Route Planning for Agricultural Robots


In this project, we designed a route planner to guide agricultural robots to farm fields. This algorithm was integrated with a google map application for ease of use.


Coverage planning for convex fields is the problem of finding the optimal moving direction. However, for complex non-convex fields, the back and forth motion is interrupted by obstacles / field boundaries. Exisiting approaches split the field into sub-fields and progress from covering one subfield to another, moving in the same direction. However, this is not particularly efficient for larger fields. In addition, there is a constraint that the robot must adhere to headlands ( no arable lands at the edges )while moving between sub-fields.
In this work, we formulate the NP-hard problem of splitting the area into subfields and solve it in a greedy manner. We iterate over turning directions to find the largest subfield, which is then separated out and the process continued. The final set of subfields are guaranteed to be covered more optimally than the single direction approach. The subfields are then joined to form an adjacency graph and then the optimal route is planned.


The route planner is a part of the Software Architecture For Agricultural Robots (SAFAR). SAFARis a joint project of UniBots and MobotSoft, an academic initiative to build a Software Architecture For Agricultural Robots. UniBots, a university spin-off company based in UK, was set by Simon Blackmore to commercialise recent developments in behavioural control for outdoor mobile robots. UniBots provides a conduit from existing university designs and prototypes around the world into the market. The purpose of the SAFAR project is to develop a set of designs, tools and resources to promote the development of agricultural robots. MobotSoft is in charge of the software development using Microsoft Robotics Developer Studio as the underlying platform.

Here is webpage where an user can test out the route planner.


Here is project webpage for SAFAR.