Rapidly-exploring Random Tree (RRT), has been very successful in solving motion planning problems. The large scale of data provided by the emerging of smart paradigm makes the running of RRT algorithm a challenging task. In fact, research is increasingly oriented towards the parallelization of RRT. However, one challenge in parallelizing RRT is the global computation and communication overhead of nearest neighbor search, a key operation in RRTs. This is a critical issue as it limits the scalability of previous algorithms. in this paper we present a new parallel algorithms to address this problem by extending existing work based in MapReduce with a new conception and implementation of the RRT in a big data context
by using a in-memory framework. The experimental results show that our approach are scalable and efficiently in large data structures.