Obstacle detection, and more generally, terrain classification are two of the most important and fundamental perception functions required for robust unmanned off-road vehicle operation. To better address these tasks, we have developed a novel method that uses multiple readings from multiple sensor modalities to compute a vector measure of the physical density of a particular world location as it appears to each sensor modality. This “density map” representation serves as a powerful discriminator for the terrain classification task.
We have developed this concept into a system to characterize terrain in real time from a set of sensors on-board an autonomous vehicle by assigning each patch of terrain a type and by estimating a cost metric for the vehicle to traverse that terrain. The system is fast enough to produce these estimates in real time; on our testbed vehicle, our terrain classification system is updated at roughly 70 Hz by a variety of different ladar and radar sensors. This paper discusses our methods for modeling each sensor modality, establishing the classification system, and compensating for the fact that the sensor readings may be unsynchronized and taken from a moving vehicle.
A number of experiments are presented using both a stationary platform and using the autonomous Raptor vehicle developed by SAIC for the PerceptOR program. Results indicate that this system can be used to correctly classify clear flat ground, sparse vegetation, and impenetrable vegetation, and is practical for use as a guidance system for a completely autonomous vehicle. Additionally, we have demonstrated a limited ability to use this system for more sophisticated terrain classification, such as the ability to identify metal wire fencing.
The military has an anticipated need for a remotely controlled ground system to perform reconnaissance; surveillance; target acquisition; patrolling; and nuclear, biological, and chemical (NBC) detection. In particular, the U.S. Army Infantry School would like the system to operate in the most dangerous areas of the modeM battlefield—open terrain that is highly trafficable. This has led to the premise that the system should be fast. Also, discovering the enemy's location is often dangerous with the cost assessed in human lives. From these requirements emerged the Unmanned Ground Vehicle (UGV) programs. Emphasis is on effective robotic technology that has multiservice applications and is unique to unmanned vehicles on the gr1 The maturity of these robotic technologies was started to be confirmed in (1) UGV Demo I, held in 1992; and will continue to be confirmed in (2) UGV Demo II, scheduled in 1996. UGV Demo I focused primarily on teleoperation, while the UGV Demo II is designed to complement the first demonstration by focusing on supervised autonomy. The primary goal of the UGV Demo II program is to demonstrate the utility of advanced UGV systems to conduct tasks that enhance the Department of Defense force structure. This demonstration will combine both offensive and defensive operations in a militarily relevant situation. For offensive operation, four cooperating UGVs will initiate a movement-tocontact scenario. The vehicles will conduct a screening operation for a manned force using bounding overwatch over semiarid terrain. Once in overwatch positions, they will use a reconnaissance, surveillance, and target acquisition (RSTA) mission module to observe threats; and to locate, detect, assess, and designate threats for indirect fire. For defensive operation, the vehicles will conduct a retrograde scenario. Four cooperating UGVs will screen a manned force by sequentially occupying preplanned defensive positions to maximize damage to advancing enemy forces. Once the commander determines that enemy forces have been weakened, the vehicles will move to preplanned locations in the main battle area to help designate remnants of advancing enemy forces.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.