서브메뉴
검색
A Practical Approach to Learning Dynamics for Rough Terrain Navigation
A Practical Approach to Learning Dynamics for Rough Terrain Navigation
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20250211151001
- ISBN
- 9798382610849
- DDC
- 629.8
- 저자명
- Wang, Sean J.
- 서명/저자
- A Practical Approach to Learning Dynamics for Rough Terrain Navigation
- 발행사항
- [Sl] : Carnegie Mellon University, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 139 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 85-11, Section: B.
- 주기사항
- Advisor: Johnson, Aaron M.
- 학위논문주기
- Thesis (Ph.D.)--Carnegie Mellon University, 2024.
- 초록/해제
- 요약Unmanned ground vehicles offer great potential, but struggle in rough terrain environments due to their inability to reason about complex dynamics over longer horizons. Thus, driving strategies are often short-sighted and underutilize the robot's dynamic capabilities. This thesis addresses the challenges of long-horizon, dynamics-aware decision making in rough terrain, arising from the inability to model complex system dynamics. The findings reveal two key insights: 1) leveraging low-quality simulation data can reduce training requirements of real-world dynamics models; and 2) long-horizon decision making can still utilize imprecise dynamics models through careful handling of prediction uncertainty.We first discuss our model-based reinforcement learning approach for rough terrain navigation. This approach trains a dynamics model to predict the robot's trajectory over uneven terrain and capture prediction uncertainty. Decision making uses this model along with a closed-loop divergence constraint to aid in longer-horizon trajectory prediction and prevent exploitation of potentially problematic modeling errors. We show that this approach leads to robust, non-myopic driving strategies that take full advantage of the robot's capabilities.Next, we explore leveraging simulation to reduce real-world training data requirements. This culminates in an approach that uses a large variety of simulated systems to train a dynamics model that quickly and probabilistically adapts to any new, including real-world, target system using any available target system data. Using this model within an uncertainty-aware decision making framework results in safe, albeit low performance, driving upon initialization. As more target system observations are collected, the adaptive dynamics model becomes more tailored to the target system resulting in increased driving performance.Finally, we combine these concepts to form a non-myopic rough terrain navigation framework that can quickly and robustly adapt to new target systems. We show that upon initialization, this framework chooses conservative routes that avoids obstacles. However, after just one demonstration of driving over obstacles, the framework chooses more aggressive routes over obstacles that match the system's capabilities.
- 일반주제명
- Robotics
- 일반주제명
- Information technology
- 키워드
- Sim2real
- 기타저자
- Carnegie Mellon University Mechanical Engineering
- 기본자료저록
- Dissertations Abstracts International. 85-11B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008250123s2024 us c eng d■001000017160346
■00520250211151001
■006m o d
■007cr#unu||||||||
■020 ▼a9798382610849
■035 ▼a(MiAaPQ)AAI30993985
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a629.8
■1001 ▼aWang, Sean J.
■24512▼aA Practical Approach to Learning Dynamics for Rough Terrain Navigation
■260 ▼a[Sl]▼bCarnegie Mellon University▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a139 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 85-11, Section: B.
■500 ▼aAdvisor: Johnson, Aaron M.
■5021 ▼aThesis (Ph.D.)--Carnegie Mellon University, 2024.
■520 ▼aUnmanned ground vehicles offer great potential, but struggle in rough terrain environments due to their inability to reason about complex dynamics over longer horizons. Thus, driving strategies are often short-sighted and underutilize the robot's dynamic capabilities. This thesis addresses the challenges of long-horizon, dynamics-aware decision making in rough terrain, arising from the inability to model complex system dynamics. The findings reveal two key insights: 1) leveraging low-quality simulation data can reduce training requirements of real-world dynamics models; and 2) long-horizon decision making can still utilize imprecise dynamics models through careful handling of prediction uncertainty.We first discuss our model-based reinforcement learning approach for rough terrain navigation. This approach trains a dynamics model to predict the robot's trajectory over uneven terrain and capture prediction uncertainty. Decision making uses this model along with a closed-loop divergence constraint to aid in longer-horizon trajectory prediction and prevent exploitation of potentially problematic modeling errors. We show that this approach leads to robust, non-myopic driving strategies that take full advantage of the robot's capabilities.Next, we explore leveraging simulation to reduce real-world training data requirements. This culminates in an approach that uses a large variety of simulated systems to train a dynamics model that quickly and probabilistically adapts to any new, including real-world, target system using any available target system data. Using this model within an uncertainty-aware decision making framework results in safe, albeit low performance, driving upon initialization. As more target system observations are collected, the adaptive dynamics model becomes more tailored to the target system resulting in increased driving performance.Finally, we combine these concepts to form a non-myopic rough terrain navigation framework that can quickly and robustly adapt to new target systems. We show that upon initialization, this framework chooses conservative routes that avoids obstacles. However, after just one demonstration of driving over obstacles, the framework chooses more aggressive routes over obstacles that match the system's capabilities.
■590 ▼aSchool code: 0041.
■650 4▼aRobotics
■650 4▼aInformation technology
■653 ▼aModel-based reinforcement learning
■653 ▼aRough terrain navigation
■653 ▼aSim2real
■653 ▼aTerrain environments
■653 ▼aLearning dynamics
■690 ▼a0771
■690 ▼a0489
■690 ▼a0800
■71020▼aCarnegie Mellon University▼bMechanical Engineering.
■7730 ▼tDissertations Abstracts International▼g85-11B.
■790 ▼a0041
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17160346▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.


