This paper describes a lane-changing motion planning model for intelligent vehicles under constraints of collision avoidance in dynamical driving environments. The key innovation is decoupling the longitudinal and lateral motion planning to realize trajectory re-planning in a normal lane-changing process to prevent collisions. The longitudinal planning model decides a collision-free termination point of motion through planning the longitudinal acceleration and velocity. Taking the termination time as input, the lateral planning model plans the optimal reference trajectory for normal lane-changing maneuvers or re-plans the lane-changing trajectory to eliminate potential accidents. When traffic states have variations that may bring about the collisions, the termination point can be updated through the longitudinal planning model, based on which the lateral planning model makes adjustments to the pre-planned trajectory to complete the lane-changing successfully or return its original lane. The simulation results show that the proposed model not only can handle the general motion planning problem but also can re-plan trajectories in emergent conditions to ensure safety, while vehicle dynamics retain in a stable state during the lane-changing or returning maneuvers.
INDEX TERMS Intelligent vehicles, motion planning, accident prevention, optimization.The associate editor coordinating the review of this manuscript and approving it for publication was Fuhui Zhou. the execution module [4]. Through the sensory and communication module, environmental information, including the road friction coefficient and lane marks are observed [5], [6]. And information among vehicles, including vehicle speeds and accelerations could be exchanged by vehicle-to-vehicle (V2V) communication systems [7], [8]. Based on such information, the decision-making module makes reasonable instructions [9], [10]. The motion planning module provides a feasible reference trajectory after receiving the lane-changing demand from the decision-making module [11]. And the execution module applies steering actions to make the vehicle follow the reference lane-changing trajectory [12].This paper studies the motion planning strategy in the active lane-changing system of the intelligent vehicle, because the design has to take many constraints into consideration, such as collision avoidance and driving comfort, which are essential for intelligent vehicles to be accepted by
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.