東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Data-Driven Methods for Real-Time Co...

Weaver, Catherine Nichole,

FindBook

Google Book

Amazon

博客來

Data-Driven Methods for Real-Time Control in Autonomous Racing Games /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Data-Driven Methods for Real-Time Control in Autonomous Racing Games // Catherine Nichole Weaver.
作者:	Weaver, Catherine Nichole,
面頁冊數:	1 electronic resource (124 pages)
附註:	Source: Dissertations Abstracts International, Volume: 86-03, Section: B.
Contained By:	Dissertations Abstracts International86-03B.
標題:	Mechanical engineering. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31242663
ISBN:	9798384448204

Data-Driven Methods for Real-Time Control in Autonomous Racing Games /
Weaver, Catherine Nichole,

Data-Driven Methods for Real-Time Control in Autonomous Racing Games /Catherine Nichole Weaver. - 1 electronic resource (124 pages)

Source: Dissertations Abstracts International, Volume: 86-03, Section: B.

Offline datasets and demonstrations can provide valuable guidance for planning and control in robotic and intelligent systems. Often, demonstration data consists of sequences of observations and control actions that occurred in the environment, demonstrating a specific task or desirable behavior. They can originate from human experts or demonstrators, simple rule-based or model-based controllers, or even previously machine-learned policies. However, this data is most commonly unstructured, without annotations of underlying tasks, rewards, thoughts, rules, or states that were used by the demonstration generator. For long-horizon, complicated tasks, these unstructured demonstrations often fail to provide enough information to facilitate learning. Thus, additional structure in sequential demonstrations could inform or enhance learning-based planning and control.This dissertation explores how meaningful partitions of sequential data can guide and accelerate learning, and improve the performance and reliability of control systems. In particular, we primarily focus on the complicated task of planning and control for an autonomous racing vehicle, which must rapidly traverse a closed racetrack with complicated, unknown vehicle dynamics. We identify three challenges that exist in current algorithms for autonomous racing systems. First, the control system should be robust to state deviations and maintain control when it encounters previously unseen states. Second, training the control system should efficiently leverage its knowledge to minimize the number of environment interactions necessary to train a high-performance system. Third, the control system should emulate human behavior to race in predictable and understandable ways. In this dissertation, we explore how offline datasets can address these challenges while maintaining good racing performance through both modular planning and control and end-to-end learning. In the first part, we explore control systems that are built on separate planning and control modules. In particular, we design a trajectory generation module that can leverage an existing demonstration for fast, online trajectory planning. In Chapter 2, we propose a novel acceleration motion primitive for online trajectory generation that can plan trajectories that are better suited for the complex racing environment than existing methods. Analysis of the trajectories reveals that our method generates trajectories reduce the error between generated trajectories and the offline demonstration and lead to less aggressive acceleration and jerk than existing velocity motion primitives. In Chapter 3, we learn a sequence of motion primitives from a reference trajectory, and use the primitive sequence to generate racing trajectories in real-time. When used with Model Predictive Control (MPC), our proposed acceleration motion primitive and learning-based trajectory generation algorithm allows the MPC to recover from deviations from the reference while maintaining racing speeds. In the second part, we explore how offline data can improve end-to-end control policy learning. In Chapter 4, we tackle the problem of learning a control policy from long horizon sparse rewards by adding additional hierarchical structure from offline data. Our Skill-Critic method for online fine-tuning of the hierarchical policies reduces the requirements for online interactions with the environment and results in the fastest racer. In Chapter 5, rather than learning from a designed reward function, we tackle the problem of imitating human driver demonstrations. We propose a method that leverages offline sequence modeling architectures and online fine-tuning to imitate human racers. Our proposed method is more sample efficient. The resulting policies are more stable and are able to achieve the fastest lap-times compared to existing methods.

English

ISBN: 9798384448204Subjects--Topical Terms:

649730
Mechanical engineering.
Subjects--Index Terms:

Autonomous racing

Data-Driven Methods for Real-Time Control in Autonomous Racing Games /
LDR:05402nmm a22004693i 4500 001 2432380
005 20250707081451.5
006 m o d
007 cr|nu||||||||
008 261011s2024 miu||||||m |||||||eng d
020 $a 9798384448204
035 $a (MiAaPQD)AAI31242663
035 $a AAI31242663
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Weaver, Catherine Nichole, $e author. $3 3821580
245 1 0 $a Data-Driven Methods for Real-Time Control in Autonomous Racing Games / $c Catherine Nichole Weaver.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (124 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: 86-03, Section: B.
500 $a Advisors: Tomizuka, Masayoshi Committee members: Grigas, Paul; Aswani, Anil.
502 $b Ph.D. $c University of California, Berkeley $d 2024.
520 $a Offline datasets and demonstrations can provide valuable guidance for planning and control in robotic and intelligent systems. Often, demonstration data consists of sequences of observations and control actions that occurred in the environment, demonstrating a specific task or desirable behavior. They can originate from human experts or demonstrators, simple rule-based or model-based controllers, or even previously machine-learned policies. However, this data is most commonly unstructured, without annotations of underlying tasks, rewards, thoughts, rules, or states that were used by the demonstration generator. For long-horizon, complicated tasks, these unstructured demonstrations often fail to provide enough information to facilitate learning. Thus, additional structure in sequential demonstrations could inform or enhance learning-based planning and control.This dissertation explores how meaningful partitions of sequential data can guide and accelerate learning, and improve the performance and reliability of control systems. In particular, we primarily focus on the complicated task of planning and control for an autonomous racing vehicle, which must rapidly traverse a closed racetrack with complicated, unknown vehicle dynamics. We identify three challenges that exist in current algorithms for autonomous racing systems. First, the control system should be robust to state deviations and maintain control when it encounters previously unseen states. Second, training the control system should efficiently leverage its knowledge to minimize the number of environment interactions necessary to train a high-performance system. Third, the control system should emulate human behavior to race in predictable and understandable ways. In this dissertation, we explore how offline datasets can address these challenges while maintaining good racing performance through both modular planning and control and end-to-end learning. In the first part, we explore control systems that are built on separate planning and control modules. In particular, we design a trajectory generation module that can leverage an existing demonstration for fast, online trajectory planning. In Chapter 2, we propose a novel acceleration motion primitive for online trajectory generation that can plan trajectories that are better suited for the complex racing environment than existing methods. Analysis of the trajectories reveals that our method generates trajectories reduce the error between generated trajectories and the offline demonstration and lead to less aggressive acceleration and jerk than existing velocity motion primitives. In Chapter 3, we learn a sequence of motion primitives from a reference trajectory, and use the primitive sequence to generate racing trajectories in real-time. When used with Model Predictive Control (MPC), our proposed acceleration motion primitive and learning-based trajectory generation algorithm allows the MPC to recover from deviations from the reference while maintaining racing speeds. In the second part, we explore how offline data can improve end-to-end control policy learning. In Chapter 4, we tackle the problem of learning a control policy from long horizon sparse rewards by adding additional hierarchical structure from offline data. Our Skill-Critic method for online fine-tuning of the hierarchical policies reduces the requirements for online interactions with the environment and results in the fastest racer. In Chapter 5, rather than learning from a designed reward function, we tackle the problem of imitating human driver demonstrations. We propose a method that leverages offline sequence modeling architectures and online fine-tuning to imitate human racers. Our proposed method is more sample efficient. The resulting policies are more stable and are able to achieve the fastest lap-times compared to existing methods.
546 $a English
590 $a School code: 0028
650 4 $a Mechanical engineering. $3 649730
650 4 $a Computer engineering. $3 621879
650 4 $a Automotive engineering. $3 2181195
650 4 $a Information technology. $3 532993
650 4 $a Robotics. $3 519753
653 $a Autonomous racing
653 $a Autonomous vehicles
653 $a Control systems
653 $a Imitation learning
653 $a Reinforcement learning
690 $a 0548
690 $a 0489
690 $a 0464
690 $a 0800
690 $a 0771
690 $a 0540
710 2 $a University of California, Berkeley. $b Mechanical Engineering. $e degree granting institution. $3 3821326
720 1 $a Tomizuka, Masayoshi $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-03B.
790 $a 0028
791 $a Ph.D.
792 $a 2024
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31242663