This paper presents a new speed control model applicable to real-world driving. It is developed for intersection left turns and is based on anticipated acceleration reference (AAR) inputs. This addresses combined visual anticipation of lateral and longitudinal accelerations for the approach to an intersection where both stopping and turning outcomes are possible. The relationship between the AAR and the resulting vehicle accelerations are studied for both stopping and turning events using naturalistic driving data. A closed-loop model is developed, including braking to rest when the left turn is not attempted and for the turn and exit stages when it is. Parameter ranges are estimated, and as a demonstration of model applicability, Monte Carlo simulations are conducted to generate representative left turns using a full simulation model. Extension of the AAR model to other speed control problems, for example, driving on curved roads, is also discussed.