ReviewAdaptive cruise control look-ahead system for energy management of vehicles
Highlights
► Adaptive cruise control combined with the look-ahead system provides increases vehicle safety, provides a more relaxed driving environment, and has the added benefit of reduced fuel consumption. ► The membership functions and fuzzy rules of adaptive cruise control have been made adaptive by using ANFIS. ► Look-Ahead system predicts the future environmental conditions and it is able to reduce the energy consumption of vehicles.
Introduction
Cruise control in vehicles enhances safe and efficient driving by maintaining a constant speed at a preset level. Adaptive Cruise Control (ACC) is the latest development in cruise control. It controls engine throttle position and braking to maintain a safe distance behind a vehicle in front by responding to the speed of this vehicle, thus providing a safer and more relaxing driving environment (Kun & Ioannou, 2004). This is achieved by using a radar headway sensor, a digital signal processor, and an intelligent speed control algorithm. If the vehicle in front slows down, or another obstacle is detected, ACC sends a signal to the engine and braking system to decelerate the vehicle. Then, when the vehicle in front speeds up, or the obstacle is no longer detected, ACC will re-accelerate the vehicle back to the set speed (Serafin, 1996). Conventional analytical control methods for adaptive cruise control can generate good results; however they are difficult to design and computationally expensive. This is because the control object (the vehicle) is highly nonlinear and its full mathematical representation is difficult to derive (Wagg, 2003). In order to achieve a robust, less computationally expensive, and at the same time more natural human-like speed control, intelligent control techniques can be used (Passino & Yurkovich, 1998).
The fuzzy control method provides a practical alternative to conventional analytical control approaches in solving nonlinear automotive control problems (Naranjo, Gonzalez, Garcia, & Pedro, 2007). The fuzzy control method was first introduced by Mamdani (1976) for systems that are difficult to control using conventional methods and is based on the work by Zadeh on fuzzy sets (Zadeh, 1965). Fuzzy coheory has found a number of applications in vehicle control. For example, Naranjo, Gonzalez, Reviejo, Garcia, and Pedro (2003) have demonstrated a fuzzy adaptive cruise controller offering driving strategies and actuation of the engine throttle. The driving information is supplied by the vehicle tachometer and a Real Time Kinematic (RTK) differential Global Positioning System (GPS). The developed controller demonstrated good inter-vehicle gap keeping performance. Zheng and McDonald Zheng and McDonald (2005) simulated the driver’s expectations, quantitatively defined as the expected deceleration rate, for several time-to-collision levels, to avoid collision with the vehicle in front. A two-level ACC algorithm was formed to simulate the performance of the ACC equipped vehicle in various scenarios. The investigation focused on scenarios where a robust ACC was obtainable from the technical perspective, but where the driver expectations were allowed to be breached. The results revealed that whilst appropriate ACC settings can be found to meet the driver expectations, the ACC settings that were the most robust for a range of traffic conditions were not necessarily the most user-friendly. Abdullah et al. Abdullah, Hussain, Warwick, and Zayed (2008) proposed a multiple-controller framework incorporating a fuzzy-logic-based switching and tuning supervisor along with a generalised learning model for an ACC. The proposed methodology combines a PID controller and a pole placement controller. The switching decision between the two controllers was made on the basis of the required performance using a fuzzy-logic-based supervisor. The experimental results demonstrated the effectiveness of the controller with respect to adaptively tracking the desired speed changes of the vehicle.
In the field of fuzzy control, neuro-fuzzy approaches have become popular for adaptive control of ill-defined and uncertain systems. For example, the Adaptive Neural Network based Fuzzy Inference System (ANFIS) is capable of dealing with uncertain systems (Buragohain and Mahanta, 2008, Gill and Singh, 2010, Melin and Castillo, 2005, Shoorehdeli et al., 2009). ANFIS is a multi-layer adaptive network-based fuzzy inference system (Jang, 1993) based on Takagi–Sugeno–Kang (TSK) fuzzy inference (Sugeno & Kang, 1998).
This paper presents an ANFIS-based ACC system that reduces the energy consumption of the vehicle and improves its efficiency. The proposed adaptive cruise control look-ahead system has the following features:
- (1)
It calculates the energy consumption of the vehicle under combined dynamic loads like wind drag, slope, kinetic energy and rolling friction. The experimental data is generated using the Probabilistic Highway Model (PMH) technique recently developed by the authors (Khayyam, Kouzani, Abdi, & Nahavandi, 2009).
- (2)
A look-ahead strategy has been employed to predict the future slope based on recent work by the authors (Khayyam, Kouzani, Nahavandi, Marano, & Rizzoni, 2010).
- (3)
ANFIS is used for cruise control of the vehicle speed. The developed cruise control system adaptively controls the vehicle speed based on the preset speed and the predicted future slope information. Optimal membership functions are obtained by using the subtractive clustering method (Wu & Banzhaf, 2010).
The paper is organized as follows: Section 2 discusses the method used to construct road information taking into account environmental conditions, driver behavior, as well as slope; Section 3 presents the proposed ANFIS cruise control system; Section 4 provides the experimental model and the associated results; Section 5 provides the concluding remarks.
Section snippets
Environmental conditions and driver behaviour
To examine the role of environmental conditions in the modeling and simulation of vehicle systems, two types of data are considered: real data and synthetic data. Whilst utilization of real environmental data such as the geometrical information associated with real roads and climate is ideal, this information is often unavailable, or available but inadequate for extensive investigation.
Synthetic data of highway profiles that resembles real highway profiles can be a useful tool for road-based
Adaptive cruise control with ANFIS
ANFIS is a multi-layer adaptive network-based fuzzy inference system (Jang, 1993). ANFIS consists of five layers to implement different node functions to learn and tune parameters in a fuzzy inference using a hybrid learning mode. In the forward pass, with fixed premise parameters, the least squared error estimate is employed to update the consequent parameters and to pass the errors to the backward pass. In the backward pass, the consequent parameters are fixed and the gradient descent method
Proposed energy management system
In a vehicle, the road power demand can be calculated by using the vehicle speed and drag (which includes environmental conditions). The overview of the developed power flow calculation model is shown in Fig. 8. The model includes three main units: Friction Management Unit (FMU); Drive Strategy Unit (DSU); Energy Calculation Unit (ECU).
FMU employs the following data:
- i.
Current Road Slope: This data specifies the actual slope angle of the road at the current location of the vehicle as described in
Conclusion
Adaptive Cruise Control (ACC) in motor vehicles enhances safe and efficient driving by maintaining a constant speed at a preset level. It controls engine throttle position and braking to maintain a safe distance behind a vehicle in front by responding to the speed of this vehicle, thus providing a safer and more relaxing driving environment. This is achieved by using a radar headway sensor, a digital signal processor, and an intelligent speed control algorithm. This paper demonstrates that the
Acknowledgment
The authors thank Air International Company, Australian Research Council (ARC), and AutoCRC who support this work.
References (22)
Advances in the linguistic synthesis of fuzzy controllers
International Journal of Man–Machine Studies
(1976)Fuzzy sets
Information and Control
(1965)- et al.
Manual vs. adaptive cruise control – Can driver’s expectation be matched?
Transportation Research Part C
(2005) - et al.
Autonomous intelligent cruise control using a novel multiple-controller framework incorporating fuzzy-logic-based switching and tuning
Journal of Neurocomputing
(2008) - et al.
A novel approach for ANFIS modelling based on full factorial design
Applied Soft Computing
(2008) - et al.
Identification using ANFIS with intelligent hybrid stable learning algorithm approaches and stability analysis of training methods
Applied Soft Computing
(2009) - et al.
Intrusion detection using hierarchical neural networks
Pattern Recognition Letters
(2005) - et al.
The use of computational intelligence in intrusion detection systems: A review
Applied Soft Computing
(2010) - et al.
Predicting injection profiles using ANFIS
Information Sciences
(2007) - et al.
Modeling of traffic flow of automated vehicles
IEEE Transaction on Intelligent Transportation Systems
(2004)
Driver preferences and usability of adjustable distance controls for an Adaptive Cruise Control (ACC) system
Ford Motor Company Systems Technology, Inc
Cited by (83)
Predictive cruise control for hybrid electric vehicles based on hierarchical convex optimization
2024, Energy Conversion and ManagementA strategy of vehicle following on slope road at night considering the safety of the intended functionality
2023, Physica A: Statistical Mechanics and its ApplicationsFuel consumption optimization for a plug-in hybrid electric bus during the vehicle-following scenario
2023, Journal of Energy StorageReal-time self-adaptive Q-learning controller for energy management of conventional autonomous vehicles
2023, Expert Systems with ApplicationsVehicle Road Grade Prediction Based on CNN-LSTM
2023, IFAC-PapersOnLine