Abstract: A method and system for assisting with guiding a vehicle over terrain is provided. The method includes training at least one first classifier technique using a first set of terrain classifier training data, such that the at least one first classifier technique is trained to output at least one probability value usable to classify terrain. The first trained classifier technique is then used to generate a second set of terrain classifier training data. A second classifier technique is trained using the output of the at least one first classifier technique, and additional data to output a probability value useable to classify terrain.

Abstract: A Light Detection and Ranging (LIDAR) apparatus and method are disclosed having a rotatable light source enabled to emit a light ray, the light ray being emitted at a plurality of angular intervals; a reflection device, which can be parabolic in shape, and an analysis device for calculating a position at which one or more features are present based on the angle that the light ray was emitted and the time delay associated with the received reflected light, from a feature, wherein the analysis device takes into account the reflection of the light ray from the reflection device. In this manner, light rays may be reflected from heading in one direction to improve the resolution of the LIDAR in a second direction. Furthermore, where a parabolic reflector is used, positions of features can be calculated directly in a Cartesian coordinate system. Autonomous vehicles can use a LIDAR such as described herein to improve forward looking resolution in collision avoidance systems or terrain selection systems.

Abstract: A method and system for assisting with guiding a vehicle over terrain is provided. The method includes training at least one first classifier technique using a first set of terrain classifier training data, such that the at least one first classifier technique is trained to output at least one probability value usable to classify terrain. The first trained classifier technique is then used to generate a second set of terrain classifier training data. A second classifier technique is trained using the output of the at least one first classifier technique, and additional data to output a probability value useable to classify terrain.

Abstract: A Light Detection and Ranging (LIDAR) apparatus and method are disclosed having a rotatable light source enabled to emit a light ray, the light ray being emitted at a plurality of angular intervals; a reflection device, which can be parabolic in shape, and an analysis device for calculating a position at which one or more features are present based on the angle that the light ray was emitted and the time delay associated with the received reflected light, from a feature, wherein the analysis device takes into account the reflection of the light ray from the reflection device. In this manner, light rays may be reflected from heading in one direction to improve the resolution of the LIDAR in a second direction. Furthermore, where a parabolic reflector is used, positions of features can be calculated directly in a Cartesian coordinate system. Autonomous vehicles can use a LIDAR such as described herein to improve forward looking resolution in collision avoidance systems or terrain selection systems.