A Survey of Motion Planning Methods for Autonomous Driving in Mixed Traffic
Abstract
Autonomous driving systems inevitably operate in mixed traffic where autonomous vehicles coexist with humandriven vehicles (HDVs). Motion planning must therefore handle uncertain intent, heterogeneous driving styles, asymmetric responsibility, and behavioral adaptation to the ego vehicle’s actions. This survey reviews trajectory-level motion planning for mixed traffic and classifies methods by the mechanism through which human behavior enters planning. Reactionbased planners enforce safety through constraints and rules without explicit intent inference; prediction-based planners embed forecast HDV motion in optimization and decision processes; interaction-aware planners condition human responses on candidate ego actions; and coordination-enabled planners shape responses through vehicle-, sequence-, or infrastructure-level interventions. The taxonomy emphasizes planning assumptions rather than numerical solvers. Because practical systems often combine these mechanisms, fallback and receding-horizon strategies are treated as cross-cutting design principles. The review highlights strengths, limitations, and transferable insights for safety-critical human-machine coexistence.