Trajectory optimization for autonomous overtaking with visibility maximization

Hans Andersen; Wilko Schwarting; Felix Naser; You Hong Eng; Marcelo H. Ang; Daniela Rus; Javier Alonso-Mora

doi:10.1109/ITSC.2017.8317853

Trajectory optimization for autonomous overtaking with visibility maximization

Hans Andersen^*, Wilko Schwarting, Felix Naser, You Hong Eng, Marcelo H. Ang, Daniela Rus, Javier Alonso-Mora

^*Corresponding author for this work

Learning & Autonomous Control

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

38 Citations (Scopus)

Abstract

In this paper we present a trajectory generation method for autonomous overtaking of static obstacles in a dynamic urban environment. In these settings, blind spots can arise from perception limitations. For example, the autonomous car may have to move slightly into the opposite lane in order to cleanly see in front of a car ahead. Once it has gathered enough information about the road ahead, then the autonomous car can safely overtake. We generate safe trajectories by solving, in real-time, a non-linear constrained optimization, formulated as a Receding Horizon planner. The planner is guided by a high-level state machine, which determines when the overtake maneuver should begin. Our main contribution is a method that can maximize visibility, prioritizes safety and respects the boundaries of the road while executing the maneuver. We present experimental results in simulation with data collected during real driving.

Original language	English
Title of host publication	Proceedings 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC 2017)
Place of Publication	Piscataway, NJ, USA
Publisher	IEEE
Number of pages	8
ISBN (Electronic)	978-1-5386-1525-6
DOIs	https://doi.org/10.1109/ITSC.2017.8317853
Publication status	Published - 2017
Event	20th IEEE International Conference on Intelligent Transport Systems, ITSC 2017 - Mielparque Yokohama, Yokohama, Japan Duration: 16 Oct 2017 → 19 Oct 2017 Conference number: 20 http://www.itsc2017.org/ http://www.itsc2017.org/

Conference

Conference	20th IEEE International Conference on Intelligent Transport Systems, ITSC 2017
Abbreviated title	ITSC 2017
Country/Territory	Japan
City	Yokohama
Period	16/10/17 → 19/10/17
Internet address	http://www.itsc2017.org/ http://www.itsc2017.org/

Keywords

Trajectory
Autonomous vehicles
Roads
Urban areas
Vehicle dynamics
Planning
Optimization

Access to Document

10.1109/ITSC.2017.8317853

Cite this

@inproceedings{4625078213534d84bfc31f914023d974,

title = "Trajectory optimization for autonomous overtaking with visibility maximization",

abstract = "In this paper we present a trajectory generation method for autonomous overtaking of static obstacles in a dynamic urban environment. In these settings, blind spots can arise from perception limitations. For example, the autonomous car may have to move slightly into the opposite lane in order to cleanly see in front of a car ahead. Once it has gathered enough information about the road ahead, then the autonomous car can safely overtake. We generate safe trajectories by solving, in real-time, a non-linear constrained optimization, formulated as a Receding Horizon planner. The planner is guided by a high-level state machine, which determines when the overtake maneuver should begin. Our main contribution is a method that can maximize visibility, prioritizes safety and respects the boundaries of the road while executing the maneuver. We present experimental results in simulation with data collected during real driving.",

keywords = "Trajectory, Autonomous vehicles, Roads, Urban areas , Vehicle dynamics, Planning, Optimization",

author = "Hans Andersen and Wilko Schwarting and Felix Naser and Eng, {You Hong} and Ang, {Marcelo H.} and Daniela Rus and Javier Alonso-Mora",

year = "2017",

doi = "10.1109/ITSC.2017.8317853",

language = "English",

booktitle = "Proceedings 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC 2017)",

publisher = "IEEE",

address = "United States",

note = "20th IEEE International Conference on Intelligent Transport Systems, ITSC 2017, ITSC 2017 ; Conference date: 16-10-2017 Through 19-10-2017",

url = "http://www.itsc2017.org/, http://www.itsc2017.org/",

}

Andersen, H, Schwarting, W, Naser, F, Eng, YH, Ang, MH, Rus, D & Alonso-Mora, J 2017, Trajectory optimization for autonomous overtaking with visibility maximization. in Proceedings 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC 2017). IEEE, Piscataway, NJ, USA, 20th IEEE International Conference on Intelligent Transport Systems, ITSC 2017, Yokohama, Japan, 16/10/17. https://doi.org/10.1109/ITSC.2017.8317853

Trajectory optimization for autonomous overtaking with visibility maximization. / Andersen, Hans; Schwarting, Wilko; Naser, Felix et al.
Proceedings 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC 2017). Piscataway, NJ, USA: IEEE, 2017.

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Trajectory optimization for autonomous overtaking with visibility maximization

AU - Andersen, Hans

AU - Schwarting, Wilko

AU - Naser, Felix

AU - Eng, You Hong

AU - Ang, Marcelo H.

AU - Rus, Daniela

AU - Alonso-Mora, Javier

N1 - Conference code: 20

PY - 2017

Y1 - 2017

N2 - In this paper we present a trajectory generation method for autonomous overtaking of static obstacles in a dynamic urban environment. In these settings, blind spots can arise from perception limitations. For example, the autonomous car may have to move slightly into the opposite lane in order to cleanly see in front of a car ahead. Once it has gathered enough information about the road ahead, then the autonomous car can safely overtake. We generate safe trajectories by solving, in real-time, a non-linear constrained optimization, formulated as a Receding Horizon planner. The planner is guided by a high-level state machine, which determines when the overtake maneuver should begin. Our main contribution is a method that can maximize visibility, prioritizes safety and respects the boundaries of the road while executing the maneuver. We present experimental results in simulation with data collected during real driving.

AB - In this paper we present a trajectory generation method for autonomous overtaking of static obstacles in a dynamic urban environment. In these settings, blind spots can arise from perception limitations. For example, the autonomous car may have to move slightly into the opposite lane in order to cleanly see in front of a car ahead. Once it has gathered enough information about the road ahead, then the autonomous car can safely overtake. We generate safe trajectories by solving, in real-time, a non-linear constrained optimization, formulated as a Receding Horizon planner. The planner is guided by a high-level state machine, which determines when the overtake maneuver should begin. Our main contribution is a method that can maximize visibility, prioritizes safety and respects the boundaries of the road while executing the maneuver. We present experimental results in simulation with data collected during real driving.

KW - Trajectory

KW - Autonomous vehicles

KW - Roads

KW - Urban areas

KW - Vehicle dynamics

KW - Planning

KW - Optimization

UR - http://www.scopus.com/inward/record.url?scp=85046251385&partnerID=8YFLogxK

U2 - 10.1109/ITSC.2017.8317853

DO - 10.1109/ITSC.2017.8317853

M3 - Conference contribution

AN - SCOPUS:85046251385

BT - Proceedings 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC 2017)

PB - IEEE

CY - Piscataway, NJ, USA

T2 - 20th IEEE International Conference on Intelligent Transport Systems, ITSC 2017

Y2 - 16 October 2017 through 19 October 2017

ER -

Trajectory optimization for autonomous overtaking with visibility maximization

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this