Localization Based on Natural Features Detector for Steep Slope Vineyards

Placing ground robots to work in steep slope vineyards is a complex challenge. The Global Positioning System (GPS) signal is not always available and accurate. A reliable localization approach to detect natural features for this environment is required. This paper presents an improved version of a visual detector for Vineyards Trunks and Masts (ViTruDe) and, a robot able to cope pruning actions in steep slope vineyards (AgRob V16). In addition, it presents an augmented data-set for other localization and mapping algorithm benchmarks. ViTruDe accuracy is higher than 95% under our experiments. Under a simulated runtime test, the accuracy lies between 27% - 96% depending on ViTrude parametrization. This approach can feed a localization system to solve a GPS signal absence. The ViTruDe detector also considers economic constraints and allows to develop cost-effective robots. The augmented training and datasets are publicly available for future research work.

[1]  Ricardo Carelli,et al.  Optimized EIF-SLAM algorithm for precision agriculture mapping based on stems detection , 2011 .

[2]  Yael Edan,et al.  Harvesting Robots for High‐value Crops: State‐of‐the‐art Review and Challenges Ahead , 2014, J. Field Robotics.

[3]  António Paulo Moreira,et al.  Towards a Reliable Robot for Steep Slope Vineyards Monitoring , 2016, J. Intell. Robotic Syst..

[4]  Mohammad Valipour,et al.  How do different factors impact agricultural water management? , 2016 .

[5]  Ricardo Carelli,et al.  Agricultural Robotics: Unmanned Robotic Service Units in Agricultural Tasks , 2013, IEEE Industrial Electronics Magazine.

[6]  Filipe Neves dos Santos,et al.  Automatic Eye Localization; Multi-block LBP vs. Pyramidal LBP Three-Levels Image Decomposition for Eye Visual Appearance Description , 2015, IbPRIA.

[7]  Mohammad Valipour,et al.  VARIATIONS OF LAND USE AND IRRIGATION FOR NEXT DECADES UNDER DIFFERENT SCENARIOS , 2016, IRRIGA.

[8]  Sebastian Thrun,et al.  FastSLAM: a factored solution to the simultaneous localization and mapping problem , 2002, AAAI/IAAI.

[9]  Hugh Durrant-Whyte,et al.  Simultaneous localization and mapping (SLAM): part II , 2006 .

[10]  Raul Morais,et al.  Vine Trunk Detector for a Reliable Robot Localization System , 2016, 2016 International Conference on Autonomous Robot Systems and Competitions (ICARSC).

[11]  Gianfranco Visentin,et al.  Towards orbital based global rover localization , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[12]  Wang Li,et al.  Evolution of Water Lifting Devices (Pumps) over the Centuries Worldwide , 2015 .

[13]  Antonios Gasteratos,et al.  Semantic mapping for mobile robotics tasks: A survey , 2015, Robotics Auton. Syst..

[14]  Stefan Kohlbrecher,et al.  A flexible and scalable SLAM system with full 3D motion estimation , 2011, 2011 IEEE International Symposium on Safety, Security, and Rescue Robotics.

[15]  Flavio Fontana,et al.  Autonomous, Vision‐based Flight and Live Dense 3D Mapping with a Quadrotor Micro Aerial Vehicle , 2016, J. Field Robotics.

[16]  António Paulo Gomes Mendes Moreira,et al.  Towards a Reliable Monitoring Robot for Mountain Vineyards , 2015, 2015 IEEE International Conference on Autonomous Robot Systems and Competitions.

[17]  Sebastian Thrun,et al.  Probabilistic robotics , 2002, CACM.

[18]  Armando Sousa,et al.  Agricultural Wireless Sensor Mapping for Robot Localization , 2015, ROBOT.

[19]  Z. Kurt-Yavuz,et al.  A comparison of EKF, UKF, FastSLAM2.0, and UKF-based FastSLAM algorithms , 2012, 2012 IEEE 16th International Conference on Intelligent Engineering Systems (INES).