MSPRT action selection model for bio-inspired autonomous driving

This paper proposes a bio-inspired action selection mechanism, the multi-hypothesis sequential probability ratio test (MSPRT), as a decision making tool in the field of autonomous driving. We investigate the capability of the MSPRT algorithm to effectively select the optimal action whenever the autonomous agent is required to drive the vehicle. We present numerical simulations to demonstrate the robustness of the MSPRT action selection when dealing with noisy measurements.