Intelligent Off-Road Vehicles



Publications   Links   Videos   Pictures

Back to the IFOR homepage

 Autonomous Navigation for Forest Machines



The project "Autonomous Navigation for Forest Machines" is part of a long-term vision in forestry, of developing an unmanned vehicle that transports timber from the area of felling to the main roads for further transportation.

The main goal of the project is to present a working solution for autonomous path tracking navigation, to be implemented in a vehicle for operation in forest terrains. The Autonomous Ground Vehicle (AGV) should operate in two modes: Path Learning, and Path Tracking.
In the Path Learning mode, a human driver drives along the chosen path, learning the machine how to drive the path.
In the Path Tracking mode, the computer assumes control over propulsion and steering. The vehicle then automatically travels along the learnt path.
The operation has to account for unplanned deviations from the path, caused by imperfect sensing of position, and also by the vehicle sliding and jumping along the path. Another important part involves detection of new obstacles appearing on the path. In some cases the system should stop the vehicle and alert the human operator, who should be given the option of manually correcting the vehicle position, or giving the system the green light to go ahead along the original path.
The software and hardware is installed in a standard forest machine, selected and prepared in collaboration with the manufacturer. A video showing a test with this forest machine driving autonomously is avalible in flash format.

A first version of the system was installed and demonstrated on a smaller-sized robot, specifically purchased for this project. This robot was important for speeding up and simplifying the development process.

Click here to watch a short (12.5Mb) video demonstrating the obstacle avoidance function combined with a novel path tracking algorithm "Follow the Past"

Construction of Autonomous Ground Vehicles has been an intense research area for the last decade. A number of successful applications in agriculture and the mining industry, mostly not commercial, have been demonstrated. It is reasonable to believe that similar solutions are relevant for a forest-based AGV. However, the forest environments have enough peculiarities to make the proposed development project highly advanced, and full of challenging tasks for research. The research work deals with obstacle detection problems, where radar sensors are utilized to detect objects close to the vehicle. Another area of research is Path Tracking and control algorithms that take into account the specific problems involved in controlling a huge forest machine in a forest environment. The suggested hardware solution will involve two computers connected by a high-speed radio-based network. One computer onboard the vehicle is used for low-level control and sensor interfacing, while the other, remote computer contains all the high-level parts of the system. This arrangement simplifies and speeds up the development work significantly. The software solution involves a behavior-based architecture. The vehicle's tasks are defined as behaviors, such as Stay on path and Avoid obstacles. Each of these behaviors is specified separately and works essentially reflexively, i.e. the action is a direct function of the current sensor input.

Current status: We currently have a forest machine equipped with several sensors able to accurately follow a previously demonstrated path with the Follow the Past method. It is able to avoid obstacles using VFH+, but we are currently working on a path planning algorithm to enhance the performance. A middleware called Nav2000 has been developed as a link between the hardware and higher level functions. We have also developed a method using a combination of high precision DGPS and wheel odometry to detect and measure slip in a forest environment.

In December 2008 the performance of the path-tracking algorithm Follow the Past was evaluated in a real forest environment. The average tracking error was found to be less than 6cm. A video from the test is avalible in flash format.

Current members:

Project leader:
Thomas Hellström

Ola Ringdahl
Former members:
Thomas Johansson
Kalle Prorok
Fredrik Georgsson

Urban Sandström


Kempe Foundation
Umeå university
Komatsu Forest AB
BAE Systems Hägglunds AB
Carl Tryggers Stiftelse

Back to the IFOR homepage

Intelligent Off-Road Vehicles
Umeå University, Umeå Sweden
Content last updated on August 23 2013