Guidance-Based On-Line Motion Planning For Autonomous Highway Overtaking

Abstract

In the context of intelligent transportation, this paper presents a novel on-line trajectorygeneration method for autonomous lane changing. The proposed scheme is guidance based, realtime applicable, and ensures safety and passenger ride comfort. Based on the principles of Rendezvous Guidance, the passing vehicle is guided in real-time to match the position and velocity of a shadow target (i.e., rendezvous with) during the overtaking manoeuvre. The shadow target's position and velocity are generated based on real-time sensory information gathered about the slower vehicle ahead of the passing vehicle as well as other vehicles which may be travelling in the passing lane. Namely, the guidance principle is also used to prevent any potential collision with these obstacle vehicles. The proposed method can be used as a fully autonomous system or simply as a driver-assistance tool. Extensive simulations and experiments, some of which are presented herein, clearly demonstrate the tangible efficiency of the proposed method.

Trajectory planning and tracking for autonomous overtaking: State-of-the-art and future prospects

“…Inter-disciplinary techniques inspired by robotics and missile guidance systems [5,55,56] for vehicle path-planning are also reported in literature. One of the novel approaches proposed was to use motion primitives (combination of steady-state equilibrium trajectories and pre-specified manoeuvres) [57].…”

“…The experimental results demonstrated that collision free and feasible trajectories can be generated in real-time using this approach [57]. Ghumman et al designed a trajectory planning method based on Rendezvous Guidance technique (passing vehicle is guided in real-time to match the position and velocity of a shadow target during an overtaking manoeuvre) inspired from missile guidance systems [55,56], see Figure 5c. Similarly, an approach for overtaking manoeu-vre consisting of consecutive tracking of virtual reference points positioned a priori at known distances from the lead vehicle is proposed in [5].…”

Modeling and Nonlinear Adaptive Control for Autonomous Vehicle Overtaking

“…The solution of the optimization problem determines the optimal time and distance for the lane change maneuver using 5-th degree polynomial functions. An on-line time-optimal trajectory planning algorithm for the guidance of a pursuer vehicle overtaking a slower vehicle which is based on Rendezvous-Guidance principle was proposed in [36]. Two-layer controller architecture for overtaking maneuver is presented in [37].…”

Safety of Lane Change Maneuver Through A Priori Prediction of Trajectory Using Neural Networks

“…The change in behavior coupled with the lack of the awareness of the global scenario of the traffic state for spatial temporal anticipation and reduced maneuvering time may result in collision when the front or side ahead vehicle brakes or during lane changing on the highways. Absolute errors in the decision-making time typically caused by driver at the time of lane change failure to accurately and timely interpret information about other vehicles in close proximity, have often resulted in serious accidents and congestion on the highways [32], [33].…”