Temporal Difference Learning to Detect Unsafe System States

This paper proposes a general framework to detect unsafe states of a system whose basic realtime param-eters are captured by multi-sensors. Our approach is to learn a danger level function which can be used to alert the users in advance of dangerous situations. The main challenge to this learning problem is the labelling issue, i.e., it is difficult to assign an objective danger level at each time step to the training data, except at the collapse points where a penalty can be assigned and at the successful ends where a certain reward can be assigned. In this paper, we treat the danger level as ex-pected future reward (penalty is regarded as negative reward) and use temporal difference (TD) learning [2] to learn a function to approximate the expected future reward. The TD learning obtains the approximation by propagating the penalty/reward observable at collapse points or successful ends to the entire feature space fol-lowing some constraints. Our approach is applied to, but not limited to, the application of monitoring of driv-ing safety and the experimental results demonstrate the effectiveness of the approach