Abstract
Intelligent object manipulation for grasping is a challenging problem for robots. Unlike robots, humans almost immediately know how to manipulate objects for grasping due to learning over the years. In this paper, we have developed learning-based pose estimation by decomposing the problem into both position and orientation learning. More specifically, for grasp position estimation, we explore three different methods such as genetic algorithm (GA)-based optimization method to minimize error between calculated image points and predicted end-effector (EE) position, a regression-based method (RM) where collected data points of robot EE and image points have been regressed with a linear model, a pseudoinverse (PI) model which has been formulated in the form of a mapping matrix with robot EE position and image points for several observations. Further for grasp orientation learning, we develop a deep reinforcement learning (DRL) model which we name as grasp deep Q-network (GDQN) and benchmarked our results with Modified VGG16 (MVGG16). Rigorous experimentation shows that due to inherent capability of producing very high-quality solutions for optimization problems and search problems, GA-based predictor performs much better than the other two models for position estimation. For orientation, learning results indicate that off policy learning through GDQN outperforms MVGG16, since GDQN architecture is specially made suitable for the reinforcement learning. Experimentation based on our proposed architectures and algorithms shows that the robot is capable of grasping nearly all rigid body objects having regular shapes.
Similar content being viewed by others
References
Bohg J, Morales A, Asfour T, Kragic D (2014) Data-driven grasp synthesis-a survey. IEEE Trans Robot 30(2):289–309. https://doi.org/10.1109/TRO.2013.2289018
Depierre A, Dellandrea E, Chen L (2018) Jacquard: a largescale dataset for robotic grasp detection. In: Proceedings of the 2018 IEEE/RSJ international conference on Intelligent Robots and Systems (IROS), pp 3511–3516 (2018)
Fu J, Lin Z, Liu M, Leonard N, Feng J, Chua TS (2016) Deep q-networks for accelerating the training of deep neural networks
Goldberg DE (1994) Genetic algorithms in search, optimization and machine learning, 2nd edn. Addison-Wesley, Boston
Huber PJ (2011) Robust statistics. Springer, Berlin, pp 1248–1251
Jiao J, Yuan L, Tang W, Deng Z, Wu Q (2017) A post-rectification approach of depth images of kinect v2 for 3d reconstruction of indoor scenes. ISPRS Int J Geo-Information 6:349. https://doi.org/10.3390/ijgi6110349
Ju Z, Yang C, Ma H (2014) Kinematics modeling and experimental verification of baxter robot. In: Proceedings of the 33rd Chinese control conference, pp. 8518–8523 (2014). https://doi.org/10.1109/ChiCC.2014.6896430
Kalashnikov D, Irpan A, Pastor P, Ibarz J, Herzog A, Quillen D, Holly E, Kalakrishnan M, Vanhoucke V, Levine S (2018) Qt-opt: scalable deep reinforcement learning for vision-based robotic manipulation (2018). arXiv:1806.10293
Konidaris G, Kuindersma S, Grupen R, Barto A (2012) Robot learning from demonstration by constructing skill trees. Int J Robot Res 31(3):360–375. https://doi.org/10.1177/0278364911428653
Kragic D, Christensen HAF (2002) Survey on visual servoing for manipulation. Comput Vis Act Percept Lab Fiskartorpsv 15:2002
Langlois J, Mouchère H, Normand N, Viard-Gaudin C (2018) 3d orientation estimation of industrial parts from 2d images using neural networks. In: ICPRAM
Lenz I, Lee H, Saxena A (2015) Deep learning for detecting robotic grasps. Int J Robot Res 34(4–5):705–724. https://doi.org/10.1177/0278364914549607
Levine S, Pastor P, Krizhevsky A, Ibarz J, Quillen D (2018) Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection. Int J Robot Res 37(4–5):421–436. https://doi.org/10.1177/0278364917710318
Li M, Hang K, Kragic D, Billard A (2016) Dexterous grasping under shape uncertainty. Robot Auton Syst 75:352–364
Lin T, Maire M, Belongie SJ, Bourdev LD, Girshick RB, Hays J, Perona P, Ramanan D, Dollár P, Zitnick CL (2014) Microsoft COCO: common objects in context. CoRR arXiv:1405.0312
Mahler J, Liang J, Niyaz S, Laskey M, Doan R, Liu X, Ojea JA, Goldberg K (2017) Dex-net 2.0: deep learning to plan robust grasps with synthetic point clouds and analytic grasp metrics. CoRR arXiv:1703.09312
Michalewicz Z (1996) Genetic algorithms + data structures = evolution programs, 3rd edn. Springer, Berlin
Mnih V, Kavukcuoglu K, Silver D, Graves A, Antonoglou I, Wierstra D, Riedmiller MA (2013) Playing atari with deep reinforcement learning. CoRR arXiv:1312.5602
Mnih V, Kavukcuoglu K, Silver D, Rusu A, Veness J, Bellemare M, Graves A, Riedmiller M, Fidjeland A, Ostrovski G, Petersen S, Beattie C, Sadik A, Antonoglou I, King H, Kumaran D, Wierstra D, Legg S, Hassabis D (2015) Human-level control through deep reinforcement learning. Nature 518:529–33. https://doi.org/10.1038/nature14236
Nandi GC, Agarwal P, Gupta P, Singh A (2018) Deep learning based intelligent robot grasping strategy. In: 2018 IEEE 14th International conference on control and automation (ICCA), pp. 1064–1069 (2018). https://doi.org/10.1109/ICCA.2018.8444265
Peters J, Lee D, Kober J, Nguyen-Tuong D, Bagnell J, Schaal S (2017) Robot learning, 2nd edn., chap. 15. Springer International Publishing, pp 357–394
Pinto L, Gupta A (2015) Supersizing self-supervision: learning to grasp from 50k tries and 700 robot hours. CoRR arXiv:1509.06825
Redmon J, Farhadi A (2018) Yolov3: An incremental improvement. CoRR arXiv:1804.02767
Ren S, He K, Girshick RB, Sun J (2015) Faster R-CNN: towards real-time object detection with region proposal networks. CoRR arXiv:1506.01497
Ritter H, Haschke R (2015) Hands, dexterity, and the brain. In: PhD Cheng G (ed) Humanoid robotics and neuroscience: science, engineering and society, 3. CRC Press, Boca Raton
Sahbani A, El-Khoury S, Bidaud P (2012) An overview of 3d object grasp synthesis algorithms. Robot Auton Syst 60(3):326–336
Saxena A, Driemeyer J, Ng AY (2009) Learning 3-d object orientation from images. In: 2009 IEEE International conference on robotics and automation, pp. 794–800 (2009). https://doi.org/10.1109/ROBOT.2009.5152855
Shukla P, Nandi GC (2019) Robotized grasp: grasp manipulation using evolutionary computing. In: Proceedings of 2019 international conference on electrical, electronics and computer engineering (UPCON) (2019). DOI 978-1-7281-3455-0/19/\$31.002019IEEE
Tremblay J, To T, Sundaralingam B, Xiang Y, Fox D, Birchfield S (2018) Deep object pose estimation for semantic robotic grasping of household objects. CoRR arXiv:1809.10790
Viereck U, ten Pas A, Saenko K, Jr, RP (2017) Learning a visuomotor controller for real world robotic grasping using easily simulated depth images. CoRR arXiv:1706.04652
Zhu H, Gupta A, Rajeswaran A, Levine S, Kumar V (2018) Dexterous manipulation with deep reinforcement learning: efficient, general, and low-cost. CoRR arXiv:1810.06045
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Hitesh Kumar—Summer Intern at Indian Institute of Information Technology Allahabad.
Rights and permissions
About this article
Cite this article
Shukla, P., Kumar, H. & Nandi, G.C. Robotic grasp manipulation using evolutionary computing and deep reinforcement learning. Intel Serv Robotics 14, 61–77 (2021). https://doi.org/10.1007/s11370-020-00342-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11370-020-00342-7