Anti-control of chaos consists in injecting a chaotic behavior by means of a control scheme to a system, which in natural form does not present it. In this paper, an RBF neural network control algorithm with adaptive terminal sliding mode is proposed to realize the anti - control of chaos for manipulator with unknown parameters and bounded disturbances. The RBF neural network is used to approximate the unknown nonlinear function of the system and the adaptive terminal sliding mode control is used to achieve robustness of the system to external disturbances. The uniform ultimate boundedness of all the signals in the closed-loop system is proved by the Lyapunov stability theorem. Finally, take a two-link planar robot manipulator as a simulation example to verify the feasibility and effectiveness of the proposed method.