Method for database-driven estimate of an output quantity in a k-dimensional value range

A method for the database-driven estimate of an output quantity ({right arrow over (x)}, z) in a k-dimensional value range, method comprising:

• determining a location probability range Ri for a k-dimensional output quantity ({right arrow over (x)},z) for an element i of a measurement series {i=1, . . . ,n}, in which the location probability range Ri is limited by a lower (k−1) dimensional area zi and an upper (k−1) dimensional area zi, both of which are predetermined or parameterized with sensor measured values or derived from a database taking into account additional sensor measured values;
• quantizing the lower limiting area zi and the upper limiting area zi by assigning a lower limiting value zi({right arrow over (x)}v) and an upper limiting value zi({right arrow over (x)}v) of the ith location probability range Ri to each point {right arrow over (x)}v in a predetermined (k−1) dimensional search grid, wherein the index i=1, . . . ,n refers to the respective location probability range Ri and the index v refers to the points in the search grid;
• assigning a number wi({right arrow over (x)}v) or wi({right arrow over (x)}v) to each limiting value zi({right arrow over (x)}v) or zi({right arrow over (x)}v), wherein the number wi({right arrow over (x)}v) corresponds to how many location probability ranges Ri the point ({right arrow over (x)}v,zi({right arrow over (x)}v)) lies, and the number wi({right arrow over (x)}v) respectively states in how many location probability ranges Ri the point ({right arrow over (x)}v, zi({right arrow over (x)}v)) lies, such that the special case n=1, w1({right arrow over (x)}v)=1 and w1({right arrow over (x)}v)=1 applies to all the grid points {right arrow over (x)}v;
• and
• determining a probability range S for the output quantity to be estimated ({right arrow over (x)}, z), in which at least m of the n location probability ranges Ri overlap, such that, when the number wi({right arrow over (x)}v) or wi({right arrow over (x)}v) assigned to the limiting value zi({right arrow over (x)}v) or zi({right arrow over (x)}v) is larger than or equal to m, each point ({right arrow over (x)}v,zi({right arrow over (x)}v)) or ({right arrow over (x)}v, zi({right arrow over (x)}v)) lies within the probability range S, and, such that, when zi({right arrow over (x)}v)≦ Zj({right arrow over (x)}v), wi({right arrow over (x)}v)≧m, wj({right arrow over (x)}v)≧m applies and no limiting value zl({right arrow over (x)}v) or zi({right arrow over (x)}v) with wl({right arrow over (x)}v)≦m or wl({right arrow over (x)}v)≦m exists between zi({right arrow over (x)}v), zj({right arrow over (x)}v), the entire connecting distance of two points ({right arrow over (x)}v, zi({right arrow over (x)}v)), ({right arrow over (x)}v, zj({right arrow over (x)}v)) lies within the probability range S.