Platforms for robot vision are based on modular concepts, building blocks and platform technologies to provide users with better integration processes and ultimately more stable and flexible solutions. Based on the three levels of (1) hardware, (2) vendor software and (3) customer-specific software, users can design tailored vision solutions for functional applications.
As a highly flexible robot vision platform, the rc_visard NG is the first to unite all three levels on one sensor. Without additional hardware or external computing power, the rc_visard NG delivers powerful robot vision right on the edge in one single device.
rc_visard NG users do not need any expertise or prior experience in machine vision: Thanks to its user-friendly web interface, the rc_visard NG can be used intuitively and the installation effort is reduced to a minimum.
The rc_visard NG can also be connected and configured via Rest-API, ROS, OPC UA and GenICam.
The UserSpace feature allows users to deploy custom software directly on Roboception’s sensor hardware through Docker containers.
The UserSpace is highly useful for collision-free motion planning, Industry 4.0 applications, vision pipelines, or application programs – all while preventing users from having to purchase additional hardware to run those individual software tools.
REST-API and gRPC interfaces can be used within the UserSpace to obtain grasp points and image data, giving access to all activated rc_reason modules and connected sensors.
The rc_reason suite of software modules is an advanced AppliedAI solution designed for robotic applications:
Users select the plug-and-produce software module that best fits their individual needs, and with just a few mouse clicks, the rc_visard NG provides task-relevant information such as grasp points. Any additional software elements can be included via the platform’s UserSpace.
The rc_visard NG combines the high-performance rc_reason software suite with the UserSpace, which allows users to deploy their own software in Docker containers – directly on the sensor. This smart vision platform is powered by the high-performance NVIDIA® Jetson Orin™ series, the most advanced embedded AI solution for robot vision on the market. Designed to perform most powerfully and power-efficiently, this small AI computer can be housed directly in the sensor hardware, making the rc_visard NG smarter than ever!
rc_visard NG | |||
---|---|---|---|
GPU/CPU | Nvidia® Jetson Orin™ Nano 8 GB | ||
Base distance | 160 mm | ||
Focal length (lenses) | 6 mm | ||
Image resolution | 1440 x 1080 Pixel (1.6 MPixel) | ||
Field of view | horizontal | 43° | |
vertical | 33° | ||
Depth measurement range* | 0.5 m – 3.0 m | ||
Workspace | 0.5 m distance | 0.24 m x 0.30 m | |
1.0 m distance | 0.64 m x 0.60 m | ||
2.0 m distance | 1.44 m x 1.20 m | ||
3.0 m distance | 2.24 m x 1.80 m | ||
Depth resolution | 0.5 m distance | 0.05 mm | |
1.0 m distance | 0.2 mm | ||
2.0 m distance | 0.9 mm | ||
3.0 m distance | 2.0 mm | ||
Depth image resolution & FPS | 0.5 m distance | High: 720 x 540 @ 7.4 Hz (latency: 230 ms) | |
Medium: 360 x 270 @ 25.0 Hz (latency: 70 ms) | |||
Low: 240 x 180 @ 25.0 Hz (latency: 50 ms) | |||
1.14 m distance | Full: 1440 x 1080 @ 3.0 Hz (latency: 530 ms) | ||
High: 720 x 540 @ 16.1 Hz (latency: 170 ms) | |||
Medium: 360 x 270 @ 25.0 Hz (latency: 70 ms) | |||
Low: 240 x 180 @ 25.0 Hz (latency: 50 ms) | |||
Power supply | 18-30 V | ||
Protection class | IP54 | ||
Cooling | Passiv | ||
Temperature range (Celsius) | 0°C – 45°C | ||
Size (LxHxW in mm) | 230 x 75 x 85 mm | ||
Weight | 979 g |
*In principle, the rc_visard NG can measure infinite ranges. However, the accuracy is decreasing quadratically due to the stereo method, which is why we recommend the measurement range stated above.
The complete product documentation of the rc_visard NG is available online.
Roboception offers tools for easy and efficient interfacing and operation of the rc_visard NG.
Roboception GmbH
Kaflerstr. 2
81241 Munich
Germany
+49 89 889 50 79-0