System and method for controlling a mobile industrial robot using a probabilistic occupancy grid

A robot controller configured to control at least one industrial robot, which is movable on a substrate, the robot controller comprising:

• an input interface for receiving data representative of an elevation map and a chromaticity map of the substrate from at least one sensor;
• processing circuitry configured to perform the steps of:
• initializing an occupancy grid of cells which each represents a portion of the substrate and is associated with an occupancy probability that some physical object is present in the cell;
• obtaining the elevation map and the chromaticity map of the substrate;
• computing, on the basis of the elevation map, a mean elevation of each cell and deriving a first partial occupancy probability, wherein a higher first partial occupancy probability corresponds to a greater mean elevation;
• on the basis of the chromaticity map,
• estimating a distribution of the chromaticity,
• identifying dominant chromaticity values, and
• computing, on the basis of a chromaticity of each cell, a second partial occupancy probability, wherein a lower second partial occupancy probability is assigned to the cell if its chromaticity is one of the dominant chromaticity values;
• merging, for each cell, the first and second partial occupancy probabilities into an occupancy probability for the cell;
• and
• controlling the industrial robot on the basis of the occupancy grid;
• and
• an output interface for supplying commands to the industrial robot.

A computer program product comprising a non-transitory data carrier storing a computer program, which includes instructions for causing a robot controller to perform a method, the robot controller being configured to control at least one industrial robot, which is movable on a substrate, the method including the steps of:

• initializing an occupancy grid of cells which each represents a portion of the substrate and is associated with an occupancy probability that some physical object is present in the cell;
• obtaining an elevation map and a chromaticity map of the substrate;
• computing, on the basis of the elevation map, a mean elevation of each cell and deriving a first partial occupancy probability, wherein a higher first partial occupancy probability corresponds to a greater mean elevation;
• on the basis of the chromaticity map,
• estimating a distribution of the chromaticity,
• identifying dominant chromaticity values, and
• computing, on the basis of a chromaticity of each cell, a second partial occupancy probability, wherein a lower second partial occupancy probability is assigned to the cell if its chromaticity is one of the dominant chromaticity values;
• merging, for each cell, the first and second partial occupancy probabilities into an occupancy probability for the cell;
• and
• controlling the industrial robot on the basis of the occupancy grid.