Review Article

Are Self-Driving Vehicles Ready to Launch? An Insight into Steering Control in Autonomous Self-Driving Vehicles

Table 6

Swarm Intelligence-based steering control optimization in self-driving vehicles.

ABCDEF

[104]PSO has been used to overcome the nonlinearity in the MPCKinematic parameters, dynamic parametersSimulationOptimized MPC, reduced the computation timeN/A

[106]Proposed an optimal guidance scheme (improved PSO) based on MPC in the design of the kinematics controllerKinematics parameter, curvature of the path, rotation transformationSimulationHelped to avoid obstacles meeting curvature constraintsThis approach can also be extended to path planning and following other unmanned vehicles

[107]Proposed a PSO-based nonlinear-MPC (NMPC) technique to calculate the yaw moment of the vehicleKinematic parameters, dynamic parametersSimualtionOptimized the steering performance of a vehicleThe effectiveness of the proposed method is only verified under the single-lane manoeuvre

[108]NMPC with QPSO has been proposed for the dynamic steering control of the vehicleKinematic parameters, dynamic parameters, wheel steering angle.MATLABThe concurrent design greatly improved the speed of optimizationDeviation has been noticed in the reference trajectory

[109]Developed a model-free PID controller with derivative filter (PDF) parameter tuning method by using PSODynamic parameterSimulationYielded a good transient response with no steady-state errorThe higher the number of particles, the longer algorithm takes to complete its iteration but the result sometimes is not even better than the previous run

[110]Discussed how the PID controller is tuned to control angular and linear motionKinematic parameters, dynamic parameters, vehicle mass, radius wheelbaseMATLABThe controller optimally tuned the angular motion of the car by selecting the most appropriate values of the PIDThe control algorithm could not search more than one path and chose the one among them in case of obstacles in the road

[111]This paper compares five kinds of tuning methods of a parameter for the PID controller, such as FA, PSO, ACO, BA, and ICAKinematic parameters, dynamic parameters, vehicle mass, radius wheelbaseSimulationProvided correct results as compared to the PID controllerThis research needs to be extended to check its performance on real vehicle conditions

[113]Proposed an optimized design of FOPID using PSO and GAKinematic and dynamic parametersMATLABImproved the steering control of the AVOther methods to tune the parameters of a FOPID controller which could be tested on an actual system

[115]Proposed a supertwisting algorithm to tune the control parameters of the higher-order SMC using PSOSteering wheel angle, kinematic and dynamic parameters, cornering stiffnessMATLABThe dynamic variables obtained by SMC with PSO are better than the results obtained by SMCOnly theoretical study is carried out

[82]A novel approach for four-wheel steer and drive vehicle has been presented which helps to track a path using SMCKinematic parameters, initial heading error θSimulationThe proposed method showed the accurate path followed and accurate reference velocity and acceleration profile followed under varying terrain conditionsExperiments will be carried out to verify the validity of the proposed method

[116]Devised a path tracking technique for automatic steering control of a vehicle based on Stanley controllerKinematics and dynamic parametersSimulationIn general, both modified controllers performed well in guiding the vehicle to follow the intended pathThe control parameters still need to be optimized for better steering control of the vehicle

[117]QPSO is employed to optimize the track control. A steering control model has been devised by using adaptive parallel seriesDynamic parameters, steer angleN/AThe tracking control is effectively achieved in the semiautonomous driver assistance systemNeeds to be applied to the real system, such as senior vehicles and autonomous vehicles

A: authors, B: contribution, C: considered parameters, D: testbed, E: strengths, and F: limitations.