Uncertainty-Aware Decision-Making and Planning for Autonomous Forced Merging

Abstract-- In this paper, we develop an uncertainty-aware decision-making and motion-planning method for an autonomous ego vehicle in forced merging scenarios, considering the motion uncertainty of surrounding vehicles. The forced merging scenario on the highway. Following the decision and the SVs' occupancy, the reference trajectory for the EV is calculated I. However, the motion uncertainties of dynamic obstacles The method is aware of the environmental uncertainties using introduce challenges to the safety in motion-planning online estimation of the acceleration bounds of the SVs, such problems. Among various uncertain scenarios, forced merging that it dynamically captures the uncertainties of SVs without on highways presents notable difficulties, as it demands inferring their intentions.