Chapter 11: Going Autonomous: the BeeSoft Planner
In This Chapter...
Yyoull learn all about autonomous planning and operation using the BeeSoft Planner, the software package that uses maps to plan globally optimal robotic motion. Youll see how your robot determines the costs of traversing a particular path in its environment, and how it decides on the best route to a goal point.
The BeeSoft Planner and the subsidiary tools sonarint and laserint, are example applications, supplied as a part of the BeeSoft package to assist you in your robotic research and development activities. These tools are not officially supported by RWI, Inc.
To run these example applications, you need a working knowledge of the X-Window System, and you need to have the X-Window system up and running on your workstation. RWI, Inc., does not recommend, and will not support, running X-Windows on your robots internal computers.
The Planner is BeeSofts robot motion management and exploration package. It helps your robot plan globally optimal motion, and uses occupancy maps to plan these optimal paths.
The ultimate goal of most research and experimentation with mobile robots is to provide a robot that simply proceeds, dependably and autonomously, to any location requested by its operator or user, and performs any task, again, simply, reliably and autonomously, for which it is equipped, The operator should be able to assume that the robot will figure out the best route to the requested location, and to go there without wreaking havoc or causing panic in the corridors.
The BeeSoft Planner, BeeSofts global navigation robot motion management and exploration package, helps you "train" your robot to operate in just such a manner. Using occupancy maps, built by the BeeSoft Mapper, your robot can compute its minimum cost route in either of two modes of autonomous travel:
Autonomous goal-directed travel: Having been given one or more goal points, the robot figures out which is nearest (in terms of reachability) and proceeds to that location, automatically avoiding obstacles along the way, and recording as complete a map of the territory it traverses along the way as it can.
Upon gaining each sub-goal, the robot "checks off" that sub-goal, deleting it from itsconsideration, and then re-analyzes its current situation. figuring out where to go next.
Autonomous exploration: The robots mission here is to extend and improve its map of the world. It heads for the nearest reachable unexplored territory.
Occupancy maps alone cannot insure collision-free robot travel. First, they are a bit too inaccurate; also, they are unable to track moving humans. Therefore, in a dynamic, real-time environment, the BeeSoft Planner determines only the general direction of robot motion. After consulting its maps and deciding upon a minimum-cost route, the Planner hands the robot off to colliServer, the BeeSoft motion control program that specializes in collision avoidance to actually guide the robot along that route to the goal point. Thus, the Planner is continuously "replanning."