東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Energy-Efficient Motion Planning and...

Joa, Eunhyek,

Linked to FindBook

Google Book

Amazon

博客來

Energy-Efficient Motion Planning and Control for Connected, Automated Vehicles /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Energy-Efficient Motion Planning and Control for Connected, Automated Vehicles // Eunhyek Joa.
Author:	Joa, Eunhyek,
Description:	1 electronic resource (163 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 86-09, Section: A.
Contained By:	Dissertations Abstracts International86-09A.
Subject:	Automotive engineering. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31766421
ISBN:	9798310102866

Energy-Efficient Motion Planning and Control for Connected, Automated Vehicles /
Joa, Eunhyek,

Energy-Efficient Motion Planning and Control for Connected, Automated Vehicles /Eunhyek Joa. - 1 electronic resource (163 pages)

Source: Dissertations Abstracts International, Volume: 86-09, Section: A.

As the demand for sustainable transportation solutions continues to rise, Connected Automated Vehicles (CAVs) present a promising opportunity to reduce energy consumption and environmental impact significantly. This dissertation addresses the challenge of developing energy-efficient motion planning and control strategies for CAVs.The research problem is to minimize total energy consumption while satisfying safety and input constraints for a given route. The key challenges are twofold. First, the long-horizon nature of the energy consumption minimization problem makes real-time computation difficult, as computational demands grow with the time horizon. Second, unlike fully autonomous vehicles equipped with precise localization systems such as LiDAR and high-definition maps, partial or conditionally automated vehicles rely on less precise localization methods, leading to meter-level localization uncertainty that introduces stochasticity to the optimal control problem. As a result, the problem is framed as a long-horizon stochastic optimal control problem, where both computational efficiency and addressing uncertainty are critical.To tackle these challenges, we present a data-driven approach to derive an approximate solution to the energy consumption minimization problem. We approach this by leveraging Model Predictive Control (MPC). Specifically, the long-horizon stochastic optimal control problem is approximated with the shorter-horizon optimal control problem, solved in a receding horizon manner. This reformulation makes the problem computationally tractable for real-time implementation. Additionally, to avoid myopic behavior due to the shorter horizon, we construct a value function using data-driven techniques and prove that as the dataset grows, the performance of our approximate solution converges to that of the long horizon stochastic optimal control problem. This is a key contribution, ensuring the approach remains effective while maintaining computational efficiency.We apply this method to the specific case of longitudinal motion planning for CAVs, focusing on scenarios where localization uncertainty is present. To validate the effectiveness of the proposed method, we conduct Vehicle-in-the-Loop (VIL) experiments, where a real vehicle is tested in an actual environment while the surrounding vehicles, traffic signals, and other elements of the driving scenario are simulated. These experiments demonstrate that our method achieves better energy efficiency compared to state-of-the-art algorithms designed for energy-efficient motion planning.Furthermore, we explore the potential for lateral motion planning to improve energy efficiency beyond what can be achieved through longitudinal motion planning alone. By considering lateral maneuvers such as lane changes, we show that additional energy savings are possible by validating through VIL experiments.

English

ISBN: 9798310102866Subjects--Topical Terms:

2181195
Automotive engineering.
Subjects--Index Terms:

Connected Automated Vehicles

Energy-Efficient Motion Planning and Control for Connected, Automated Vehicles /
LDR:04368nmm a22004333i 4500 001 2432618
005 20250731101857.5
006 m o d
007 cr|nu||||||||
008 261011s2024 miu||||||m |||||||eng d
020 $a 9798310102866
035 $a (MiAaPQD)AAI31766421
035 $a AAI31766421
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Joa, Eunhyek, $e author. $3 3821912
245 1 0 $a Energy-Efficient Motion Planning and Control for Connected, Automated Vehicles / $c Eunhyek Joa.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (163 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 86-09, Section: A.
500 $a Advisors: Borrelli, Francesco Committee members: Tomizuka, Masayoshi; Moura, Scott.
502 $b Ph.D.Eng. $c University of California, Berkeley $d 2024.
520 $a As the demand for sustainable transportation solutions continues to rise, Connected Automated Vehicles (CAVs) present a promising opportunity to reduce energy consumption and environmental impact significantly. This dissertation addresses the challenge of developing energy-efficient motion planning and control strategies for CAVs.The research problem is to minimize total energy consumption while satisfying safety and input constraints for a given route. The key challenges are twofold. First, the long-horizon nature of the energy consumption minimization problem makes real-time computation difficult, as computational demands grow with the time horizon. Second, unlike fully autonomous vehicles equipped with precise localization systems such as LiDAR and high-definition maps, partial or conditionally automated vehicles rely on less precise localization methods, leading to meter-level localization uncertainty that introduces stochasticity to the optimal control problem. As a result, the problem is framed as a long-horizon stochastic optimal control problem, where both computational efficiency and addressing uncertainty are critical.To tackle these challenges, we present a data-driven approach to derive an approximate solution to the energy consumption minimization problem. We approach this by leveraging Model Predictive Control (MPC). Specifically, the long-horizon stochastic optimal control problem is approximated with the shorter-horizon optimal control problem, solved in a receding horizon manner. This reformulation makes the problem computationally tractable for real-time implementation. Additionally, to avoid myopic behavior due to the shorter horizon, we construct a value function using data-driven techniques and prove that as the dataset grows, the performance of our approximate solution converges to that of the long horizon stochastic optimal control problem. This is a key contribution, ensuring the approach remains effective while maintaining computational efficiency.We apply this method to the specific case of longitudinal motion planning for CAVs, focusing on scenarios where localization uncertainty is present. To validate the effectiveness of the proposed method, we conduct Vehicle-in-the-Loop (VIL) experiments, where a real vehicle is tested in an actual environment while the surrounding vehicles, traffic signals, and other elements of the driving scenario are simulated. These experiments demonstrate that our method achieves better energy efficiency compared to state-of-the-art algorithms designed for energy-efficient motion planning.Furthermore, we explore the potential for lateral motion planning to improve energy efficiency beyond what can be achieved through longitudinal motion planning alone. By considering lateral maneuvers such as lane changes, we show that additional energy savings are possible by validating through VIL experiments.
546 $a English
590 $a School code: 0028
650 4 $a Automotive engineering. $3 2181195
650 4 $a Engineering. $3 586835
650 4 $a Transportation. $3 555912
650 4 $a Mechanical engineering. $3 649730
653 $a Connected Automated Vehicles
653 $a Motion planning
653 $a Model Predictive Control
653 $a Vehicle-in-the-Loop
690 $a 0540
690 $a 0537
690 $a 0548
690 $a 0709
710 2 $a University of California, Berkeley. $b Mechanical Engineering. $e degree granting institution. $3 3821326
720 1 $a Borrelli, Francesco $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-09A.
790 $a 0028
791 $a Ph.D.Eng.
792 $a 2024
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31766421