Scale-only visual homing from an omnidirectional camera

Liu, Ming; Pradalier, Cédric; Pomerleau, François; Siegwart, Roland

doi:10.1109/icra.2012.6224900

Cited by 33 publications

(15 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• For each robot client , the utility surplus function is defined as (1) where denotes the willingness to pay of robot client is the completion time of robot for resource retrieval. The logarithmic function is a widely used utility function for proportionally fair resource allocation in communication networks (see [54]).…”

Section: A the Msdr Problem Formulationmentioning

confidence: 99%

“…For traditional robotic systems, robots have to carry adequate physical processing power and various sensors among other resources to facilitate the completion of various tasks such as visual navigation [1], range-finder-based navigation [2], [3], path planning [4], recognition [5], and scene analysis [6], [7]. However, it is infeasible to develop a universal robot that could cover all possible services due to the limitation of cost, reliability, power consumption, payload, sensory and kinematic constraints, among many others.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Real-Time Multisensor Data Retrieval for Cloud Robotic Systems

Wang

Liu

Meng

2015

IEEE Trans. Automat. Sci. Eng.

Self Cite

View full text Add to dashboard Cite

Cloud technology elevates the potential of robotics with which robots possessing various capabilities and resources may share data and combine new skills through cooperation. With multiple robots, a cloud robotic system enables intensive and complicated tasks to be carried out in an optimal and cooperative manner. Multisensor data retrieval (MSDR) is one of the key fundamental tasks to share the resources. Having attracted wide attention, MSDR is facing severe technical challenges. For example, MSDR is particularly difficult when cloud cluster hosts accommodate unpredictable data requests triggered by multiple robots operating in parallel. In these cases, near real-time responses are essential while addressing the problem of the synchronization of multisensor data simultaneously. In this paper, we present a framework targeting near real-time MSDR, which grants asynchronous access to the cloud from the robots. We propose a market-based management strategy for efficient data retrieval. It is validated by assessing several quality-of-service (QoS) criteria, with emphasis on facilitating data retrieval in near real-time. Experimental results indicate that the MSDR framework is able to achieve excellent performance under the proposed management strategy in typical cloud robotic scenarios.Note to Practitioners-This paper was motivated by the problem of sharing resources in cloud robotic systems efficiently for accomplishing real-time tasks. Existing approaches to cloud robotics bear very strict assumptions that the resources are unconstrained and ubiquitous. However, there are technical challenges for multirobot systems to access the cloud and retrieve resources in near real-time. This paper presents a general framework for setting up cloud robotic system with a novel resource management strategy. We mathematically formulate the problem of multisensor data retrieval through the cloud as a Stackelberg game, and propose an optimal solution with proof. We then define the QoS criteria for evaluation considering the constraints of robotic tasks. In the experimental scenarios, our management mechanism significantly improves the performance for multisensor data retrieval in the evaluation of QoS, CPU load, and bandwidth usage.

show abstract

Section: A the Msdr Problem Formulationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Real-Time Multisensor Data Retrieval for Cloud Robotic Systems

Wang

Liu

Meng

2015

IEEE Trans. Automat. Sci. Eng.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The nodes are usually extracted from places with salient features, while edges among the nodes determine the connectivity. For vision based approaches, the localization is mostly achieved by feature matching and geometrical triangulation [19]. In this proposed approach, the localization task aims at finding the topological region [8], [23] to which the current robot pose belongs.…”

Section: Introductionmentioning

confidence: 99%

A Hidden Markov Model approach for Voronoi localization

Song

Liu

2013

2013 IEEE International Conference on Robotics and Biomimetics (ROBIO)

Self Cite

View full text Add to dashboard Cite

Localization is one of the fundamental problems for mobile robots. Hence, there are several related works carried out for both metric and topological localization. In this paper, we present a lightweight technique for on-line robot topological localization in a known indoor environment. This approach is based on the Generalized Voronoi Diagram (GVD). The core task is to build local GVD to match against the global GVD using adaptive descriptors. We propose and evaluate a concise descriptor based on geometric constraints around meeting points on GVD, while adopting Hidden Markov Model (HMM) for inference. Tests on real maps extracted from typical structured environment using range sensor are presented. The results show that the robot can be efficiently localized with minor computational cost based on sparse measurements.

show abstract

“…Visual homing algorithms can be divided mainly into two branches: holistic and feature-based methods [7,8]. Feature-based methods extract salient features in the environment and match these features between images [9][10][11], whereas holistic methods operate on the whole image [7,12,13]. Recently, methods were proposed that combine holistic and feature-based approaches [14]; a comparison of both branches can be found in [15].…”

Section: Introductionmentioning

confidence: 99%

Cloud-Edge Suppression for Visual Outdoor Navigation

Hoffmann

Möller

2017

Robotics

View full text Add to dashboard Cite

Outdoor environments pose multiple challenges for the visual navigation of robots, like changing illumination conditions, seasonal changes, dynamic environments and non-planar terrain. Illumination changes are mostly caused by the movement of the Sun and by changing cloud cover. Moving clouds themselves also are a dynamic aspect of a visual scene. For visual homing algorithms, which compute the direction to a previously visited place by comparing the current view with a snapshot taken at that place, in particular, the changing cloud cover poses a problem, since cloud movements do not correspond to movements of the camera and thus constitute misleading information. We propose an edge-filtering method operating on linearly-transformed RGB channels, which reliably detects edges in the ground region of the image while suppressing edges in the sky region. To fulfill this criterion, the factors for the linear transformation of the RGB channels are optimized systematically concerning this special requirement. Furthermore, we test the proposed linear transformation on an existing visual homing algorithm (MinWarping) and show that the performance of the visual homing method is significantly improved compared to the use of edge-filtering methods on alternative color information.

show abstract

Scale-only visual homing from an omnidirectional camera

Cited by 33 publications

References 31 publications

Real-Time Multisensor Data Retrieval for Cloud Robotic Systems

Real-Time Multisensor Data Retrieval for Cloud Robotic Systems

A Hidden Markov Model approach for Voronoi localization

Cloud-Edge Suppression for Visual Outdoor Navigation

Contact Info

Product

Resources

About