Multi-Mission Planning of Service Robot Based on L-HMM

In recent years, the service robot has been developed rapidly, which has brought a lot of convenience for industries and human life. It is of great significance to study service robot. Mission planning is the key component of robot, which is used to solve the sequential decision problem of robot. Because of the highly dynamic and uncertain working environment of service robot, how to model and deal with these complex environments is very important for agents to complete mission planning correctly and efficiently. In this paper, a multimission planning method based on L-HMM and utility function description considering path cost for service robot are proposed, high-dimensional partially observable states of agents are abstractly classified into three-dimensional states, combined with HMM model based on Bayesian network. L-HMM not only reasonably models the stochastic process of agent, but also avoids the dimension explosion problem in the process of model solving. In addition, in the iterative process of utility function, considering the impact of path cost on planning effect prevents the agent from planning irrationally and inefficiently due to the encapsulation of navigation nodes. Finally, humanoid robot NAO is used to verify the effect of the theory proposed, multi-mission experiments show the planning results are excellent and highefficient.