Autonomous waypoints planning and trajectory generation for multi-rotor UAVs

Yilan Li, Hossein Eslamiat, Ningshan Wang, Ziyi Zhao, Amit Sanyal, Qinru Qiu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Autonomous trajectory generation in a complex environment is a challenging task for multi-rotor unmanned aerial vehicles (UAVs), which have high maneuverability in three-dimensional motion. Safe and effective operations for these UAVs demand obstacle avoidance strategies and advanced trajectory planning and control schemes for stability and energy efficiency. To solve those problems in one framework analytically is extremely challenging when the UAV needs to fly large distance in a complex environment. To address this challenge, a two-level optimization strategy is adopted. At the higher-level, a sequence of waypoints is selected that lead the UAV from its current position to the destination. At the lower-level, an optimal trajectory is generated between each pair of adjacent waypoints analytically. While the goal of trajectory generation is to maintain the stability of the UAV, the goal of the waypoints planning is to select waypoints with the lowest control thrust consumption throughout the entire trip while avoiding collisions with obstacles. The entire framework is implemented using deep reinforcement learning, which learns the highly complicated and non-linear interaction between those two levels, and the impact from the environment. A progressive learning strategy is investigated that not only reduces convergence time but also improves result quality. We further investigate and provide results regarding the tuning of gains in the optimal trajectory scheme using genetic algorithm. The experimental results demonstrate that our proposed approach is able to generate a list of obstacle-free waypoints with minimum control energy and develop an optimal trajectory with optimized platform velocity, acceleration, jerk and control thrust.

Original languageEnglish (US)
Title of host publicationDESTION 2019 - Proceedings of the Workshop on Design Automation for CPS and IoT
EditorsGowri Sankar Ramachandran, Jorge Ortiz
PublisherAssociation for Computing Machinery, Inc
Pages31-40
Number of pages10
ISBN (Electronic)9781450366991
DOIs
StatePublished - Apr 15 2019
Event2019 Workshop on Design Automation for CPS and IoT, DESTION 2019 - Montreal, Canada
Duration: Apr 15 2019 → …

Publication series

NameDESTION 2019 - Proceedings of the Workshop on Design Automation for CPS and IoT

Conference

Conference2019 Workshop on Design Automation for CPS and IoT, DESTION 2019
CountryCanada
CityMontreal
Period4/15/19 → …

Fingerprint

Trajectory Generation
Unmanned aerial vehicles (UAV)
Rotor
Optimal Trajectory
Rotors
Trajectories
Planning
Entire
Trajectory Planning
Obstacle Avoidance
Learning Strategies
Convergence Time
Nonlinear Interaction
Reinforcement Learning
Energy Efficiency
Lowest
Tuning
Maneuverability
Collision
Adjacent

Keywords

  • Deep reinforcement learning
  • Multi-rotor UAV
  • Optimal trajectory generation
  • Waypoints planning

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Networks and Communications
  • Computer Science Applications
  • Control and Systems Engineering
  • Modeling and Simulation

Cite this

Li, Y., Eslamiat, H., Wang, N., Zhao, Z., Sanyal, A., & Qiu, Q. (2019). Autonomous waypoints planning and trajectory generation for multi-rotor UAVs. In G. S. Ramachandran, & J. Ortiz (Eds.), DESTION 2019 - Proceedings of the Workshop on Design Automation for CPS and IoT (pp. 31-40). (DESTION 2019 - Proceedings of the Workshop on Design Automation for CPS and IoT). Association for Computing Machinery, Inc. https://doi.org/10.1145/3313151.3313163

Autonomous waypoints planning and trajectory generation for multi-rotor UAVs. / Li, Yilan; Eslamiat, Hossein; Wang, Ningshan; Zhao, Ziyi; Sanyal, Amit; Qiu, Qinru.

DESTION 2019 - Proceedings of the Workshop on Design Automation for CPS and IoT. ed. / Gowri Sankar Ramachandran; Jorge Ortiz. Association for Computing Machinery, Inc, 2019. p. 31-40 (DESTION 2019 - Proceedings of the Workshop on Design Automation for CPS and IoT).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Li, Y, Eslamiat, H, Wang, N, Zhao, Z, Sanyal, A & Qiu, Q 2019, Autonomous waypoints planning and trajectory generation for multi-rotor UAVs. in GS Ramachandran & J Ortiz (eds), DESTION 2019 - Proceedings of the Workshop on Design Automation for CPS and IoT. DESTION 2019 - Proceedings of the Workshop on Design Automation for CPS and IoT, Association for Computing Machinery, Inc, pp. 31-40, 2019 Workshop on Design Automation for CPS and IoT, DESTION 2019, Montreal, Canada, 4/15/19. https://doi.org/10.1145/3313151.3313163
Li Y, Eslamiat H, Wang N, Zhao Z, Sanyal A, Qiu Q. Autonomous waypoints planning and trajectory generation for multi-rotor UAVs. In Ramachandran GS, Ortiz J, editors, DESTION 2019 - Proceedings of the Workshop on Design Automation for CPS and IoT. Association for Computing Machinery, Inc. 2019. p. 31-40. (DESTION 2019 - Proceedings of the Workshop on Design Automation for CPS and IoT). https://doi.org/10.1145/3313151.3313163
Li, Yilan ; Eslamiat, Hossein ; Wang, Ningshan ; Zhao, Ziyi ; Sanyal, Amit ; Qiu, Qinru. / Autonomous waypoints planning and trajectory generation for multi-rotor UAVs. DESTION 2019 - Proceedings of the Workshop on Design Automation for CPS and IoT. editor / Gowri Sankar Ramachandran ; Jorge Ortiz. Association for Computing Machinery, Inc, 2019. pp. 31-40 (DESTION 2019 - Proceedings of the Workshop on Design Automation for CPS and IoT).
@inproceedings{a4ae40465a9548889c9596397272c93d,
title = "Autonomous waypoints planning and trajectory generation for multi-rotor UAVs",
abstract = "Autonomous trajectory generation in a complex environment is a challenging task for multi-rotor unmanned aerial vehicles (UAVs), which have high maneuverability in three-dimensional motion. Safe and effective operations for these UAVs demand obstacle avoidance strategies and advanced trajectory planning and control schemes for stability and energy efficiency. To solve those problems in one framework analytically is extremely challenging when the UAV needs to fly large distance in a complex environment. To address this challenge, a two-level optimization strategy is adopted. At the higher-level, a sequence of waypoints is selected that lead the UAV from its current position to the destination. At the lower-level, an optimal trajectory is generated between each pair of adjacent waypoints analytically. While the goal of trajectory generation is to maintain the stability of the UAV, the goal of the waypoints planning is to select waypoints with the lowest control thrust consumption throughout the entire trip while avoiding collisions with obstacles. The entire framework is implemented using deep reinforcement learning, which learns the highly complicated and non-linear interaction between those two levels, and the impact from the environment. A progressive learning strategy is investigated that not only reduces convergence time but also improves result quality. We further investigate and provide results regarding the tuning of gains in the optimal trajectory scheme using genetic algorithm. The experimental results demonstrate that our proposed approach is able to generate a list of obstacle-free waypoints with minimum control energy and develop an optimal trajectory with optimized platform velocity, acceleration, jerk and control thrust.",
keywords = "Deep reinforcement learning, Multi-rotor UAV, Optimal trajectory generation, Waypoints planning",
author = "Yilan Li and Hossein Eslamiat and Ningshan Wang and Ziyi Zhao and Amit Sanyal and Qinru Qiu",
year = "2019",
month = "4",
day = "15",
doi = "10.1145/3313151.3313163",
language = "English (US)",
series = "DESTION 2019 - Proceedings of the Workshop on Design Automation for CPS and IoT",
publisher = "Association for Computing Machinery, Inc",
pages = "31--40",
editor = "Ramachandran, {Gowri Sankar} and Jorge Ortiz",
booktitle = "DESTION 2019 - Proceedings of the Workshop on Design Automation for CPS and IoT",

}

TY - GEN

T1 - Autonomous waypoints planning and trajectory generation for multi-rotor UAVs

AU - Li, Yilan

AU - Eslamiat, Hossein

AU - Wang, Ningshan

AU - Zhao, Ziyi

AU - Sanyal, Amit

AU - Qiu, Qinru

PY - 2019/4/15

Y1 - 2019/4/15

N2 - Autonomous trajectory generation in a complex environment is a challenging task for multi-rotor unmanned aerial vehicles (UAVs), which have high maneuverability in three-dimensional motion. Safe and effective operations for these UAVs demand obstacle avoidance strategies and advanced trajectory planning and control schemes for stability and energy efficiency. To solve those problems in one framework analytically is extremely challenging when the UAV needs to fly large distance in a complex environment. To address this challenge, a two-level optimization strategy is adopted. At the higher-level, a sequence of waypoints is selected that lead the UAV from its current position to the destination. At the lower-level, an optimal trajectory is generated between each pair of adjacent waypoints analytically. While the goal of trajectory generation is to maintain the stability of the UAV, the goal of the waypoints planning is to select waypoints with the lowest control thrust consumption throughout the entire trip while avoiding collisions with obstacles. The entire framework is implemented using deep reinforcement learning, which learns the highly complicated and non-linear interaction between those two levels, and the impact from the environment. A progressive learning strategy is investigated that not only reduces convergence time but also improves result quality. We further investigate and provide results regarding the tuning of gains in the optimal trajectory scheme using genetic algorithm. The experimental results demonstrate that our proposed approach is able to generate a list of obstacle-free waypoints with minimum control energy and develop an optimal trajectory with optimized platform velocity, acceleration, jerk and control thrust.

AB - Autonomous trajectory generation in a complex environment is a challenging task for multi-rotor unmanned aerial vehicles (UAVs), which have high maneuverability in three-dimensional motion. Safe and effective operations for these UAVs demand obstacle avoidance strategies and advanced trajectory planning and control schemes for stability and energy efficiency. To solve those problems in one framework analytically is extremely challenging when the UAV needs to fly large distance in a complex environment. To address this challenge, a two-level optimization strategy is adopted. At the higher-level, a sequence of waypoints is selected that lead the UAV from its current position to the destination. At the lower-level, an optimal trajectory is generated between each pair of adjacent waypoints analytically. While the goal of trajectory generation is to maintain the stability of the UAV, the goal of the waypoints planning is to select waypoints with the lowest control thrust consumption throughout the entire trip while avoiding collisions with obstacles. The entire framework is implemented using deep reinforcement learning, which learns the highly complicated and non-linear interaction between those two levels, and the impact from the environment. A progressive learning strategy is investigated that not only reduces convergence time but also improves result quality. We further investigate and provide results regarding the tuning of gains in the optimal trajectory scheme using genetic algorithm. The experimental results demonstrate that our proposed approach is able to generate a list of obstacle-free waypoints with minimum control energy and develop an optimal trajectory with optimized platform velocity, acceleration, jerk and control thrust.

KW - Deep reinforcement learning

KW - Multi-rotor UAV

KW - Optimal trajectory generation

KW - Waypoints planning

UR - http://www.scopus.com/inward/record.url?scp=85066042108&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066042108&partnerID=8YFLogxK

U2 - 10.1145/3313151.3313163

DO - 10.1145/3313151.3313163

M3 - Conference contribution

T3 - DESTION 2019 - Proceedings of the Workshop on Design Automation for CPS and IoT

SP - 31

EP - 40

BT - DESTION 2019 - Proceedings of the Workshop on Design Automation for CPS and IoT

A2 - Ramachandran, Gowri Sankar

A2 - Ortiz, Jorge

PB - Association for Computing Machinery, Inc

ER -