Binocular vision perception and obstacle avoidance of visual simulation system for power lines inspection with UAV

Automatic perception and obstacle avoidance in three-dimensional(3D) complex environment is one of the most challenging task for UAV-based power lines inspection. In this paper, binocular vision perception and obstacle avoidance of visual simulation system for power lines inspection with UAV is proposed. First, the realistic power lines inspection scene is established by Vega Prime simulation platform. Then, the power towers and obstacles are perceived based on binocular stereo vision technology. Last, a smooth and safe path will be planned based on interfered fluid dynamical system(IFDS) and the real-time local optimal path can be planned by combining IFDS method and rolling optimization strategy. The simulation results indicate this system has real-time performance and high fidelity.

[1]  Mandyam V. Srinivasan,et al.  A stereo vision system for UAV guidance , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[2]  Aude Billard,et al.  A dynamical system approach to realtime obstacle avoidance , 2012, Autonomous Robots.

[3]  Jae-Hun Kim,et al.  Vision-based automatic real time inspection of power transmission line , 2013, IEEE ISR 2013.

[4]  J. Katrasnik,et al.  A Survey of Mobile Robots for Distribution Power Line Inspection , 2010, IEEE Transactions on Power Delivery.

[5]  Y. Volkan Pehlivanoglu,et al.  A new vibrational genetic algorithm enhanced with a Voronoi diagram for path planning of autonomous UAV , 2012 .

[6]  Dawei Li,et al.  Three-dimensional path planning for unmanned aerial vehicles based on fluid flow , 2014, 2014 IEEE Aerospace Conference.

[7]  Roger Appleby,et al.  Evaluation of a passive millimeter-wave (PMMW) imager for wire detection in degraded visual conditions , 2009, Defense + Commercial Sensing.

[8]  Ming-Ting Sun,et al.  An Algorithm for Power Line Detection and Warning Based on a Millimeter-Wave Radar Video , 2011, IEEE Transactions on Image Processing.

[9]  Julien Beaudry,et al.  On the application of VTOL UAVs to the inspection of power utility assets , 2010, 2010 1st International Conference on Applied Robotics for the Power Industry.

[10]  Honglun Wang,et al.  UAV feasible path planning based on disturbed fluid and trajectory propagation , 2015 .

[11]  Qian Wang,et al.  High Speed Automatic Power Line Detection and Tracking for a UAV-Based Inspection , 2012, 2012 International Conference on Industrial Control and Electronics Engineering.

[12]  Vincent Roberge,et al.  Comparison of Parallel Genetic Algorithm and Particle Swarm Optimization for Real-Time UAV Path Planning , 2013, IEEE Transactions on Industrial Informatics.

[13]  Ebrahim Mattar,et al.  D* Lite Based Real-Time Multi-Agent Path Planning in Dynamic Environments , 2011, 2011 Third International Conference on Computational Intelligence, Modelling & Simulation.