Estimating Uncertain Spatial Relationships in Robotics

Abstract:In this paper, we describe a representation for spatial information, called the stochastic map, and associated procedures for building it, reading information from it, and revising it incrementally as new information is obtained. The map contains the estimates of relationships among objects in the map, and their uncertainties, given all the available information. The procedures provide a general solution to the problem of estimating uncertain relative spatial relationships. The estimates are probabilistic in nature, an advance over the previous, very conservative, worst-case approaches to the problem. Finally, the procedures are developed in the context of state-estimation and filtering theory, which provides a solid basis for numerous extensions.

v2: the authors' typeset full-length version, as published in Uncertainty in Artificial Intelligence 2 (1988), pp. 435-461, and reprinted in Autonomous Robot Vehicles (1990), pp. 167-193. v1 is a scan of the shorter UAI 1986 proceedings version

Artificial Intelligence (cs.AI)

arXiv:1304.3111 [cs.AI]

(or arXiv:1304.3111v2 [cs.AI] for this version)

Uncertainty in Artificial Intelligence 2 (UAI 1986), Machine Intelligence and Pattern Recognition 5, North-Holland, 1988, pp. 435-461; reprinted in Autonomous Robot Vehicles, Springer, 1990, pp. 167-193

https://doi.org/10.1007/978-1-4613-8997-2_14 DOI(s) linking to related resources