Multi-level offloading decision on efficient object tracking for humanoid robot

Energy efficiency is an important issue for a humanoid robot to track an object, especially robot using battery packs with limited capacity. The tracking algorithm is implemented bymany functions, such as walking patterns, balance control, object recognition, path planning, etc. Performing these functions on a remote server can offload the computation on robot for energy efficiency. The offloading needs a proper decision rule in respect to the efficiency and performance. This paper presents a multi-level decision method by classifying the functions into three levels related to stability, real-time performance, and energy efficiency. Based on these levels, the decision rules are designed to offload these functions to track the object efficiently. They are validated by a humanoid robot platform called DARwIn-OP. This method could also be used tominimize the energy consumption on other tasks of a humanoid robot.