Requirements

Note

Due to USB connection speed issues, running the software inside a virtual machine environment is not supported.

General

An internet connection is required at the start of each session to access the Slamcore software license.

Sensor data

Slamcore software supports the following cameras over USB port >= 3.0:

Alternatively, users without cameras can use public datasets:

  • EuRoC MAV Dataset

  • OpenLORIS-Scene Dataset

  • TUM VI Benchmark Dataset

System and Hardware

To run Slamcore software, the required hardware and OS specifications are:

x86_64

NVIDIA Jetson

Ubuntu

20.04

22.04

18.04

20.04

PC 1

JetPack 4 2

JetPack 5 3

Slamcore Tools

Supported

Supported

Supported

Supported

Panoptic Plugin

Not supported

Not supported

Not supported

Supported on JetPack 5.1

Python API

Supported

Supported

Supported

Supported

C++ API

Supported

Supported

Supported

Supported

ROS 2 Foxy

Supported

Via docker

Via docker

Supported

ROS 2 Galactic

Supported

Via docker

Via docker

Supported

ROS 2 Humble

Via docker

Supported

Via docker

Via docker
1

The processor should support the AVX2 instruction set.

2

Slamcore supports JetPack 4.4.1 - 4.6.1 (L4T 32.4.4 - 32.7.1) on the NVIDIA Jetson Nano, TX2, Xavier NX and Xavier AGX.

3

Slamcore supports JetPack 5.0.2 - 5.1.1 (L4T 35.1 - 35.3.1) on the NVIDIA Jetson Xavier NX, Xavier AGX, Orin Nano, Orin NX and Orin AGX.

Listed are the minimum and recommended processors, memory and storage to run each of our SDK tools and APIs.

Tool/API

Processor

Memory

Storage

Minimum

Recommended

Minimum

Recommended

Minimum

Recommended

Dataset Recording

x86 (i5) or Jetson Nano

x86 (i5) or Jetson Orin Nano

2GB

4GB

16GB 4

128GB 4 SSD

VIO Mode 5

x86 (i5) or Jetson Nano

x86 (i5) or Jetson Orin Nano

2GB

8GB

16GB

16GB

SLAM Mode 5

x86 (i5) or Jetson Nano

x86 (i5) or Jetson Orin Nano

4GB

16GB

16GB

16GB

2.5D Mapping 6

x86 (i5) or Jetson Nano

x86 (i5) or Jetson Orin Nano

4GB

16GB

16GB

16GB

ROS 2 Example 5

x86 (i5) or Jetson Xavier NX

x86 (i5) or Jetson Orin Nano

8GB

16GB

16GB

128GB SSD

The table above assumes no other significant processes are consuming system resources.

4(1,2)

Disk write speeds must be sufficient to meet requirements (see Recording Datasets)

5(1,2,3)

Assuming SLAM running at 15 frames per second

6

Assuming both SLAM and 2.5D mapping running at 15 frames per second

ROS Wrappers

The Slamcore ROS Wrappers support:

  • ROS 2 Foxy and Galactic on Ubuntu 20.04 and JetPack 5

  • ROS 2 Humble on Ubuntu 22.04

To run our ROS Wrappers on different Ubuntu distributions (e.g. ROS 2 Humble on JetPack 5/Ubuntu 20.04) or in an isolated environment you can use Docker. Follow the instructions on slamcore-ros2-docker to run our ROS Wrappers via Docker.

ROS Visualisation

To run both SLAM and the ROS visualisations (RViz2) on the same system requires additional resources, we have tested this on a machine with the following hardware specification:

  • Core i7-7700HQ CPU @ 2.80GHz

  • 16GB of RAM

It is possible and recommended to run SLAM and the ROS visualisations on separate, networked systems.

Recording Datasets

To record datasets they will need to be written to a drive capable of sustaining write speeds set out in the table below.

Write Speed (MB/s)

x64

NVIDIA Jetson Platforms

without depth

25

12.5

with depth

100

50