This paper presents research in cognitive vehicle energy management for low-cost hybrid electric vehicle (HEV) power systems for small vehicles, such as all-terrain vehicles (ATVs). The power system consists of a small engine, a lead-acid battery, and an ultracapacitor. For simplicity of implementation and low hardware cost, engine control is restricted to two states, i.e., on and off, and vehicle speed control is restricted to three discrete levels, namely, high, medium, and low. The authors developed advanced algorithms for modeling and optimizing vehicle energy flow, machine learning of optimal control settings generated by dynamic programmling on real-world drive cycles, and an intelligent energy controller designed for online energy control based on knowledge about the driving mission and knowledge obtained through machine learning. The intelligent vehicle energy controller cognitive intelligent power management (CIPM) has been implemented and evaluated in a simulated vehicle model and in an ATV, i.e., Polaris Ranger EV, which was converted to an HEV. Experimental results show that the intelligent energy controller CIPM can lead to a significant improvement in fuel economy compared with the existing conventional vehicle controllers in an ATV.