Task Allocation for Multi-Robot Task and Motion Planning: a case for Object Picking in Cluttered Workspaces
This addresses planning in clutter for applications like search and rescue, but it is incremental as it builds on existing integrated task and motion planning methods.
The paper tackles the problem of multi-robot task and motion planning for object picking in cluttered workspaces, where the number of required object re-arrangements is unknown beforehand, and demonstrates results in simulation with two Franka Emika manipulators using an AND/OR graph-based approach that maximizes a combined utility function for task allocation.
We present an AND/OR graph-based, integrated multi-robot task and motion planning approach which (i) performs task allocation coordinating the activity of a given number of robots, and (ii) is capable of handling tasks which involve an a priori unknown number of object re-arrangements, such as those involved in retrieving objects from cluttered workspaces. Such situations may arise, for example, in search and rescue scenarios, while locating/picking a cluttered object of interest. The corresponding problem falls under the category of planning in clutter. One of the challenges while planning in clutter is that the number of object re-arrangements required to pick the target object is not known beforehand, in general. Moreover, such tasks can be decomposed in a variety of ways, since different cluttering object re-arrangements are possible to reach the target object. In our approach, task allocation and decomposition is achieved by maximizing a combined utility function. The allocated tasks are performed by an integrated task and motion planner, which is robust to the requirement of an unknown number of re-arrangement tasks. We demonstrate our results with experiments in simulation on two Franka Emika manipulators.