Computational Sensor Lab creates specialty imaging sensors for improving robustness and capabilities of robot vision systems. 

Rather than only miniaturizing  existing capabilities, our goal is to bring new capabilities to vision systems. For most of our implementations there is no conventional system substitute. Simply, conventional systems cannot do what our sensors do because either the sensor signal is missing, or the system is not fast enough to cope with continuous events in the physical world. 

Our algorithms manipulate parameters and arrangements in three areas: 1) image formation and sensing, 2) on-chip computation using analog and mixed-mode circuits, and 3) system integration using commercial embedded processors and networks.

Mainly, the superior performance of our sensors comes from analog on-chip signal processing that enables low latency and rapid adaptation to environmental changes. Miniature size, low power and low cost are added benefits of our solutions.

Please explore our work and let us know what you think.

In the news !!!



In the news

Note to Prospective  Team Members

Other Vision Chip Groups

Vision and Autonomous System Center (VASC)

The Robotics Institute

School of Computer Science

Carnegie Mellon University