Software Reference Manual
The Qualcomm® Robotics RB5 Development Kit is based on the Qualcomm Robotics RB5 Platform that facilitates accelerated development of innovative, power-efficient, high computing robots and drones for enterprise, industrial, and professional service applications.
At the heart of the kit is the Qualcomm® QRB5165 processor. Customized for robotics applications, this processor offers powerful heterogeneous computing architecture that delivers 15 Tera Operations Per Second (TOPS) of compute. It also offers incredible machine learning (ML) accuracy, a powerful image signal processor (ISP) with support for seven concurrent cameras, a dedicated computer vision engine for enhanced video analytics (EVA), as well as the new Hexagon™ Tensor Accelerator (HTA). Its fifth-generation Qualcomm® AI Engine powers inferencing and accuracy with the dedicated Hexagon Tensor Accelerator. QRB5165 can support an industrial temperature range of –30 C to +105 C, with long life support. The kit can also offer LTE/5G/CBRS communications via a mezzanine card.
The QRB5165 processor and Qualcomm® Robotics RB5 platform cater to a wide range of applications such as autonomous mobile robots (AMR), inventory robots, retail robots, cobots, pick-sort-place robots, cleaning robots, first mile robots, last mile delivery robots and delivery drones, prosumer and commercial drones, industrial and manufacturing robots, healthcare robots, defense robots, etc.
From the development board offerings for prototyping, to off-the-shelf system-on-module (SoM) solutions to speed commercialization, to the flexibility for chip-on-board designs, the Qualcomm Robotics RB5 Platform offers flexible options for development and commercialization.
12.4x12.7 mm LP4, 12.4 x 14 mm LP5 MEP
4+4 Qualcomm® Kryo™ 585 - Gold Core @ 2.84 GHz (Octa-core 64-bit ARM v8 compliant applications processor. )
Four-channel PoP high-speed memory – LPDDR5 or LPDDR4X SDRAM. (4 × 16-bit) designed for a 2750 MHz (LPDDR5) or 2133 MHz (LPDDR4X) clock and system cache
External 2x2 802.11ax, BT5.1, external 802.11ad
Qualcomm® PM8250 + Qualcomm® PM8150L or Qualcomm® PM8150A + Qualcomm® PM8150B + Qualcomm® PM3003A
Qualcomm® Adreno™ 650 Native 8-bit integer support for efficient GPU DNN
OpenGL ES 3.2, Vulkan 1.1, DX12 FL 12_1; OpenCL 2.0 full profile
Adreno DPU 995, supports up to three 4K displays (one internal display through DSI and two external displays through DisplayPort)
Two 4-lane DSI D-PHY 1.2 or two 3-trio C-PHY v1.1 with VESA DSC v1.1. DisplayPort v1.4 at 8.1 Gbps/lane over Type-C with support for MST and VESA DSC v1.1 and FEC (USB3 and USB2 concurrency supported). Miracast – up to 4K60
64 MP 30 fps ZSL with a dual ISP. Real-time sensor input resolution: 25 + 25 + 2 + 2 + 2 + 2 + 2 with support for up to 12 cameras by D-PHY and 18 cameras by C-PHY (seven concurrent)
MIPI CSI configurable in 4 + 4 + 4 + 4 + 4 + 4 configuration
Video decode up to 4K240/8K60. Native decode support for H.265 Main 10, H.265 Main, H.264 High, VP9 profile 2, VP8, and MPEG-2 codecs
Video encode up to 4K120/8K30. Native encode support for H.265 Main 10, H.265 Main, H.264 High, and VP8 codecs
Enc & Dec
Concurrent 4K60 decode and 4K30 encode
Integrated WCD9380 high fidelity audio codec
SoundWire interface (two Tx and two Rx data lines; optional configuration of three Tx and one Rx data lines) for codec. Dedicated SoundWire interface for smart speaker amplifier
Essential and advance voice communications package, Voice UI activation package, Voice UI speech enhancement package, 3D audio capture package
V66, integrated low power island, 2 MB L2, 1.5 GHz
Hexagon™ DSP with Quad Hexagon™ Vector eXtensions (HVX) V66Q, 1.5 GHz, for machine learning, integrated DNN for advanced VA and Neural Processing SDK
Qualcomm Neural Processing Unit (NPU230) for high-performance machine learning use cases
Qualcomm® Sensing Hub for contextual awareness and always-on sensor support
UFS 3.0 gear 4 – for on-board memory and UFS 2.1 gear 3. SD v3.0 4 bit for SD card
PCIe (x3), USB 3.1, USB 3.1 Type-C w/DP
Qualcomm® Secure Processing Unit (SPU240) for advanced secure use cases
|Computer Vision||Dedicated CVP H/W block - CVP 2.x for Digital Image stabilization, Image correction etc.|