Here is an end-to-end planner for reconfigurable modular robots that allow for collaborative object manipulation and transport. This method can be used to coordinate the actions of multiple robots, allowing these modular robots to transport objects of various shapes and weight.
As the researchers explain:
Our approach is based on a centralized planner using stochastic best-first search with a custom heuristic and pruning strategy. We use Quadratic Programming to define multi-robot controller to evaluate action feasibility for transitions between the search tree nodes with respect to important constraints of the system (collisions, joint and torque limits). The controller can be design to be aware of human reachable space for object handover and use it as a measure to asses closeness to the goal node.
[HT: Aurélien Morel, Anastasia Bolotnikova, Celinna Ju, Jan Rabaey, Auke Ijspeert]