Analysis and design of recovery behaviour of autonomous-vehicle avoidance manoeuvres

Anistratov, Pavel; Olofsson, Björn; Nielsen, Lars

doi:10.1080/00423114.2021.1900577

Cited by 3 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Through this, the depth camera acquires the depth image, and the left and right infrared cameras measure the depth [9][10][11][12]. The middle infrared dot matrix projector is equivalent to a fill light, and the RGB camera on the right is used to collect color pictures, which can align the color video stream with the depth stream [13].…”

Section: D435i Modulementioning

confidence: 99%

Obstacle Avoidance Design of Aerial Robot Combining A star algorithm Algorithm and Optical Dynamic Capture Method

Shi

Cai²,

Yuan³

2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

The traditional A star obstacle avoidance algorithm is based on binocular cameras for indoor positioning, which requires rich obstacle feature points and has the risk of explosion in a single indoor environment. In this paper, the method of merging the A star algorithm and optical dynamic capture is proposed. By pasting Marker points on key moving parts, the actual position of the aerial robot is calculated with the optical dynamic capture system, and compared with the target position planned by the A star algorithm and corrected in real time during a flight. Through the experimental analysis of the original acceleration of the aerial robot and different position between the target point and the actual point in the flight process, the stability and flight accuracy of the aerial robot in the flight process can be significantly improved, which has good practical application value.

show abstract

Section: D435i Modulementioning

confidence: 99%

Obstacle Avoidance Design of Aerial Robot Combining A star algorithm Algorithm and Optical Dynamic Capture Method

Shi

Cai²,

Yuan³

2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

“…In this approach, the lateral displacement and the car’s speed have been controlled by utilizing the angle of the steer and the momentum. This study did not consider a speed higher than 70 km/h (Anistratov et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

Part B: Steering and control of an autonomous vehicle in emergency lane change maneuvers based on skilled driver’s performance

Minaei

Ghaffari

Ardekany

2023

Journal of Vibration and Control

View full text Add to dashboard Cite

This paper considers the vehicle control process in emergency lane change (ELC). The control method is divided into two parts: before crossing the obstacle and after crossing it. The first part is done by a feed-forward controller inspired by the driver’s behavior pattern in the ELC maneuver. This controller is compensated by a neural network system and two proportional-integral (PI) and proportional-derivative (PD) controllers, which correct the output of the feed-forward controller to follow the path more accurately. The second part consists of two PD controllers responsible for controlling and steering the vehicle in the main path after crossing the obstacle. The main novelty of the proposed method is that the computational burden is low because of using a feed-forward controller, which is the main source of the calculation’s burden. So as a result, the controller system can cover the ELC maneuver in under 2 seconds in various lateral displacements to bypass the obstacle and prevent collisions. The co-simulations are performed in CarSim software and MATLAB/Simulink, which shows that the control system can appropriately steer the vehicle and follow the desired at different speeds, in the presence of road friction and parameter uncertainty.

show abstract

“…Yuan et al 6 proposed a circle arc collision avoidance path considering the obstacle distance, road adhesion coefficient, vehicle speed, steering wheel stress angle, and driver's linear steering cognition. Anistratov et al 7 presented a method of recovery behavior of autonomous-vehicle avoidance maneuvers, and the generality is demonstrated by applying the recovery extensions to formulations based on minimum time 1 and on a squared lateral-error norm. Singh and Nishihara 8 proposed a decision-making diagrams based on the lane change aspect ratio and dimensionless time to collision.…”

Section: Introductionmentioning

confidence: 99%

A high-speed human-like collision avoidance controller based on a neural network under different road adhesion coefficients

Pan

2023

Proceedings of the Institution of Mechanical Engineers, Part D:

View full text Add to dashboard Cite

Safety and stability have been two main considerations in the field of collision avoidance. However, if the response of a vehicle to avoid collision does not conform to the habits of a human driver, it can cause tension and discomfort to the driver, or even worse, misunderstanding between the driver and an automatic driving system can occur, leading to a traffic accident. Therefore, a driver’s reaction characteristics should be considered, and the reaction expected by the driver should be satisfied as much as possible. This study proposes a human-like collision avoidance model based on a neural network under emergency conditions. The vehicle response data collected from experienced drivers in the collision-avoidance stage via driving simulators are used to train the neural network model. A front-wheel angle controller is developed to track the output of the human-like neural network model. Moreover, the stability region of a vehicle is obtained by the K-means method. Further, a differential braking controller is designed to ensure the safety and stability of the vehicle. The simulation results show that the proposed human-like collision avoidance controller not only meets the safety and stability requirements of collision avoidance but can also ensure good driving comfort for human drivers.

show abstract

Analysis and design of recovery behaviour of autonomous-vehicle avoidance manoeuvres

Cited by 3 publications

References 16 publications

Obstacle Avoidance Design of Aerial Robot Combining A star algorithm Algorithm and Optical Dynamic Capture Method

Obstacle Avoidance Design of Aerial Robot Combining A star algorithm Algorithm and Optical Dynamic Capture Method

Part B: Steering and control of an autonomous vehicle in emergency lane change maneuvers based on skilled driver’s performance

A high-speed human-like collision avoidance controller based on a neural network under different road adhesion coefficients

Contact Info

Product

Resources

About