Search-based task and motion planning for hybrid systems: Agile autonomous vehicles

Ajanović, Zlatan; Regolin, Enrico; Shyrokau, Barys; Hana, Ćatić,; Horn, Martin; Ferrara, Antonella

doi:10.1016/j.engappai.2023.105893

Cited by 13 publications

(3 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The strength of learning-based algorithms is their ability to adaptively adjust path planning strategies to different environments and driving needs through offline training [24], [25]. However, learning-based algorithms also face challenges such as large data requirements, long training times, and poor interpretability [26].…”

Section: Related Workmentioning

confidence: 99%

An Adaptive Path Planning Method for Curved Roads via Three-Dimensional Space-Aware Profiling Maps

Huang,

Dawton,

Arakawa

2024

IEEE Access

View full text Add to dashboard Cite

In modern transportation, autonomous driving technology has emerged as a significant innovation, offering improved safety, efficiency, and convenience. One of its core technologies is path planning, which creates an optimal route for vehicles in various traffic situations, ensuring they arrive safely and efficiently. However, existing path planning methods suffer from inflexible and inefficient road sampling, and limitations in path expression due to curve models. In this paper, we introduce a novel path planning framework that operates from a coarse-to-optimal approach. We first introduce an adaptive sampling method to construct a threedimensional (3D) space-aware profiling map in the Frenet frame to quantify abstract traffic scenarios. This cost map guides the generation of waypoints by incorporating obstacle distributions in the s-direction and cost values in the l-direction. We then design a cost function to obtain the coarse path by considering ride comfort, anti-deviation from the center of the road, and path safety. Finally, a new path model is re-established based on the Taylor series, and a quadratic programming approach is employed to fine-tune the coarse path to attain the optimal path. Experimental results show that the proposed adaptive sampling method can dynamically adjust the sampling strategy according to the change in the number and distribution of obstacles on the road, significantly improving the sampling effectiveness rate to 100 %, 99.85 %, 99.68 % and 99.61 % for oneobstacle, two-obstacle, three-obstacle, and four-obstacle scenarios. Compared to the conventional method, the generated path length is shortened by 3.48 % and 8.42 % and the maximum heading angle is reduced by 18.68 % and 30.21 % in the scenarios with obstacles of the same and different sizes. INDEX TERMS Path planning, frenet frame, cost function, taylor series, quadratic program, autonomous driving I. INTRODUCTION

show abstract

Section: Related Workmentioning

confidence: 99%

An Adaptive Path Planning Method for Curved Roads via Three-Dimensional Space-Aware Profiling Maps

Huang,

Dawton,

Arakawa

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The comparison of kinematic and dynamic models concerning experimental data [4] shows different statistics of forecast errors, including the effect of discretization error accumulation. In [8], a search-based method solves the problem with nonlinear and unstable dynamics.…”

Section: Introductionmentioning

confidence: 99%

“…In [12], the longitudinal and lateral motion control for the fourwheel independent drive intelligent vehicle was designed: the upper layer was the motion controller, and the lower layer was the control distributor. In [8], complex dynamics in a predictive manner were applied to achieve optimal robot behavior in dynamic scenarios.…”

Section: Introductionmentioning

confidence: 99%

Planning Speed Mode of All-Wheel Drive Autonomous Vehicles Considering Complete Constraint Set

Diachuk,

Easa

2024

Vehicles

View full text Add to dashboard Cite

The study aims to improve the technique of motion planning for all-wheel drive (AWD) autonomous vehicles (AVs) by including torque vectoring (TV) models and extended physical constraints. Four schemes for realizing the TV drive were considered: with braking internal wheels, using a rear-axle sport differential (SD), with braking front internal wheel and rear-axle SD, and with SDs on both axles. The mathematical model combines 2.5D vehicle dynamics model and a simplified drivetrain model with the self-locking central differential. The inverse approach implies optimizing the distribution of kinematic parameters by imposing a set of constraints. The optimization procedure uses the sequential quadratic programming (SQP) technique for the nonlinear constrained minimization. The Gaussian N-point quadrature scheme provides numerical integration. The distribution of control parameters (torque, braking moments, SDs’ friction moment) is performed by evaluating linear and nonlinear algebraic equations inside of optimization. The technique proposed demonstrates an essential difference between forecasts built with a pure kinematic model and those considering the vehicle’s drive/control features. Therefore, this approach contributes to the predictive accuracy and widening model properties by increasing the number of references, including for actuators and mechanisms.

show abstract

Introduction to the special issue on Intelligent Control and Optimisation

McLoone

Guelton

Guerra

et al. 2023

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

Search-based task and motion planning for hybrid systems: Agile autonomous vehicles

Cited by 13 publications

References 46 publications

An Adaptive Path Planning Method for Curved Roads via Three-Dimensional Space-Aware Profiling Maps

An Adaptive Path Planning Method for Curved Roads via Three-Dimensional Space-Aware Profiling Maps

Planning Speed Mode of All-Wheel Drive Autonomous Vehicles Considering Complete Constraint Set

Introduction to the special issue on Intelligent Control and Optimisation

Contact Info

Product

Resources

About