Embedded Computer Vision Real Time? Nvidia Jetson TX2 + VisionWorks toolkit

CSI Camera module

The Computer Vision is a really computational power requesting task, if you work with computer vision you know that to reach very high frame rates you need to maximize the parallelism of the algorithms and you know that massive parallelism is reachable only moving elaborations to GPUs. The embedded massive …

Continue reading

First boot of the Nvidia Jetson TX2 and CUDA test

The 7th march Nvidia launched the new Jetson TX2. In the launch post I described the differences with the previous Jetson and how the new Jetson TX2 can double the performances of the TX1. Now it’s time to see how it really works, so let’s stop the written words and let’s …

Continue reading

[Video] Testing the new uNavSB H-Bridge board for uNav Motor Controller

http://myzharbot.robot-home.it/blog/build-myzharbot-get-started/component-list/

The motors that move MyzharBot are really powerful, really too much powerful for the motor drivers mounted on the little uBridge shield used originally by the amazing uNav Motor Control board made by Officine Robotiche. For this reason Mauro Soligo (under a “very little” pressure) realized the new uNavSB carrier board that uses the …

Continue reading

Test of the integration of Ultrasonic Bumper with ROS framework

Ultrasonic Bumper Board - ROS test

In the following video you can see one of the first test of the integration of the Ultrasonic Bumper with the ROS framework. The test verifies the response time of two sensors mounted on the front panel of MyzharBot-v4. The ros_ultrasonic_bumper node acquires the ranges from the two sensors and publishes …

Continue reading

Ultrasonic Bumper Board based on ST Nucleo32

Sonar Board prototype

The optical spatial sensors mounted on MyzharBot v3 and MyzharBot v4 have a intrinsic limitation that make it unable to perceive obstacle that are too near along its forward motion direction. Asus Xtion Pro Live does not see obstacles nearest than 50cm, Stereolabs ZED does not see obstacles nearest than …

Continue reading