How to Choose a 3D Vision Technology
Designers of autonomous vehicles, robots, and many other systems are faced with a critical challenge: Which 3D perception technology to use? There are a wide variety of sensors on the market, employing modalities including passive stereo, active stereo, time of flight, 2D and 3D lasers, and monocular approaches. This talk will provide an overview of 3D sensor technologies and their capabilities and limitations, based on Carnegie Robotics’ experience selecting the right 3D technology and sensor for a diverse range of autonomous robot designs.
There is no perfect sensor technology and no perfect sensor, but there is always a sensor which best aligns with the requirements of your application -- you just need to find it. We’ll describe a quantitative and qualitative evaluation process for 3D sensors, including testing processes using both controlled environments and field testing, and some surprising characteristics and limitations we've uncovered through that testing.
Since 2011, Chris Osterwood has led the development of many of Carnegie Robotics' robotic component products and custom robotic systems including MultiSense, smart monocular and ring cameras, purpose-built manipulators, off-road unmanned ground vehicles, and indoor autonomous robots. He guides many of Carnegie Robotics’ industry partnerships and leads developments of customized versions of the MultiSense and downstream software for particularly demanding and high volume markets including infrastructure mapping and assessment, resource mining, and agricultural applications. Prior to joining CRL, Chris was a Senior Engineer and Product Manager at RedZone Robotics Inc. where he led the engineering and product development for several highly successful sewer inspection robots including Solo, the first commercially available autonomous sewer robot. Chris has a Mechanical Engineering Degree with Research Honors from Carnegie Mellon University.