Jetson Nano – A newbie to ROS and A.I. ecosystem

By saipriya mukunthaprabhu In A.I., Robotics

06

Jun
2019

We would have already worked with ROS  where it will be involved with SLAM, Navigation etc. But when we need to work with any Artificial Intelligence which involves high GPU access were the entry level SBC’s like Raspberry Pi, Beaglebone Black, Odroid U3 and many more can’t afford this GPU capability. This is the right entry into the ROS hardware ecosystem of Jetson Nano board which is mainly used for A.I. & run multiple neural networks in parallel for applications like image classification, object detection, segmentation, and speech processing.

While checking up the cost of Jetson Nano which seems to be very affordable when comparing to other Jetson boards with these capabilities.

Technical Specifications

GPU128-core Maxwell
CPUQuad-core ARM A57 @ 1.43 GHz
Memory4 GB 64-bit LPDDR4 25.6 GB/s
StoragemicroSD (not included)
Video Encode4K @ 30 | 4x 1080p @ 30 | 9x 720p @ 30 (H.264/H.265)
Video Decode4K @ 60 | 2x 4K @ 30 | 8x 1080p @ 30 | 18x 720p @ 30 (H.264/H.265)
Camera1x MIPI CSI-2 DPHY lanes
ConnectivityGigabit Ethernet, M.2 Key E
DisplayHDMI 2.0 and eDP 1.4
USB4x USB 3.0, USB 2.0 Micro-B
OthersGPIO, I2C, I2S, SPI, UART
Mechanical100 mm x 80 mm x 29 mm

To know more details about the Jetson Nano, you can visit official link: https://developer.nvidia.com/embedded/buy/jetson-nano-devkit

To get started ROS on Jetson Nano you can find the best self understandable link: https://www.stereolabs.com/blog/getting-started-with-jetson-nano/

Leave a reply