Qualcomm® Robotics RB3 Platform(SDA845)
The Qualcomm Robotics RB3 development kit supports the development of smart, power-efficient and cost-effective robots by combining high-performance heterogeneous computing, Qualcomm®Artificial Intelligence (AI) Engine for on-device machine learning, computer vision, vault-like security, multimedia and Wi-Fi and cellular connectivity (4G/LTE and CBRS). Comprised of a comprehensive set of software & hardware, including the industry’s best performing 6-Axis Motion Sensor (ICM-42688), Top Port PDM Microphone (ICS-41351), and Barometric Pressure Sensor (ICP-10101) from TDK InvenSense.The Qualcomm Robotics RB3 development kit is designed to help manufacturers and developers create robotic products ranging from large industrial and enterprise robots to small battery-operated one’s with challenging power and thermal dissipation requirements.
Qualcomm® Robotics RB3 Platform
Dedicated platform build smart, power-efficient and cost-efficient robots
Robotics RB3 Applications
Automated Guided Vehicle
Self-driving Vehicle for logistics
Qualcomm® Robotics RB3 Platform Highlights
On-device intelligence powered by Qualcomm Artificial Intelligence (AI) Engine
The Qualcomm Robotics RB5 Platform supports the leading 5th generation Qualcomm AI Engine with the brand-new Qualcomm Hexagon™ Tensor Accelerator, pushing 15 trillion operations per second(TOPS) with maximum efficiency to run complex AI and deep learning workloads at the Edge.
Power efficient and cost-effective
The Qualcomm ® Robotics RB3 Platform is designed to support large industrial and enterpriseenterprise robot’s as well as small battery-operated robots with challenging power and thermal dissipation requirements.
Comprehensive development kit
The kit includes the robotics-focused development board, compliant with the 96Boards open hardware specification for supporting a broad range of mezzanine-board expansions and range of sensor support like camera sensor, depth camera, time-of-flight, multi-mic support, GMSL sensor, Ultrasonic Time-of-Flight Sensor with Extended Range and support for additional sensors like IMU, pressure sensor etc.
Flexible design options for commercialization
In addition to a feature packed development kit, the platform offers a range of solutions for commercialization from off-the-shelf System-on-Module (SoM) solutions to speed commercialization, to the flexibility for chip-on-board designs for cost-optimization at scale.
High Resolution depth sensing
Robust depth sensing solution infused with an inertial measurement unit (IMU) using depth camera.
Time-of-Flight (ToF) camera
Time-of-flight for gestures and hand tracking use cases
Perception and Navigation using Tracking Camera Sensor module to do visual simultaneous localization and mapping (vSLAM).
Qualcomm ®Secure Processing Unit, hardware root of trust, trusted execution environment, secure boot, camera security
Support for multiple sensors and 3rd party algorithms through Sensor Software Framework
Wi-Fi integrated 802.11ac 2x2 with MU-MIMO and support for Bluetooth 5.0 and cellular mezzanines for LTE and CBRS
Robotics RB3 Feature Demo
Qualcomm’s Robotics RB3 Platform with ROS has been seamlessly integrated with and drives Kobuki mobile research base. RB3 platform’s ToF camera or structured light camera can be used for depth mapping and development of navigation algorithms to drive the Kobuki. RB3 platform’s tracking camera can be used for visual simultaneous location and mapping (vSLAM), and the high resolution camera can be used for video recording.
Specifications of the Robotics DragaonBoard™ 845c
|Component||Qualcomm® Robotics RB3 Development Kit|
|CPU||SDA845 8x Kryo 385 CPU, up to 2.8 GHz|
|GPU||Qualcomm® Adreno™ 630 GPU with support for Open GL ES 3.2 and Open CL 2.0|
|DSP||Qualcomm® Hexagon™ 685 DSP with 3rd Gen Vector Extensions|
|ISP||Qualcomm® Spectra™ 280 Image Signal Processor with new architecture for 14-bit image signal processing|
|RAM||4GB LPDDR4x SDRAM @ 1866 MHz|
|Memory||LPDDR4x, 4x16 bit; up to 1866MHz, 4GB RAM|
|Storage||64GB UFS 2.1 on-board storage and 1 x MicroSD card slot|
|Ethernet||1x GbE Ethernet|
|Wireless||Wi-Fi integrated 802.11ac 2x2 with MU-MIMO; Tri-band Wi-Fi: 2.4 GHz and 5 GHz with Dual Band Simultaneous (DBS).
Qualcomm ® TrueWireless™ Bluetooth 5.0
|Location||GPS, Glonass, BeiDou, Galileo, QZSS, and SBAS|
|USB||1 x USB 2.0 Micro B (Debug only)
1 x USB 3.0 Type C (OTG mode)
2x USB 3.0 Type A (Host mode only)
|Display||Two 4-lane DSI, D-PHY 1.2 or C-PHY 1.0; VESA DSC 1.1
1 x HDMI 1.4 (Type A - full) connector
|Video||Ultra HD Premium video capture @ 4K (3840x2160) 60fps, 10bit HDR, Rec 2020 color gamut; H.264 (AVC), H.265 (HEVC) and VP9 support; Slow motion HEVC video encoding of either HD (720p) video up to 480fps or FHD (1080p) up to 240fps|
|Audio||MP3; aacPlus, eAAC; WMA 9/Pro|
|Camera||Single HFR 16 MPix camera at 60fps ZSL, Dual 16 MPix cameras at 30fps ZSL, Single 32 MPix camera at 30fps ZSL|
|Sensor||ICM-42688 6-Axis High Performance Motion Sensor, ICS-41351 Top Port Digital Microphone, and ICP-10101 Barometric Pressure Sensor from TDK InvenSense.|
|Expansion Interfaces||2 x 60 pin High-Speed connectors , 2 x 40 pin Low-Speed connectors, 1 x 20 pin Low-Speed connector|
|LED||7 x LED indicators|
|Button||Power ,Volume Up/Down,Force Usb Boot, DIP Switch|
|Power Source||12V@2.5A adapter with a DC plug|
|Size||85mm by 54 mm|
- Software Support for Linux and Robot Operating System (ROS)
- Qualcomm® Neural Processing SDK: optimizing deep learning processing performance across available resources to achieve superior edge computing experience.
- Qualcomm FastCV Computer Vision SDK: Offers a mobile-optimized computer vision (CV) library which enables new user experiences like gesture recognition, face detection, tracking and recognition, text recognition and tracking and augmented reality.
- Qualcomm® Hexagon DSP SDK: The Hexagon™ SDK is designed to optimize the features and performance of multimedia software.
- Qualcomm® Secure Processing Unit (SPU) offers vault-like security that safeguards your facial data, iris scan and other biometric data.