Hierarchical Trajectory Planning of an Autonomous Car Based on the Integration of a Sampling and an Optimization Method

Lim, Wontaek; Lee, Seongjin; Sunwoo, Myoungho; Jo, Kichun

doi:10.1109/tits.2017.2756099

Cited by 202 publications

(107 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Assumptions A1, A2, A5 and A7 are common in the literature and are used to reduce complexity [2], [3]. The use of a high-level planning algorithm which is postulated in A3 is quite common in AV architectures too [10]. Lastly, A4 is necessary for a distributed control scheme and A6 can be satisfied by choosing the MPC sampling time appropriately.…”

Section: Modelingmentioning

confidence: 99%

Nonlinear Model Predictive Control for Distributed Motion Planning in Road Intersections Using PANOC

Katriniok

Sopasakis

Schuurmans

et al. 2019

2019 IEEE 58th Conference on Decision and Control (CDC)

View full text Add to dashboard Cite

The coordination of highly automated vehicles (or agents) in road intersections is an inherently nonconvex and challenging problem. In this paper, we propose a distributed motion planning scheme under reasonable vehicleto-vehicle communication requirements. Each agent solves a nonlinear model predictive control problem in real time and transmits its planned trajectory to other agents, which may have conflicting objectives. The problem formulation is augmented with conditional constraints that enable the agents to decide whether to wait at a stopping line, if safe crossing is not possible. The involved nonconvex problems are solved very efficiently using the proximal averaged Newton method for optimal control (PANOC). We demonstrate the efficiency of the proposed approach in a realistic intersection crossing scenario. A. Katriniok is with Ford Research

show abstract

Section: Modelingmentioning

confidence: 99%

Nonlinear Model Predictive Control for Distributed Motion Planning in Road Intersections Using PANOC

Katriniok

Sopasakis

Schuurmans

et al. 2019

2019 IEEE 58th Conference on Decision and Control (CDC)

View full text Add to dashboard Cite

show abstract

“…For example, automated guided vehicles (AGV) have been broadly applied to the handling of heavy objects or large devices in production environments [3], multi-axis CNC machines have been extensively used to machine parts with sculptured surfaces in the fields of machinofacture and aerospace [4], robots have been developed for welding, spraying and assembling in smart factories [5], firefighting robots have come into service in order to reduce the risks that human firefighters face [6], the Roomba promises its customers "effortless cleaning" or robot vacuums allow owners to "clean your floors without lifting a finger" [7], and feeding assistive robots have been proposed to help older people and people with disabilities in their daily life [8]. Thanks to the development of artificial intelligence [9], machine vision [10], sensor technology [11], etc., autonomous driving technology [12], as a new automation technology which is deeply integrated with various advanced technologies [13], is witnessed to have leapt forward in the last decade [14], and as a result, many unicorn enterprises are known to have developed, such as Waymo [15], Momenta [16], and Apollo [17].…”

Section: Introductionmentioning

confidence: 99%

HFO-LADRC Lateral Motion Controller for Autonomous Road Sweeper

Zeng

Liu

et al. 2020

Sensors

View full text Add to dashboard Cite

How to make a controller robust and stable to reject the disturbance of uncertainty is an inevitable challenge. Aiming at addressing the lateral control problem for an autonomous road sweeper, a heading-error-based first order linear active disturbance rejective controller (HFO-LADRC) is proposed in this paper. To eliminate the lateral error and the heading error at the same time, a new model, called the heading-error-based model, is proposed for lateral motion, and the Lyapunov function was employed to explore the convergence ability of the heading error and lateral error. Since the heading-error-based model is first order, the ADRC is designed as first order and linear, and each module of the HFO-LADRC has been devised in detail. To ensure solution accuracy, the fourth order Runge–Kutta method was adopted as the differential system solver, and a typical ring scenario and a double lane-changing scenario were designed referencing the standard. Considering the obvious influence, wheelbase uncertainty, steering ratio uncertainty and Gaussian white noise disturbance were taken into account for the tests. The results illustrate that, in the case of both wheelbase uncertainty and steer ratio uncertainty, the HFO-LADRC has strong robustness and stability compared with a typical pure pursuit controller and classical SO-LADRC.

show abstract

“…These planners will keep off obstacles by accurately controlling the trends of the curves. Optimal‐control‐based methods do not have integrated capabilities for keeping the subject vehicle away from an obstacle [15], and thus, it is necessary to utilise other algorithms to ensure the level of safety [16].…”

Section: Introductionmentioning

confidence: 99%

Methodology of hierarchical collision avoidance for high‐speed self‐driving vehicle based on motion‐decoupled extraction of scenarios

Liu

Chen

Lan

et al. 2020

IET intell. transp. syst

View full text Add to dashboard Cite

Hierarchical Trajectory Planning of an Autonomous Car Based on the Integration of a Sampling and an Optimization Method

Cited by 202 publications

References 33 publications

Nonlinear Model Predictive Control for Distributed Motion Planning in Road Intersections Using PANOC

Nonlinear Model Predictive Control for Distributed Motion Planning in Road Intersections Using PANOC

HFO-LADRC Lateral Motion Controller for Autonomous Road Sweeper

Methodology of hierarchical collision avoidance for high‐speed self‐driving vehicle based on motion‐decoupled extraction of scenarios

Contact Info

Product

Resources

About