서브메뉴
검색
Spiking Neural Networks Enabled Circuits and Systems for Edge Robots
Spiking Neural Networks Enabled Circuits and Systems for Edge Robots
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260209102902
- ISBN
- 9798265404909
- DDC
- 620
- 서명/저자
- Spiking Neural Networks Enabled Circuits and Systems for Edge Robots
- 발행사항
- [Sl] : Georgia Institute of Technology, 2023
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2023
- 형태사항
- 154 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 87-05, Section: B.
- 주기사항
- Advisor: Raychowdhury, Arijit.
- 학위논문주기
- Thesis (Ph.D.)--Georgia Institute of Technology, 2023.
- 초록/해제
- 요약Robotic computing at the edge needs to meet multiple constraints on power and form factor while delivering the required performance for power-hungry neural network kernels. This work proposed spiking neural network (SNN) alternatives and augmentations for algorithms and circuits for edge robots. We show SNN-driven locomotion for powerconstrained hexapod robots, SNN-augmented target tracking for high-speed aerial robots and SNN-assisted visual navigation for size-critical micro-robots.The first part (Chapters II and III) of the work extends the rhythmic leg movement of insects to an SNN-based gait generator to demonstrate an online reward-based training method for autonomous learning to walk. We then utilize an event-based vision sensor as the sensory front-end to the hexapod locomotion to show the first spike-only closed-loop robotic platform.In the second part (Chapter IV and V), we observe that SNN and event-camera forms a sensor-processor pair well-suited for high-speed processing while frame-camera with convolutional neural network (CNN) suits the applications with the high-accuracy requirement. This trade-off between accuracy vs. latency in the event and frame-based visual processing arises from the detailed temporal and spatial resolutions captured by event and frame cameras respectively. We utilize these complementary strengths to build high-speed target identification and tracking system with SNN providing high-speed but noisy target estimates with CNN preserving the lost accuracy by providing reliable periodic anchors. We build a heterogeneous SoC with low-power RRAM compute-in-memory mapping CNN and highspeed SRAM compute-near-memory accelerating SNN. We also extend this framework of fused event and frame processing to optical flow to generalize it beyond target tracking applications.The final part (Chapter VI) of the work generalizes the idea of multi-modal processing applied in the previous chapters to divide the robotic computing workloads between CNN perception front-end and SNN localization back-end. Our SoC uses RRAM compute-nearmemory kernels to accelerate CNN-based perception while SRAM compute-in-memory carries out SNN-based localization for micro-robots. To summarize, this work attempted to substitute and augment compute-constrained robotic computing with SNN for energy saving and performance improvement.
- 일반주제명
- Robots
- 일반주제명
- Neurons
- 일반주제명
- Surveillance
- 일반주제명
- Energy consumption
- 일반주제명
- Neural networks
- 일반주제명
- Legs
- 일반주제명
- Robotics
- 기본자료저록
- Dissertations Abstracts International. 87-05B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260203s2023 us c eng d■001000017365956
■00520260209102902
■006m o d
■007cr#unu||||||||
■020 ▼a9798265404909
■035 ▼a(MiAaPQ)AAI32315543
■035 ▼a(MiAaPQ)GeorgiaTech75596
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a620
■1001 ▼aLele, Ashwin Sanjay.
■24510▼aSpiking Neural Networks Enabled Circuits and Systems for Edge Robots
■260 ▼a[Sl]▼bGeorgia Institute of Technology▼c2023
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2023
■300 ▼a154 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 87-05, Section: B.
■500 ▼aAdvisor: Raychowdhury, Arijit.
■5021 ▼aThesis (Ph.D.)--Georgia Institute of Technology, 2023.
■520 ▼aRobotic computing at the edge needs to meet multiple constraints on power and form factor while delivering the required performance for power-hungry neural network kernels. This work proposed spiking neural network (SNN) alternatives and augmentations for algorithms and circuits for edge robots. We show SNN-driven locomotion for powerconstrained hexapod robots, SNN-augmented target tracking for high-speed aerial robots and SNN-assisted visual navigation for size-critical micro-robots.The first part (Chapters II and III) of the work extends the rhythmic leg movement of insects to an SNN-based gait generator to demonstrate an online reward-based training method for autonomous learning to walk. We then utilize an event-based vision sensor as the sensory front-end to the hexapod locomotion to show the first spike-only closed-loop robotic platform.In the second part (Chapter IV and V), we observe that SNN and event-camera forms a sensor-processor pair well-suited for high-speed processing while frame-camera with convolutional neural network (CNN) suits the applications with the high-accuracy requirement. This trade-off between accuracy vs. latency in the event and frame-based visual processing arises from the detailed temporal and spatial resolutions captured by event and frame cameras respectively. We utilize these complementary strengths to build high-speed target identification and tracking system with SNN providing high-speed but noisy target estimates with CNN preserving the lost accuracy by providing reliable periodic anchors. We build a heterogeneous SoC with low-power RRAM compute-in-memory mapping CNN and highspeed SRAM compute-near-memory accelerating SNN. We also extend this framework of fused event and frame processing to optical flow to generalize it beyond target tracking applications.The final part (Chapter VI) of the work generalizes the idea of multi-modal processing applied in the previous chapters to divide the robotic computing workloads between CNN perception front-end and SNN localization back-end. Our SoC uses RRAM compute-nearmemory kernels to accelerate CNN-based perception while SRAM compute-in-memory carries out SNN-based localization for micro-robots. To summarize, this work attempted to substitute and augment compute-constrained robotic computing with SNN for energy saving and performance improvement.
■590 ▼aSchool code: 0078.
■650 4▼aRobots
■650 4▼aNeurons
■650 4▼aSurveillance
■650 4▼aEnergy consumption
■650 4▼aNeural networks
■650 4▼aLegs
■650 4▼aRobotics
■690 ▼a0800
■690 ▼a0771
■71020▼aGeorgia Institute of Technology.
■7730 ▼tDissertations Abstracts International▼g87-05B.
■790 ▼a0078
■791 ▼aPh.D.
■792 ▼a2023
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17365956▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.


