General Object Tip Detection and Pose Estimation for Robot Manipulation
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.
KeywordsPose estimation Tool tip detection Peg-in-hole insertion
The research leading to these results has received funding from the European Communitys Seventh Framework Programme FP7/2007-2013 (Specific Programme Cooperation, Theme 3, Information and Communication Technologies) under grant agreement no. 610878, 3rd HAND.
- 3.Dantam, N.T., Amor, H.B., Christensen, H.I., Stilman, M.: Online multi-camera registration for bimanual workspace trajectories. In: 14th IEEE-RAS International Conference on Humanoid Robots (Humanoids), pp. 588–593. IEEE (2014)Google Scholar
- 7.Huang, S., Yamakawa, Y., Senoo, T., Ishikawa, M.: Dynamic compensation by fusing a high-speed actuator and high-speed visual feedback with its application to fast peg-and-hole alignment. Adv. Rob. 28(9), 613–624 (2014)Google Scholar
- 8.Liu, S., Xie, W.F., Su, C.Y.: Image-based visual servoing using improved image moments. In: International Conference on Information and Automation, 2009, ICIA 2009, pp. 577–582. IEEE (2009)Google Scholar
- 9.Song, H.C., Kim, Y.L., Song, J.B.: Automated guidance of peg-in-hole assembly tasks for complex-shaped parts. In: 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2014), pp. 4517–4522. IEEE (2014)Google Scholar
- 10.Stückler, J., Behnke, S.: Adaptive tool-use strategies for anthropomorphic service robots. In: 14th IEEE-RAS International Conference on Humanoid Robots. IEEE (2014)Google Scholar
- 11.Teney, D., Piater, J.: Continuous pose estimation in 2D images at instance and category levels. In: Tenth Conference on Computer and Robot Vision, pp. 121–127. IEEE, May 2013. https://iis.uibk.ac.at/public/papers/Teney-2013-CRV.pdf
- 12.Teney, D., Piater, J.: Multiview feature distributions for object detection and continuous pose estimation. Comput. Vis. Image Underst. 125, 265–282 (2014). https://iis.uibk.ac.at/public/papers/Teney-2014-CVIU.pdf CrossRefGoogle Scholar
- 13.Toussaint, M.: Newton methods for k-order markov constrained motion problems. CoRR abs/1407.0414 (2014). http://arxiv.org/abs/1407.0414