Low cost, low power structured light based obstacle detection

Abstract

We evaluate the capabilities of an inexpensive obstacle detection system consisting of a CCD or CMOS optical sensor, synchronously pulsed laser and supporting hardware and software. The goal is to expand the range of feasible autonomous vehicle applications to include those that are currently impractical due to limitations on the price, weight, or power requirements of their sensor suites. This system constitutes an active, mechanically passive sensor, relying on the mechanical activity of its host platform to sweep out samples from its surroundings. We evaluate sensor configurations in two example host platform designs. The first is a handheld obstacle detector to aid users with vision impairment, while the second is a short range detector used as part of the sensor ensemble for an autonomous ground vehicle. Tradeoffs for both continuous laser fan and single laser pointer configurations are evaluated. Since the geometric relation between the optical sensor and laser is fixed, we establish effective distance and angle between the laser and sensor given required minimum and maximum ranges, spatial resolution, platform velocity and expected velocities of potential obstacles. In situations with sufficient ambient light, range data from the laser return is used to speed the computation of well known computer vision techniques for object detection to yield estimates of obstacle positions within the environment. Pulsing the laser synchronously with a short shutter time on the camera allows operation of the device as an ANSI Z 136 class 1 device since the laser's active duty cycle is highly compressed. This approach renders visible wavelengths effectively invisible to the naked eye.