| CPC G01S 13/931 (2013.01) [G01S 17/931 (2020.01)] | 20 Claims |

|
1. A method comprising:
determining a probability distribution over a list of possible occupancy states (S, D, F, SD, SF, DF, SDF) of an area at a previous point in time, the area comprising a cell of an occupancy grid that comprises a plurality of further cells, and the list of possible occupancy states (S, D, F, SD, SF, DF, SDF) comprising:
a static occupancy state(S), a dynamic occupancy state (D), a free-space state (F), a first uncertainty state (SD) between the static occupancy state(S) and the dynamic occupancy state (D), a second uncertainty state (SF) between the static occupancy state(S) and the free-space state (F), a third uncertainty state (DF) between the dynamic occupancy state (D) and the free-space state (F), and an unknown occupancy state (SDF);
determining measurement data related to the area at a pre-determined point in time using a sensor;
using a Hidden Markov Model (HMM), determining a probability distribution over the list of possible occupancy states (S, D, F, SD, SF, DF, SDF) of the area at the pre-determined point in time based on the measurement data and the probability distribution over the list of possible occupancy states (S, D, F, SD, SF, DF, SDF) of the area at the previous point in time; and
based on the probability distribution of the area at the pre-determined point in time, at least one of (a) planning a path for a robot including avoiding collisions of the robot and (b) detecting objects for driving of a vehicle.
|