An Autonomous Crop Treatment Robot: Part II. Real Time Implementation

Abstract

Implementation of an autonomous vehicle for precision treatment of crop plants is described. The navigation system integrates the vision system described in Part I with inertial and odometric sensing. A modular approach is adopted, where the crop grid observation model is re-formulated as a non-linear compression filter, which combines a set of observations of crop plants into a single pseudo-observation of the position of the crop planting grid relative to the vehicle position. The compression filter encapsulates all internal detail of the vision system (camera calibration, crop layout, etc.). The output from this vision module can be used as an observation in the conventional way by the vehicle's navigation Kalman filter.

Plant features classified into crop and weed by the vision module are registered into a treatment map. The need to treat targets from a moving platform requires time delays in the processing of observations to be considered. A method of compensation is introduced which allows time delayed vision observations to be used; the effectiveness of the technique is illustrated by an example with an artificially extended time delay.

In field trials of the vehicle have been performed, and the accuracy of both vehicle navigation and crop treatment are reported. We conclude that the navigation accuracy falls within the 20 mm root mean square error region thought appropriate for precise horticultural operations, and that spray application is sufficiently accurate for the treatment of individual crop plants.

Keywords

Kalman filter navigation sensor fusion agriculture

Get full access to this article

View all access options for this article.

References

Bak, M. , Larsen, T.D. , Nørgaard, M. , Andersen, N.A. , Poulsen, N.K. , and Ravn, O. 1998. Location estimation using delayed measurements. IEEE 5th Int. Workshop on Advanced Motion Control, Coimbra, Portugal.

Bar-Shalom, Y. , and Fortmann, T. 1988. Tracking and Data Association. New York: Academic Press.

Barshan, B. , and Durrant-Whyte, H.F. 1993. An inertial navigation system for a mobile robot. IROS 2243-2248.

Durrant-Whyte, H.F. 1996. An autonomous guided vehicle for cargo handling applications . International Journal of Robotics Research 15(5):407-440.

Durrant-Whyte, H.F. , Rao, B.S.Y. , and Hu, H. 1990. Toward a fully decentralized architecture for multi-sensor data fusion. ICRA 584-589, Cincinatti.

Hague, T. , and Tillett, N.D. 1996. Navigation and control of an autonomous horticultural robot. Mechatronics 6(2):165- 180.

Hashemipour, H.R. , Roy, S. , and Laub, A.J. 1988. Decentralized structures for parallel Kalman filtering. Transactions on Automatic Control 33(1), IEEE.

Kalman, R.E. 1960. A new approach to linear filtering and prediction problems . J. of Basic Eng., Trans. ASME Series D, 82:35-45.

Lindgren, D. , Probert, P. , Hague, T. , and Marchant, J.A. 2000. Relating torque and slip experienced by the wheels of an agricultural autonomous guided vehicle. 3rd EUREL Workshop, European advanced robotics systems development, pp. 12-14, Salford, U.K.

10.

McLellan, J.F. , and Friesen, L. 1996. Who needs a 20cm precision farming system? Position Location and Navigation Symposium 426-432, IEEE.

11.

Southall, J.B. 1999. The Development and Evaluation of Computer Vision Algorithms for the Control of an Autonomous Horticultural Vehicle, PhD thesis, Dept. of Comp. Sci., University of London.

12.

Southall, B. , Hague, T. , Marchant, J.A. , and Buxton, B.F. 2001. An autonomous crop treatment robot: Part I: A model for visual data interpretation. International Journal of Robotics Research 21(1):3-16.

13.

Southall, B. , Marchant, J.A. , Hague, T. , and Buxton, B.F. 1998. Model based tracking for navigation and segmentation. 5th European Conference on Computer Vision, Lecture notes in computer science , eds., H. Burkhardt and B. Neumann , 1406:797-811, Freiburg .

14.

Willner, D. , Chang, C.B. , and Dunn, K.P. 1976. Kalman filter algorithms for a multi-sensor system. In Proc. IEEE Int. Conf. Decision and Control 570-574.

15.

Xu, H. , van Brussel, H. , de Schutter, J. , and Vandorpe, J. 1995. Sensor fusion and positioning of the mobile robot LiAS. Intelligent Autonomous Systems, ed., U. Rembold et al., IOS Press.