On 2012-10-26 12:07, Christian Dornhege wrote:
> On 26.10.2012 07:13, David Lu!! wrote:
>> Would this also be a good place to standardize what the data in
>> OccupancyGrid actually means? The comments in the .msg file specify...
>> # The map data, in row-major order, starting with (0,0). Occupancy
>> # probabilities are in the range [0,100].  Unknown is -1.
>> int8[] data
>>
>> However, this standard is not respected in the navigation stack,
>> specifically costmap_2d, which also specifies costs with 8bits, but as
>> unsigned chars, leading to costs [0, 254] with 255 being the unknown
>> value (sometimes).
>>
>> [...]
>>
>> What do other people think?
>
> I think costmap and occupancy map do have slightly different 
> semantics. The occupancy map only gives world geometry (which needs to 
> be interpreted). The costmap tries to give costs for a specific robot 
> at the cell location and thus costmap_2d does all those extra values.
>

I agree with Christian on this. To say differently: The occupancy map 
gives you the probability that a cell is occupies based on sensor data. 
The costmap gives you some measure of collision-freeness which is only 
based on the occupied and unknown cells (without probabilities), the 
robot shape and its configuration.

Best,


-- 
Armin Hornung
Humanoid Robots Lab, Albert-Ludwigs-Universität Freiburg
Contact: http://www.informatik.uni-freiburg.de/~hornunga