The application presents a multi-posture lower limb rehabilitation robot, which includes a robot base and a training bed. The training bed comprises two sets of leg mechanisms, a seat, a seat width adjustment mechanism, a mechanism for adjusting the gravity center of human body, a back cushion, a weight support system and a mechanism for adjusting the back cushion angle. The robot base comprises a mechanism for adjusting the bed angle. The mechanisms for adjusting the angles of bed and back cushion can be used together to provide paralysis patients with multiple training modes of lying, sitting, and standing postures. Each leg mechanism comprises hip, knee, and ankle joints, which are driven by electric motors; angle and force sensors are installed on each joint, and can be used to identify patients' motion intention to provide patients with active and assistant training. The mechanism for adjusting the gravity center of human body, the leg mechanisms, and the weight support system can be used together to implement human natural walking gait to improve the training effect.