Learning to assess grasp stability from vision, touch and proprioception
Başlık çevirisi mevcut değil.
- Tez No: 402211
- Danışmanlar: DR. DANICA KRAGIC
- Tez Türü: Doktora
- Konular: Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve Kontrol, Bilim ve Teknoloji, Computer Engineering and Computer Science and Control, Science and Technology
- Anahtar Kelimeler: Belirtilmemiş.
- Yıl: 2012
- Dil: İngilizce
- Üniversite: KTH-Kungliga Tekniska Högskolan (Royal Institute of Technology)
- Enstitü: Yurtdışı Enstitü
- Ana Bilim Dalı: Belirtilmemiş.
- Bilim Dalı: Belirtilmemiş.
- Sayfa Sayısı: 105
Özet
Özet yok.
Özet (Çeviri)
Grasping and manipulation of objects is an integral part of a robot's physical interaction with the environment. In order to cope with real-world situations, sensor based grasping of objects and grasp stability estimation is an important skill. This thesis addresses the problem of predicting the stability of a grasp from the perceptions available to a robot once fingers close around the object before attempting to lift it. A re-grasping step can be triggered if an unstable grasp is identified. The percepts considered consist of object features (visual), gripper configurations (proprioceptive) and tactile imprints (haptic) when fingers contact the object. This thesis studies tactile based stability estimation by applying machine learning methods such as Hidden Markov Models. An approach to integrate visual and tactile feedback is also introduced to further improve the predictions of grasp stability, using Kernel Logistic Regression models. Like humans, robots are expected to grasp and manipulate objects in a goal-oriented manner. In other words, objects should be grasped so to afford subsequent actions: if I am to hammer a nail, the hammer should be grasped so to afford hammering. Most of the work on grasping commonly addresses only the problem of finding a stable grasp without considering the task/action a robot is supposed to fulfill with an object. This thesis also studies grasp stability assessment in a task-oriented way based on a generative approach using probabilistic graphical models, Bayesian Networks. We integrate high-level task information introduced by a teacher in a supervised setting with low-level stability requirements acquired through a robot's exploration. The graphical model is used to encode probabilistic relationships between tasks and sensory data (visual, tactile and proprioceptive). The generative modeling approach enables inference of appropriate grasping configurations, as well as prediction of grasp stability. Overall, results indicate that the idea of exploiting learning approaches for grasp stability assessment is applicable in realistic scenarios.
Benzer Tezler
- Bilişim teknolojileri ve yazılım dersi öğretim programının öğretmen görüşlerine göre değerlendirilmesi (Ege bölgesi örneği)
The evaluation of information technologies and software course's curriculum according to the teacher's ideas
BETÜL ÇELEBİ UZGUR
Yüksek Lisans
İngilizce
2014
Eğitim ve ÖğretimMuğla Sıtkı Koçman ÜniversitesiEğitim Bilimleri Ana Bilim Dalı
DOÇ. DR. NECDET AYKAÇ
- Karşılaştırma
Bencmarking
BURÇAK ERENMEMİŞOĞLU
Yüksek Lisans
Türkçe
1997
Endüstri ve Endüstri Mühendisliğiİstanbul Teknik ÜniversitesiMühendislik Yönetimi Ana Bilim Dalı
PROF. DR. MURAT DİNÇMEN
- Somuttan soyuta: Temel tasarım stüdyosunda bir başlangıç pratiği olarak yaparak tasarlama
From concrete to abstract: Designing by doing as an initial practice in basic design studio
BERİL GÖK
Yüksek Lisans
Türkçe
2024
Eğitim ve Öğretimİstanbul Teknik ÜniversitesiMimarlık Ana Bilim Dalı
PROF. DR. YÜKSEL DEMİR
- Evaluating peacebuilding initiatives using multiple methodologies: Lessons learned from a Greek-Turkish peace education
Barış girişimlerinin çoklu metodoloji ile değerlendirilmesi: Bir Türk-Yunan barış eğitimi girişiminden çıkan dersler
GENCO ORKUN GENÇ
Yüksek Lisans
İngilizce
2006
Siyasal BilimlerSabancı ÜniversitesiUyuşmazlık Analizi ve Çözümü Ana Bilim Dalı
DR. ESRA ÇUHADAR GÜRKAYNAK
- Yaşlı hastalarda kardiyak cerrahisi sonrası erken mobilasyon egzersizleri ile geleneksel fizyoterapinin karşılaştırılması
Comparison of early mobilisation exercises and traditional physiotherapy following cardiac surgery on older patients
AZHAR HASSAN MHMOOD
Yüksek Lisans
İngilizce
2024
Fizyoterapi ve RehabilitasyonKırşehir Ahi Evran ÜniversitesiFizyoterapi ve Rehabilitasyon Ana Bilim Dalı
DR. ÖĞR. ÜYESİ İSMAİL CEYLAN