On-line reinforcement learning for trajectory following with unknown faults

Reinforcement learning (RL) is a key method for providing robots with appropriate control algorithms. Controller blending is a technique for combining the control output of several controllers. In this article we use on-line RL to learn an optimal blending of controllers for novel faults. Since one cannot anticipate all possible fault states, which are exponential in the number of possible faults, we instead apply learning on the effects the faults have on the system. We use a quadcopter path-following simulation in the presence of unknown rotor actuator faults for which the system has not been tuned. We empirically demonstrate the effectiveness of our novel on-line learning framework on a quadcopter trajectory following task with unknown faults, even after a small number of learning cycles. The authors are not aware of any other use of on-line RL for fault tolerant control under unknown faults.