Skip to main content

ASI improves algorithm to detect drop-offs and other large negative obstacles

Published by , Editorial Assistant
Global Mining Review,

Autonomous Solutions, Inc. (ASI) has improved an algorithm for autonomous vehicles to detect drop-offs and other large negative obstacles often found in the environments in which automated off-road vehicles operate.

“ASI has developed a method for mapping point cloud occlusions in real-time,” said Taylor Bybee, Perception Tech Lead at ASI. “Which provides additional accuracy and safety when integrated into an autonomous vehicle obstacle detection and avoidance system.”

For safe navigation through an environment, autonomous ground vehicles rely on sensor data representing 3D space surrounding the vehicle. Often this data is obscured by objects or terrain, producing gaps in the sensor field of view. These gaps, or occlusions, can indicate the presence of obstacles, negative obstacles, or rough terrain.

Occlusions can be defined as a blockage which prevents a sensor from gathering data in a location. For example, occlusions can be seen as shadows in LiDAR data.

Because sensors receive no data in these occlusions, sensor data provides no explicit information about what might be found in the occluded areas. Information about the occlusions must be inferred from using an occlusion mapping algorithm to provide the navigation system with a more complete model of the environment.

“While sensor data itself doesn’t tell us what’s in the occluded areas, occlusions can represent negative obstacles like drop-offs or areas behind large obstacles,” said Jeff Ferrin, CTO at ASI. “It’s important to identify these areas for obstacle detection and avoidance to work properly.”

Application of this new technology can be useful in settings with dump edges at mine sites, steep road edges, canals, ditches, hills or stairs for indoor or urban environments.

The occlusion mapping algorithm has three main components. The first is a sensor field of view (FOV) model that describes what obstacles the sensors are expected to detect. This component is designed for point cloud sensors such as 3D LiDAR, Flash LiDAR, Structured Light, and Stereo Cameras.

Second, an occlusion map is maintained and updated using the sensor FOV model and current sensor data to provide a probabilistic estimate on areas that have not been detected within the sensor FOV.

The third component is the integration of the occlusion map into an autonomous vehicle navigation system. It is designed to work with and complement existing obstacle detection and avoidance systems.

Read the article online at:

You might also like


Embed article link: (copy the HTML code below):


This article has been tagged under the following:

Mining equipment news Mining truck news