System and method for estimating device pose in a space

A method for estimating a plurality of device poses in a space, comprising executing on at least one hardware processor of a device code adapted to:

• in at least one of a plurality of iterations:
• using at least one model to compute a first estimated device pose in a first identified region of the space in response to at least one input signal captured by the at least one sensor, where the at least one model is one of a plurality of region specific models, each trained to compute an estimated device pose in one of a plurality of regions of the space;
• providing the first estimated device pose to at least one software object executed by the at least one hardware processor to perform a pose-oriented task;
• receiving at least one other model trained to compute another estimated device pose in a second identified region of the space and selected from the plurality of region specific models according to the first estimated device pose;
• and
• using the at least one other model in at least one other iteration of the plurality of iterations to compute a second estimated device pose in the second identified region of the space.

A system for navigating in a space, comprising:

• at least one device, comprising at least one hardware processor connected to at least one sensor and adapted to:
• in each of a plurality of iterations:
• computing an estimated device pose;
• and
• computing at least one navigation instruction according to the estimated device pose;
• wherein computing the estimated device pose comprises:
• in at least one of the plurality of iterations:
• using at least one model to compute a first estimated device pose in a first identified region of the space in response to at least one input signal captured by the at least one sensor, where the at least one model is one of a plurality of region specific models, each trained to compute an estimated device pose in one of a plurality of regions of the space;
• providing the first estimated device pose to at least one software object executed by the at least one hardware processor to perform a pose-oriented task;
• receiving at least one other model trained to compute another estimated device pose in a second identified region of the space and selected from the plurality of region specific models according to the first estimated device pose;
• and
• using the at least one other model in at least one other iteration of the plurality of iterations to compute a second estimated device pose in the second identified region of the space.

A system for providing a plurality of region specific models, comprising:

• at least one hardware processor executing a code adapted to:
• for each of one or more devices connected to the at least one hardware processor, while the device is moving from a first position of the device in a space to a second position of the device in the space:
• receiving from the device at least one first message comprising a first estimated position, estimating the first position of the device in the space;
• analyzing the first estimated position to determine at least one relevant region of the space;
• transmitting to the device at least one response comprising at least one relevant region specific model associated with the at least one relevant region of the space;
• and
• receiving from the device at least one second message comprising a second estimated position, estimating the second position of the device in the space.