Abstract
This paper describes the design, implementation, and evaluation of a virtual target-based overtaking decision, motion planning, and control algorithm for autonomous vehicles. Both driver acceptance and safety, when surrounded by other vehicles, must be considered during autonomous overtaking. These are considered through safe distance based on human driving behavior. Since all vehicles cannot be equipped with a vehicle to vehicle communications at present, autonomous vehicles should perceive the surrounding environment based on local sensors. In this paper, virtual targets are devised to cope with the limitation of cognitive range. A probabilistic prediction is adopted to enhance safety, given the potential behavior of surrounding vehicles. Then, decision-making and motion planning has been designed based on the probabilistic prediction-based safe distance, which could achieve safety performance without a heavy computational burden. The algorithm has considered the decision rules that drivers use when overtaking. For this purpose, concepts of target space, demand, and possibility for lane change are devised. In this paper, three driving modes are developed for active overtaking. The desired driving mode is decided for safe and efficient overtaking. To obtain desired states and constraints, intuitive motion planning is conducted. A stochastic model predictive control has been adopted to determine vehicle control inputs. The proposed autonomous overtaking algorithm has been evaluated through simulation, which reveals the effectiveness of virtual targets. Also, the proposed algorithm has been successfully implemented on an autonomous vehicle and evaluated via real-world driving tests. Safe and comfortable overtaking driving has been demonstrated using a test vehicle.
Highlights
The final goal of autonomous vehicle (AV) development is to achieve driverless vehicles that can automatically cope with diverse tasks [1]–[3]
For driver acceptance and safety with the surrounding vehicles, safe distances have been devised based on existing safety indices and human driving data
Since most autonomous vehicles recognize the environment by the local sensor, there is a problem with the limitation of the cognitive range
Summary
The final goal of autonomous vehicle (AV) development is to achieve driverless vehicles that can automatically cope with diverse tasks (e.g., lane keeping, lane change, and overtaking) [1]–[3]. We propose efficient decision-making and motion planning based on probabilistic prediction and safety index. Learning-based prediction techniques generally need historical information This approach is vulnerable to effects such as object emergence, object disappearance, and false alarm, which frequently occur in perception modules of actual autonomous vehicles. Since the target environment in this study is a simpler overtaking situation than ramp-merging, roundabouts, and intersections, the EKF-based prediction model was adopted in consideration of the trade-off relationship between calculation load and performance. We present the autonomous overtaking algorithm containing decision-making, motion planning, and control modules. The ego vehicle plans lane change motion based on the distances from side vehicles. The relative velocity between the ego vehicle and the side vehicle needs to be considered in lane change situations [41]. Kinematic analysis is conducted to consider both driver acceptance and collision avoidance.;
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
