mufasa.nodes.mapping.pom#

Classes#

POM

Probability Occupancy Map: Bayesian log-odds accumulation with exponential decay.

Module Contents#

class mufasa.nodes.mapping.pom.POM(decay_s: float, prior: float = 0.5)#

Bases: mufasa.nodes.mapping.heat.HeatMap

Probability Occupancy Map: Bayesian log-odds accumulation with exponential decay.

Internal state and BayesianMap.data are both in log-odds space. Use map.probabilities to obtain values in [0, 1]. Produces BayesianMap so that fusion nodes can enforce compatible wiring.

Parameters:

  • decay_s (float) – Exponential decay time constant in seconds.

  • prior (float) – Sensor baseline confidence. Observations with confidence == prior are neutral (zero log-odds contribution). Above prior increases the map; below decreases it. The map itself always starts at probability 0.5 (unknown) — use a StaticMap + BayesianFusion to set a spatial prior on occupancy.

prior = 0.5#
get_config() → dict#

Return all constructor arguments as a plain JSON-serializable dict.

Used by Graph.to_config() to serialise the pipeline. Every key must be a string; every value must be JSON-serializable.

Return type:

dict