A Model Based Motion Planning Framework for Automated Vehicles in Structured Environments

Abstract

A main difficulty in autonomous driving is the assurance of maneuver acceptability by other traffic participants. Thus, knowledge about social interaction needs to be incorporated into the motion planning process. In this paper we present a model based framework to verify the acceptance of considered maneuvers and to plan social compliant motions. Therefore, we fuse two powerful approaches, one for decisionmaking and one for planning and show how the methods benefit from each other. Our method adheres to the classical structure of decision-making with subsequent trajectory planning and is consistent in the sense that both components are subject on the same, identical parametrized driver model. The overall method is real-time capable and the resulting trajectories adhere to kinematic constraints. Thus, the approach is applicable in realworld systems.

On-Road Motion Planning for Automated Vehicles at Ulm University

“…3) Lane Changing: In our previous work [27], we implemented lane change functionality by numerically integrating the IDM on the reference line to obtain the behavior trajectory. Subsequent minimization of the cost functional 1 results in a transition to the target lane.…”

Trajectory Planning for Automated Driving in Intersection Scenarios using Driver Models

“…• the holistic overall framework which extends the concepts presented in [4], [14] for social compliant behavior in intersection scenarios • a novel concept for behavior generation in intersection scenarios utilizing driver models • a new decision making approach considering the trade-off between ego progress and costs of other vehicles • the utilization of a new, efficient prediction concept for the consideration of other vehicles behavior options In general, the resulting framework performs real-time planning over long horizons while considering other vehicles at urban intersections. Furthermore, the concept yields social compliant maneuvers while preserving the progress of the ego vehicle.…”

“…In this regard, a promising approach for real-world application is to combine the advantages of local continuous optimization with efficient driver models in order to enable social compliant car-following and lane change behavior while keeping the computation time low [4], [14]. A comfortable and drivable trajectory is acquired by generating a reference trajectory using the IDM which is then integrated into a local continuous optimization problem.…”

Graph-Based Motion Planning For Automated Vehicles Using Multi-Model Branching And Admissible Heuristics

“…This allows to restrict κ, κ and the absolute acceleration a abs already during behavior planning which ensures feasible solutions in the trajectory planning module. The context in which a lane change is explored is defined by the MOBIL model [15], which is known to generate human-like decision-making for lane change behavior [14]. Thereby, it is estimated if a lane change is favorable for the combined costs of all involved vehicles.…”

“…Driver models could also be successfully used in various other concepts to efficiently generate social compliant behavior. For example, in [14] the IDM-based MOBIL model [15] is utilized in order to decide whether a lane change is desirable.…”