A New Causal Direction Reasoning Method for Decision Making on Noisy Data

A major trend in self-driving technology is to introduce new causal reasoning mechanisms for decision-making. This paper mainly discusses the problem of causal direction reasoning for nonlinear noisy data. The paper presents the errors in-variables (EIV) system to construct a causality model and the Hilbert-Schmidt independence criterion (HSIC) to compute the dependence between variables. Then, the paper proposes a new method that is based on the EIV model and HSIC. In the proposed method, noise at both the input and output is considered simultaneously. The proposed method has strong robustness and maintains a relatively stable inference accuracy when the observational noise is considerable. Experiments on simulated and real-world data are presented to demonstrate the performance of the proposed method.