MSPRT action selection model for bio-inspired autonomous driving and intention prediction
Published at IROS 2019, Workshop: “Towards Cognitive Vehicles: perception, learning and decision making under real-world constraints. Is bio-inspiration helpful?”
This paper proposes the usage of a bio-inspired action selection mechanism, known as multi-hypothesis sequential probability ratio test (MSPRT), as a decision-making tool in the ﬁeld of autonomous driving. The focus is to investigate the capability of the MSPRT algorithm to effectively select the optimal action whenever the autonomous agent is required to drive the vehicle or, to infer the human driver intention when the agent is acting as an intention prediction mechanism. After a brief introduction to the agent, we present numerical simulations to demonstrate how simple action selection mechanisms may fail to deal with noisy measurements while the MSPRT provides the robustness needed for the agent implementation on the real vehicle.