asymmetric, with respect to the mission specificity that requires the management of multiple risks arising from different sources, optimizing the global cost map in that way.

show abstract

Section: System Overviewmentioning

confidence: 99%

Cloud-Based Multi-Robot Path Planning in Complex and Crowded Environment with Multi-Criteria Decision Making Using Full Consistency Method

2019

View full text Add to dashboard Cite

show abstract

“…Most of these works rely on depth information from RGB-D or stereo sensors [4]- [7]. In [4], [6], assume an instancelevel model of the objects are known a priori. In [4], a real-time 3D object detection algorithm is applied on an RGB-D image stream and these objects are fused along with odometry information in a pose graph optimization scheme.…”

Section: A Object-slammentioning

confidence: 99%

“…In [4], a real-time 3D object detection algorithm is applied on an RGB-D image stream and these objects are fused along with odometry information in a pose graph optimization scheme. Similarly in [6], a framework for multi-robot object-SLAM is proposed. Again, each robot is equipped with an RGB-D sensor and object models are available a priori.…”

Section: A Object-slammentioning

confidence: 99%

See 1 more Smart Citation

Constructing Category-Specific Models for Monocular Object-SLAM

Parkhiya

Khawad

Murthy

et al. 2018

2018 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

We present a new paradigm for real-time objectoriented SLAM with a monocular camera. Contrary to previous approaches, that rely on object-level models, we construct category-level models from CAD collections which are now widely available. To alleviate the need for huge amounts of labeled data, we develop a rendering pipeline that enables synthesis of large datasets from a limited amount of manually labeled data. Using data thus synthesized, we learn categorylevel models for object deformations in 3D, as well as discriminative object features in 2D. These category models are instance-independent and aid in the design of object landmark observations that can be incorporated into a generic monocular SLAM framework. Where typical object-SLAM approaches usually solve only for object and camera poses, we also estimate object shape on-the-fly, allowing for a wide range of objects from the category to be present in the scene. Moreover, since our 2D object features are learned discriminatively, the proposed object-SLAM system succeeds in several scenarios where sparse feature-based monocular SLAM fails due to insufficient features or parallax. Also, the proposed categorymodels help in object instance retrieval, useful for Augmented Reality (AR) applications. We evaluate the proposed framework on multiple challenging real-world scenes and show -to the best of our knowledge -first results of an instance-independent monocular object-SLAM system and the benefits it enjoys over feature-based SLAM methods.

show abstract

“…1. A visual SLAM system might employ a single [23,45,88] or a hybrid [10,54,138] of different feature levels.…”

Section: Introductionmentioning

confidence: 99%

Feature-based visual simultaneous localization and mapping: a survey

Azzam

Taha²,

Huang

et al. 2020

SN Appl. Sci.

View full text Add to dashboard Cite

Visual simultaneous localization and mapping (SLAM) has attracted high attention over the past few years. In this paper, a comprehensive survey of the state-of-the-art feature-based visual SLAM approaches is presented. The reviewed approaches are classified based on the visual features observed in the environment. Visual features can be seen at different levels; low-level features like points and edges, middle-level features like planes and blobs, and high-level features like semantically labeled objects. One of the most critical research gaps regarding visual SLAM approaches concluded from this study is the lack of generality. Some approaches exhibit a very high level of maturity, in terms of accuracy and efficiency. Yet, they are tailored to very specific environments, like feature-rich and static environments. When operating in different environments, such approaches experience severe degradation in performance. In addition, due to software and hardware limitations, guaranteeing a robust visual SLAM approach is extremely challenging. Although semantics have been heavily exploited in visual SLAM, understanding of the scene by incorporating relationships between features is not yet fully explored. A detailed discussion of such research challenges is provided throughout the paper.

show abstract

Multi Robot Object-Based SLAM

Cited by 23 publications

References 22 publications

Cloud-Based Multi-Robot Path Planning in Complex and Crowded Environment with Multi-Criteria Decision Making Using Full Consistency Method

Cloud-Based Multi-Robot Path Planning in Complex and Crowded Environment with Multi-Criteria Decision Making Using Full Consistency Method

Constructing Category-Specific Models for Monocular Object-SLAM

Feature-based visual simultaneous localization and mapping: a survey

Contact Info

Product

Resources

About