자료유형 | 학위논문 |
---|---|
서명/저자사항 | A Unified Visual-haptic Fingertip Sensor for Advanced Robot Dexterity. |
개인저자 | Patel, Radhen B. |
단체저자명 | University of Colorado at Boulder. Computer Science. |
발행사항 | [S.l.]: University of Colorado at Boulder., 2019. |
발행사항 | Ann Arbor: ProQuest Dissertations & Theses, 2019. |
형태사항 | 153 p. |
기본자료 저록 | Dissertations Abstracts International 81-05B. Dissertation Abstract International |
ISBN | 9781088377406 |
학위논문주기 | Thesis (Ph.D.)--University of Colorado at Boulder, 2019. |
일반주기 |
Source: Dissertations Abstracts International, Volume: 81-05, Section: B.
Advisor: Correll, Nikolaus J. |
이용제한사항 | This item must not be sold to any third party vendors. |
요약 | The problem of robotic grasping and manipulation requires a system level perspective that needs to be aimed at solving the interlinked sub-problems simultaneously. These sub-problems consists of designing an appropriate robot hand, sensing technology, control, and planning strategy, that can increase the dexterity of a robot hand in complex environments. Approaches towards these lack the proper use and integration of tactile feedback that can potentially enable robot hands with far superior capabilities than found today. This thesis addresses this challenge from three aspects: hardware design, system integration, and algorithm development. On the hardware side, it traces the thorough development of a multi and cross-modal tactile sensor that can measure proximity, contact, and force (PCF). Three unique features of the PCF sensor are (i) the ability to measure visual as well as tactile object features, (ii) its low manufacturing cost and (iii) that it can be easily integrated into different type of robot hands. This is achieved by embedding infrared proximity sensing integrated chips in soft elastomer to achieve a multitude of signals. On the system integration side, the thesis manifests the individual importance of the hand design, visual and tactile sensing modalities in the context of robotic manipulation related tasks through careful real-world robotic experiments. On the algorithmic side, it shows the implementation of several algorithms concerning signal processing, computer vision, controls, probabilistic theory and machine learning for experimental evaluation. |
일반주제명 | Robotics. Computer engineering. |
언어 | 영어 |
바로가기 | ![]() |