Collaborative object manipulation and transport with self-reconfigurable modular robots can take a major role in improving modularity and adaptability of smart-home and factory-like environments. Controlling modules to achieve efficient behaviours is challenging due to the high number of degrees of freedom in the system and the physical constraints. We present an end-to-end planner that discovers collaborative behaviours for modules to manipulate and transport objects to bring them to a human defined place. 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. Results show that the proposed method can effectively coordinate the actions of multiple robots, leading to an emerging efficient manipulation and transport of objects with variable shapes and weight to within human reachable space. This work brings self-reconfigurable modular robots one step closer to assistive human-robot interaction applications or smart logistics.