We have been developing Autonomous Ground Vehicles that are able to be used for driverless navigation, mapping, scene understanding and manipulation of loads and objects.
This can be done in industrial, urban or natural environments. This area of research focuses on the combination of localization and mapping methods, motion planning, obstacle detection, obstacle avoidance and situation awareness. The algorithms on the vehicle (a John Deere Gator) then translate all these aspects into operational and useful platforms.
Our Group has also recently adapted and enhanced the Zebedee 3D Mapping technology for autonomous vehicle navigation, fully closing the loop and incorporating aspects of control, obstacle avoidance, localisation and mapping into a single platform, the Gator.
Once the Gator maps its operation environment is complete, it can start to navigate and plan pathways. The user specifies the route by selecting multiple way points.
To detect moving or static object the gator uses stereo-vision obstacle detection, once it has detected an object the Gator will come to a stop, and re-plan a new pathway.
Below are examples of our work.
For more information contact Dr. Paulo Borges on paulo.borges [at] csiro.au