Accurate Path Tracking by Adjusting Look-Ahead Point in Pure Pursuit Method

Ahn, Joonwoo; Shin, Seokmin; Kim, Min Soo; Park, Jaeheung

doi:10.1007/s12239-021-0013-7

Cited by 44 publications

(18 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, there are some shortcomings in this approach in the empirical tuning of the look-ahead parameters which can have a strong effect on performance. Future work could include incorporating an optimized look-ahead distance such as in [11] or [8]. Additionally this method does not truly incorporate the ability to handle changing conditions outside of feedback once disturbances occur.…”

Section: G Discussionmentioning

confidence: 99%

Robust Modeling and Controls for Racing on the Edge

Spisak¹,

Saba²,

Suvarna³

et al. 2022

Preprint

View full text Add to dashboard Cite

Race cars are routinely driven to the edge of their handling limits in dynamic scenarios well above 200mph. Similar challenges are posed in autonomous racing, where a software stack, instead of a human driver, interacts within a multi-agent environment. For an Autonomous Racing Vehicle (ARV), operating at the edge of handling limits and acting safely in these dynamic environments is still an unsolved problem. In this paper, we present a baseline controls stack for an ARV capable of operating safely up to 140mph. Additionally, limitations in the current approach are discussed to highlight the need for improved dynamics modeling and learning.

show abstract

Section: G Discussionmentioning

confidence: 99%

Robust Modeling and Controls for Racing on the Edge

Spisak¹,

Saba²,

Suvarna³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Based on the work of Ahn J et al [30], this paper proposes a improved method to the search look-ahead point. In the work that has been carried out, as shown in Figure 11, p v is the vehicle location, p w is the point closest to the vehicle on the reference path, r min (v) is the minimum turning radius of the vehicle at speed v. Find the shortest Dubins path within the search range (the red dotted line in Figure 11), the intersection of the Dubins path and the reference path (the blue dashed line in Figure 11) is the look-ahead point p d [31].…”

Section: Improved Algorithm To Search Look-ahead Pointmentioning

confidence: 99%

A Control Strategy for Improving the Accuracy of Lateral Tracking of Autonomous Vehicles

Liu

et al. 2022

Preprint

View full text Add to dashboard Cite

Lateral tracking is one of the key technologies for autonomous vehicles. It is particularly important when vehicles are traveling at low speeds in narrow and complex scenes, such as parking lots and alleys. In order to improve the effective and accurate control of the traditional Pure Pursuit algorithm (PP) in the lateral tracking of low-speed autonomous vehicles, a continuous adaptive piecewise fitting method based on cubic Bezier curve was proposed to smooth the reference path, and then search the look-ahead point according to the geometric relationship between the vehicle and the reference path: An improved search algorithm based on vehicle speed and road curvature was used to search the look-ahead point. If the reference path curvature changes too much, the preliminarily obtained look-ahead point are modified, and finally the improved control algorithm (Improve Pure Pursuit Method (IPP) was obtained to calculate the steering Angle of the front wheel. Subsequently, the Carsim/Simulink co-simulation model and the autonomous vehicle platform were established for verification. Simulation and real Vehicle verification show that, compared with the pure pursuit algorithm based on Vehicle speed control (VPP) and Fuzzy Logic control pure Pursuit (FPP), IPP can perform better in complex low-speed lateral tracking scenes, reduce the problem of cutting-corner when the vehicle enters a corner, and improve the lateral tracking accuracy.

show abstract

“…To collect training data, the expert selects the lookahead point a exp,t ∈ {a exp,t x , a exp,t y }, and the vehicle is controlled to reach the selected look-ahead point in realtime. The steering angle command is calculated with the pure pursuit algorithm [34]. The velocity command is proportional to the distance between the look-ahead point and the vehicle.…”

Section: Datasetmentioning

confidence: 99%

“…The pure pursuit algorithm [34] was used to calculate the steering angle command (δ ) to reach the look-ahead point:…”

Section: Vehicle and Hardwarementioning

confidence: 99%

See 1 more Smart Citation

Vision-based Autonomous Driving for Unstructured Environments Using Imitation Learning

Ahn¹,

Kim²,

Park³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Unstructured environments are difficult for autonomous driving. This is because various unknown obstacles are lied in drivable space without lanes, and its width and curvature change widely. In such complex environments, searching for a path in real-time is difficult. Also, inaccurate localization data reduce the path tracking accuracy, increasing the risk of collision. Instead of searching and tracking the path, an alternative approach has been proposed that reactively avoids obstacles in real-time. Some methods are available for tracking global path while avoiding obstacles using the candidate paths and the artificial potential field. However, these methods require heuristics to find specific parameters for handling various complex environments. In addition, it is difficult to track the global path accurately in practice because of inaccurate localization data. If the drivable space is not accurately recognized (i.e., noisy state), the vehicle may not smoothly drive or may collide with obstacles. In this study, a method in which the vehicle drives toward drivable space only using a vision-based occupancy grid map is proposed. The proposed method uses imitation learning, where a deep neural network is trained with expert driving data. The network can learn driving patterns suited for various complex and noisy situations because these situations are contained in the training data. Experiments with a vehicle in actual parking lots demonstrated the limitations of general model-based methods and the effectiveness of the proposed imitation learning method.

show abstract

Accurate Path Tracking by Adjusting Look-Ahead Point in Pure Pursuit Method

Cited by 44 publications

References 15 publications

Robust Modeling and Controls for Racing on the Edge

Robust Modeling and Controls for Racing on the Edge

A Control Strategy for Improving the Accuracy of Lateral Tracking of Autonomous Vehicles

Vision-based Autonomous Driving for Unstructured Environments Using Imitation Learning

Contact Info

Product

Resources

About