Exploration on continuous Gaussian process frontier maps

Jadidi, Majid; Miró, Jaime Valls; Valencia, Rafael; Andrade‐Cetto, Juan

doi:10.1109/icra.2014.6907754

Cited by 51 publications

(28 citation statements)

References 14 publications

(19 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We seek, however, to apply the methods from Hilbert maps in a way that allows us to use the inference capability of estimators to incrementally update maps in real-time. This will allow the maps to support fast decision-making in the course of exploring unknown environments, as with Gaussian processes in [7].…”

Section: Probabilistic Local Map Fusionmentioning

confidence: 98%

“…While Hilbert maps have these advantages over Gaussian process occupancy mapping, the logistic regression model used in Hilbert maps does not provide the covariance information necessary to implement fusion using a Bayesian Committee Machine (BCM) [6], in contrast to Gaussian process regression, where the BCM has aided online incremental map fusion [7]. The original Hilbert mapping formulation requires that we maintain and update a single global classifier, however it is desirable to perform scalable, incremental updates to a map as new data is gathered in realtime.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Probabilistic map fusion for fast, incremental occupancy mapping with 3D Hilbert maps

Doherty

Wang

Englot

2016

2016 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

We present a novel formulation of Hilbert mapping in which we construct a global occupancy map by incrementally fusing local overlapping Hilbert maps. Rather than maintain a single supervised learning model for the entire map, a new model is trained with each of a robot's range scans, and queried at all points within the robot's perceptual field. We treat the probabilistic output of the classifier as a sensor, employing sensor fusion to merge local maps. This formulation allows Hilbert mapping to be used incrementally in real-world mapping scenarios with overlap between sensor observations. The methodology is applied to three-dimensional map-building, and evaluated using real and simulated 3D range data.

show abstract

Section: Probabilistic Local Map Fusionmentioning

confidence: 98%

Section: Introductionmentioning

confidence: 99%

Probabilistic map fusion for fast, incremental occupancy mapping with 3D Hilbert maps

Doherty

Wang

Englot

2016

2016 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

show abstract

“…The development of GPOM is discussed in [25], [26]. The incremental GP map building using the Bayesian Committee Machine (BCM) technique [27] is developed in [28]- [31] and for online applications in [32]. In [33], the Hilbert maps technique is proposed and is more scalable.…”

Section: Related Workmentioning

confidence: 99%

Warped Gaussian Processes Occupancy Mapping With Uncertain Inputs

Ghaffari

Miró

Dissanayake

2017

IEEE Robot. Autom. Lett.

Self Cite

View full text Add to dashboard Cite

Abstract-In this paper, we study extensions to the Gaussian Processes (GPs) continuous occupancy mapping problem. There are two classes of occupancy mapping problems that we particularly investigate. The first problem is related to mapping under pose uncertainty and how to propagate pose estimation uncertainty into the map inference. We develop expected kernel and expected sub-map notions to deal with uncertain inputs. In the second problem, we account for the complication of the robot's perception noise using Warped Gaussian Processes (WGPs). This approach allows for non-Gaussian noise in the observation space and captures the possible nonlinearity in that space better than standard GPs. The developed techniques can be applied separately or concurrently to a standard GP occupancy mapping problem. According to our experimental results, although taking into account pose uncertainty leads, as expected, to more uncertain maps, by modeling the nonlinearities present in the observation space WGPs can improve the map quality.

show abstract

“…Application of non-parametric methods, such as GP s have recently proven great enhancements on the mapping tasks within the context of autonomous navigation. Continuous frontier maps are obtained by optimizing the process parameters, which reveal important uncertainty reduction [19,20]. Therefore, we propose the training of a GP as a tool to establish a bounded uncertainty scheme for our approach.…”

Section: Introductionmentioning

confidence: 99%

Information-based view initialization in visual SLAM with a single omnidirectional camera

Valiente

Ghaffari

Miró

et al. 2015

Robotics and Autonomous Systems

View full text Add to dashboard Cite

This paper presents a novel mechanism to initiate new views within the map building process for an EKF-based visual SLAM (Simultaneous Localization and Mapping) approach using omnidirectional images. In presence of non-linearities, the EKF is very likely to compromise the final estimation. Particularly, the omnidirectional observation model is induces non-linear errors, thus it becomes a potential source of uncertainty. To deal with this issue we propose a novel mechanism for view initialization which accounts for information gain and losses more efficiently. The main outcome of this contribution is the reduction of the map uncertainty and thus the higher consistency of the final estimation. Its basis relies on a Gaussian Process to infer an information distribution model from sensor data. This model represents feature points existence probabilities and their information content analysis leads to the proposed view initialization scheme. To demonstrate the suitability and effectiveness of the approach we present a series of real data experiments conducted with a robot equipped with a camera sensor and map model solely based on omnidirectional views. The results reveal a beneficial reduction on the uncertainty but also on the error in the pose and the map estimate.

show abstract

Exploration on continuous Gaussian process frontier maps

Cited by 51 publications

References 14 publications

Probabilistic map fusion for fast, incremental occupancy mapping with 3D Hilbert maps

Probabilistic map fusion for fast, incremental occupancy mapping with 3D Hilbert maps

Warped Gaussian Processes Occupancy Mapping With Uncertain Inputs

Information-based view initialization in visual SLAM with a single omnidirectional camera

Contact Info

Product

Resources

About