S. Thrun. Learning occupancy grids with forward models. In Proceedings of the Conference on Intelligent Robots and Systems (IROS'2001. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Mobile Robot Map Generation - Stereo (2002) (Correct)
....with uncertainty. Each grid has the probability (or certainty) of an obstacle being there and the statistical integration procedure is used to update the probability after each observation. The update of a grid is usually carried out independently of other grids (independence assumption) Thrun [13] proposed to use a forward sensor model,as opposed to an inverse model in [4] to overcome the independence assumption in mapping using ultrasonic sensors. A forward model describes the physics of the environment, from causes (occupancy) to effects (measurements) and more natural than inverse ....
....models. We have also proposed to use a forward model in stereo based environment recognition [12] but made the independence assumption. Probabilistic map learning using forward models without the independence assumption requires a search in a high dimensional space (e.g. the EM algorithm in [13]) which is usually computationally expensive. So we adopt forward sensor models under the independence assumption, which seems reasonable when the range sensor has a fairly fine angular resolution as in the case of our omnidirectional stereo and the LRF. 3.3 Interpretation of range data and ....
S. Thrun. Learning Occupancy Grids with Forward Models. In Proc. of 2001.
Robotic Mapping: A Survey - Thrun (2002) (31 citations) Self-citation (Thrun) (Correct)
No context found.
S. Thrun. Learning occupancy grids with forward models. In Proceedings of the Conference on Intelligent Robots and Systems (IROS'2001.
Learning Occupancy Grids With Forward Sensor Models - Thrun (2002) (5 citations) Self-citation (Thrun) (Correct)
.... this consideration uses sonar sensors as motivating example, it is easily extended to other sensor types that may be used for building occupancy maps, such as stereo vision [17] This article derives an alternative algorithm, which solves the mapping problem in the original, high dimensional space [24]. In particular, our approach formulates the mapping problem as a maximum likelihood problem in a high dimensional space, often with tens of thousands of dimensions. The estimation is carried out using the expectation maximization algorithm (in short: EM) 6] which is a popular statistical tool. ....
S. Thrun. Learning occupancy grids with forward models. In Proceedings of the Conference on Intelligent Robots and Systems (IROS'2001.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC