论文部分内容阅读
A multi-modal action control approach is proposed for an autonomous soccer robot when the bottom hardware is unchange-able. Different from existing methods, the proposed control approach defines actions with the principle of "perception-planning-action"inspired by human intelligence. Character extraction is used to divide the perception input into different modes. Different control modes are built by combining different control methods for the linear velocity and angular velocity. Based on production rules, the motion control is realized by connecting different perceptions to the corresponding control mode. Simulation and real experiments are conducted with the middle-sized robot Frontier-I, and the proposed method is compared with a proportional-integral-derivative (PID) control method to display its feasibility and performance. The results show that the multi-modal action control method can make robots react rapidly in a dynamic environment.