Automatic Steering and Braking for a Collision Avoiding Vehicle

Schorn, Matthias; Isermann, Rolf

doi:10.3182/20060912-3-de-2911.00067

Cited by 10 publications

(2 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…20.1.1 and 20.1.2. The approach is similar to a path control with feedforward and PD controller feedback control in Taylor et al (1999), Schorn and Isermann (2006) and Schorn (2007), and Müller and Rohleder (2006).…”

Section: Path Control For Curvesmentioning

confidence: 99%

Lateral Vehicle Control

Isermann

2021

Automotive Control

Self Cite

View full text Add to dashboard Cite

Roads are usually built from elements of circles, clothoids with intermediate connections, and straight lines; see RAA (2008). Curves have curvatures which develop steadily, such that driving without lateral jerk is possible. The vehicle has to follow the road lane in a straight direction or has to follow the curvatures by cornering with a constant or steadily changing radius. Lateral vehicle control is required for driving maneuvers like cornering, lane change, and parking; see Fig. 19.1.As shown in Fig. 19.2, the vehicle has to follow a lane, ideally in the center of the lane. The geometric form of the lane then defines the vehicle's path. The distance of the center of gravity of the vehicle to the right lane marking is noted by the lateral distance D y . (Also the distance of the front axle or of the right front wheel to the right lane marking may be used.)In the case of circles, the curvature κ = 1/R is inverse proportional to the radius, and clothoids have a curvature which is proportional to the path length L, κ = c cl L.The control of vehicles along a straight or bending lane means that the driver or an automatic controller has to follow a certain path: y = f (x). If this can be performed without time condition, it is called path control. The state variables for the position are x and y and for the orientation of the vehicle, the yaw angle ψ or the course angle ν = ψ + β; see Fig. 20.1. The manipulated variable is the steering wheel angle δ f for a car with front steering. If the position y(x) has to be reached at a certain time t, such that y = f (x, t), this a called trajectory control. Hence, for path control, the lateral motion has to be controlled and for trajectory control, the lateral and longitudinal motion; see Sect. 18.2.The lane markers are usually detected with cameras located behind the windscreen for forward looking. Monocular cameras provide, for example, a ±20 • field of view and ranges up to 80 m. Corresponding image processing then provides the distance to line crossing (DLC) or time to line crossing (TLC) in front of the vehicle and based on a lane marking approximation with polynomials or clothoid functions with the curvature κ and its first derivative dκ/dx in a distance x τ ahead. For more details, see Winner et al. (2016) andSchmitt (2012).

show abstract

Section: Path Control For Curvesmentioning

confidence: 99%

Lateral Vehicle Control

Isermann

2021

Automotive Control

Self Cite

View full text Add to dashboard Cite

show abstract

“…For example, model-based feedback control with simultaneous braking and steering has been introduced for collision avoidance in the studies by Schorn et al 6 and Schorn and Isermann. 7 The individual tire slip control has been developed to avoid obstacles by combining steering and braking. 8,9 Moreover, a fast and precise optimal control for obstacle avoidance was developed by Amrik et al 10 In the study by Hayashi et al, 11 two equal radius arcs were used to represent the path of vehicles for collision avoidance with constant deceleration.…”

Section: Introductionmentioning

confidence: 99%

Self-learning control for coordinated collision avoidance of automated vehicles

Wang

Yin

et al. 2019

Proceedings of the Institution of Mechanical Engineers, Part D:

View full text Add to dashboard Cite

For the improvement of automotive active safety and the reduction of traffic collisions, significant efforts have been made on developing a vehicle coordinated collision avoidance system. However, the majority of the current solutions can only work in simple driving conditions, and cannot be dynamically optimized as the driving experience grows. In this study, a novel self-learning control framework for coordinated collision avoidance is proposed to address these gaps. First, a dynamic decision model is designed to provide initial braking and steering control inputs based on real-time traffic information. Then, a multilayer artificial neural networks controller is developed to optimize the braking and steering control inputs. Next, a proportional–integral–derivative feedback controller is used to track the optimized control inputs. The effectiveness of the proposed self-learning control method is evaluated using hardware-in-the-loop tests in different scenarios. Experimental results indicate that the proposed method can provide good collision avoidance control effect. Furthermore, vehicle stability during the coordinated collision avoidance control can be gradually improved by the self-learning method as the driving experience grows.

show abstract

Anticollision Control Systems

Isermann

2021

Automotive Control

View full text Add to dashboard Cite

Automatic Steering and Braking for a Collision Avoiding Vehicle

Cited by 10 publications

References 2 publications

Lateral Vehicle Control

Lateral Vehicle Control

Self-learning control for coordinated collision avoidance of automated vehicles

Anticollision Control Systems

Contact Info

Product

Resources

About