Abstract
This paper implements a novel line-following system for humanoid robots. Camera embedded on the robot’s head captures the image and then extracts the line using a high-speed and high-accuracy rectangular search method. This method divides the search location into three sides of rectangle and performs image convolution by edge detection matrix. The extracted line is used to calculate relative parameters, including forward velocity, lateral velocity and angular velocity that drive line-following walking. A proposed path curvature estimation method generates the forward velocity and guidance reference point of the robot. A classical PID controller and a PID controller with angle compensation are then used to set the lateral velocity and angular velocity of the robot, improving the performance in tracking a curved line. Line-following experiments for various shapes were conducted using humanoid robot NAO. Experimental results demonstrate the robot can follow different line shapes with the tracking error remaining at a low level. This is a significant improvement from existing biped robot visual navigation systems.
Similar content being viewed by others
References
Aldana-Murillo NG, Hayet JB, Becerra HM (2015) Evaluation of local descriptors for vision-based localization of humanoid robots. In: Mexican conference on pattern recognition. Springer International Publishing, pp 179–189
Alexiadis DS, Zarpalas D (2013) Real-time, full 3-D reconstruction of moving foreground objects from multiple consumer depth cameras. IEEE Trans Multimed 15:339–358
Antonelli G, Chiaverini S, Fusco G (2007) A fuzzy-logic based approach for mobile robot path tracking. IEEE Trans Fuzzy Syst 15(2):211–221
Ariffin IM et al. (2015) Vision tracking application for mobile navigation using Humanoid robot Nao. In: International symposium on micro-nanomechatronics and human science IEEE, pp 1–7
Armesto L, Tornero J (2009) Automation of industrial vehicles: a visionbased line tracking application. In: Proceedings of IEEE conference on emerging technologies & factory automation, pp 1–7
Balaji V, Balaji M, Chandrasekaran M et al. (2015) Optimization of PID control for high speed line tracking robots. In: IEEE international symposium on robotics and intelligent sensors. IEEE, pp 147–154
Bernabe A, De San Dios MD, Ollero A (2017) Efficient integration of RSSI for tracking using wireless camera networks. Inf Fusion 36:296–312
Brandão AS, Martins FN, Soneguetti HB (2015) A vision-based line following strategy for an autonomous UAV. In: International conference on informatics in control, automation and robotics IEEE, pp 314–319
Tessier C et al (2010) Map aided localization and vehicle guidance using an active landmark search. Inf Fusion 11(3):283–296
Delfin JH, Becerra M, Arechavaleta G (2014) Visual path following using a sequence of target images and smooth robot velocities for humanoid navigation. In: IEEE-RAS international conference on humanoid robots IEEE, pp 354–359
Delgado-Galvan J et al. (2015) Vision-based humanoid robot navigation in a featureless environment. In: Mexican Conference on pattern recognition. Springer, Cham, pp 169–178
Du X, Tan KK, Htet KKK (2015) Vision-based lane line detection for autonomous vehicle navigation and guidance. In: Control conference IEEE, pp 1–5
Faragasso A et al. (2016) Vision-based corridor navigation for humanoid robots. In: IEEE international conference on robotics and automation. IEEE, pp 3190–3195
George L, Mazel A (2013) Humanoid robot indoor navigation based on 2D bar codes: application to the NAO robot. In: IEEE-RAS international conference on humanoid robots IEEE, pp 329–335
Głowicki M, Butkiewicz BS (2013) Autonomous line-follower with fuzzy control. In: Signal processing symposium IEEE, pp 1–6
Hornung A, Bennewitz M, Strasdat H (2010) Efficient vision-based navigation. Auton Robots 29(2):137–149
Bazylev D, Popchenko F, Ibraev D, et al. (2017) Humanoid robot walking on track using computer vision. In: Control and automation, IEEE, pp 1310–1315
Ismail AH et al. (2009) Vision-based system for line following mobile robot. In: IEEE symposium on industrial electronics & applications. ISIEA 2009, pp 642–645
Lobos-Tsunekawa K, Leiva F, Ruiz-Del-Solar J (2018) Visual navigation for biped humanoid robots using deep reinforcement learning. IEEE Robot Autom Lett 3:3247–3254
Luo B et al. (2015) Research on mobile robot path tracking based on color vision. In: Chinese automation congress IEEE, pp 371–375
Martinez S, Cortes J, Bullo F (2007) Motion coordination with distributed information. IEEE Control Syst 27(4):75–88
Morrison JG, Gavez-Lopez D, Sibley G (2016) Scalable multirobot localization and mapping with relative maps: introducing MOARSLAM. IEEE Control Syst 36(2):75–85
Ng KH, Che FY, Su ELM et al (2012) Adaptive Phototransistor Sensor for Line Finding. Procedia Engineering 41(41):237–243
Okarma K, Lech P (2010) A fast image analysis technique for the line tracking robots. In: Artifical intelligence and soft computing. Springer Berlin Heidelberg, pp 329–336
Oriolo G, Ulivi G, Vendittelli M (1995) On-line map building and navigation for autonomous mobile. In: Proceedings - IEEE international conference on robotics and automation, vol 3. pp 2900–2906
Oriolo G et al. (2013) Vision-based trajectory control for humanoid navigation. In: IEEE-RAS international conference on humanoid robots IEEE, pp 118–123
Pakdaman M, Mehdi M (2009) Design and implementation of line follower robot. In: Second international conference on computer and electrical engineering, pp 585–590
Rahman M, Rahman MHR, Haque AL, Islam MT (2005) Architecture of the vision system of a line following mobile robot operating is static environment. In: 9th IEEE international multitopic conference, pp 1–8
Reyes LAV, Tanner HG (2015) Flocking, formation control, and path following for a group of mobile robots. IEEE Trans Control Syst Technol 23(4):1268–1282
Roy A, Noel MM (2016) Design of a high-speed line following robot that smoothly follows tight curves. Comput Electr Eng 56:732–747
Saitoh T, Tada N, Konishi R (2009) Indoor mobile robot navigation by center following based on monocular vision. In: Computer Vision, In-the Publishers, pp 352–366
Shiao YS, Yang JL, Su DT (2013) Path tracking laws and implementation of a vision-based wheeled mobile robot. Proc Inst Mech Eng Part I J Syst Control Eng 223(6):847–862
Thuy PX, Cuong NT (2016) Vision Based autonomous path/line following of a mobile robot using a hybrid fuzzy pid controller. In: Hnkh Toàn Quốc Lần Thứ 3 Về Điều Khiển & Tự Động Ho
Wu JJ et al (2014) A real-time method for motion blur detection in visual navigation with a humanoid robot. Acta Autom Sin 40(2):267–276
Xiafu L, Yong C (2009) A design of autonomous tracing in Intelligent vehicle based on infrared photoelectric sensor. In: International conference on information engineering & computer science, pp 1–4
NAO-technical overview http://doc.aldebaran.com/2-1/family/robots/dimensions_robot.html. Accessed 5 May 2014
Yan Lu, Song D (2017) Visual navigation using heterogeneous landmarks and unsupervised geometric constraints. IEEE Trans Robot 31(3):736–749
Yussof H et al (2015) Sensor based mobile navigation using humanoid robot Nao. Procedia Comput Sci 76:474–479
Zhang J, Wang N, Wang S (2004) A developed method of tuning PID controllers with fuzzy rules for integrating processes. In: Proceedings of the IEEE American control conference 2004, pp 1109–1114
Zhang L, Zhuan X, Gao X (2010) Design and implementation of a Vision based 4-wheeled line track robot. In: 2010 WASE international conference on information engineering, pp 3–6
Acknowledgement
The authors deeply acknowledge the financial support from Xiamen University of Technology, Fujian, P.R. China under the Xiamen University of Technology Scientific Research Foundation for Talents plan.
Author information
Authors and Affiliations
Contributions
The contributions of this paper are: (1) a line-following method that uses the Gaussian filter and a simple convolution kernel to extract line information and improves the processing speed by using rectangle search; (2) A curvature approximation method to generate forward velocity; and (3) a PID controller with angle compensation to adapt to different curves. When applied collectively, the humanoid robot NAO’s navigation performance was comparatively robust and accurate.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Rights and permissions
About this article
Cite this article
Juang, LH., Zhang, JS. Robust visual line-following navigation system for humanoid robots. Artif Intell Rev 53, 653–670 (2020). https://doi.org/10.1007/s10462-018-9672-9
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10462-018-9672-9