General Object Tip Detection and Pose Estimation for Robot Manipulation

Creative Commons License

Shukla D., ERKENT Ö., Piater J.

10th International Conference on Computer Vision Systems (ICVS), Copenhagen, Danimarka, 6 - 09 Temmuz 2015, cilt.9163, ss.364-374, (Tam Metin Bildiri)

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Cilt numarası: 9163
  • Doi Numarası: 10.1007/978-3-319-20904-3_33
  • Basıldığı Şehir: Copenhagen
  • Basıldığı Ülke: Danimarka
  • Sayfa Sayıları: ss.364-374
  • Anahtar Kelimeler: Pose estimation, Tool tip detection, Peg-in-hole insertion, IMAGE MOMENTS
  • Açık Arşiv Koleksiyonu: AVESİS Açık Erişim Koleksiyonu
  • Hacettepe Üniversitesi Adresli: Hayır

Özet

Robot manipulation tasks like inserting screws and pegs into a hole or automatic screwing require precise tip pose estimation. We propose a novel method to detect and estimate the tip of elongated objects. We demonstrate that our method can estimate tip pose to millimeter-level accuracy. We adopt a probabilistic, appearance-based object detection framework to detect pegs and bits for electric screw drivers. Screws are difficult to detect with feature-or appearance-based methods due to their reflective characteristics. To overcome this we propose a novel adaptation of RANSAC with a parallel-line model. Subsequently, we employ image moments to detect the tip and its pose. We show that the proposed method allows a robot to perform object insertion with only two pairs of orthogonal views, without visual servoing.