Qualcomm today announced its Robotics RB3 Platform, an integrated offering designed specifically for robotics. The platform includes an optimized set of hardware, software, and tools designed for manufacturers and developers to “create the next generation of advanced consumer, enterprise, and industrial robotics products.”
The RB3 platform is based on Qualcomm’s SDA/SDM845 system-on-chip (SoC), and integrates features such as high-performance heterogeneous computing, 4G/LTE connectivity including CBRS support for private LTE networks, and a Quallcomm AI Engine for on-device machine learning and computing vision. Additional features include high-fidelity sensor processing for perception, odometry for localization, mapping, and navigation, security features and Wi-Fi connectivity. Qualcomm said it will also introduce 5G connectivity support for the platform later this year, enabling low latency and high-throughput for industrial robotics applications.
Fast development, commercialization
“Our technologies are at the heart of a wide array of robotics products available today, from companion robots including Anki Vector, Elli Q and Sony Aibo, to multimedia robots like Cerevo Tripon and Keecker, to labor-saving machines such as robotic vacuum cleaners from iRobot, Ecovacs and Panasonic,” said Dev Singh, director of business development and head of autonomous robotics, drones and intelligent machines at Qualcomm Technologies, Inc. “With the Qualcomm Robotics RB3 Platform, we aim to bring our cutting-edge AI, edge compute and connectivity technologies into the hands of many more robotics innovators to help spur the fast development and commercialization of a new generation of useful and intelligent robots in agriculture, consumer, delivery, inspection, service, smart manufacturing/Industry 4.0, warehousing and logistics, and other applications.”
The company said its RB3 platform is designed to allow for flexible design options for development and commercialization, from development board offerings for prototyping, to off-the-shelf system-on-module solutions for faster commercialization, as well as flexibility for chip-on-board designs to achieve cost optimization at scale. The platform supports both Linux and the Robot Operating System (ROS), while also supporting Qualcomm’s Neural Processing software development kit (SDK) for on-device AI, the Qualcomm Computer Vision Suite, the Qualcomm Hexagon DSP SDK, and Amazon’s AWS RoboMaker. The company also said it plans to support Ubuntu Linux in the future.
Beyond automation and control
Lian Jye Su, principal analyst at ABI Research, said the announcement of the RB3 comes at the right time for commercial robots that need to be autonomous, agile, intelligent, and self-aware of their environments.
“For applications such as last-mile delivery, retail assistance, construction, tower inspection, construction and mining, robots need to support new capabilities beyond just function automation and control,” Jye Su said. “Thanks to its support for a wide range of sensors and the ability to use these sensors to dynamically manage, control, and schedule the robots’ functions, platforms such as Qualcomm Robotics RB3 Platform provides the robot with the required intelligence and enable them to make informed decisions during their operation in line with the task expected from them.”
Some of the company’s competitors have already launched similar platforms, including NVIDIA and its Jetson system, and Intel’s RealSense platform, although Jye Su said those have mainly focused on machine-vision applications that provide the robot a full autonomy for its operation. “In contrast, Qualcomm Robotics RB3 Platform comes with embedded connectivity, enabling robots to communicate with the outside world. This ability not only allows the robot to augment the self-awareness of its environment, but also provides the robot with additional capabilities including better collaboration with humans and machines.”
While the adoption of LTE in outdoor robotics remains low, ABI Research said it estimates the shipments of robots with cellular connectivity, including LTE and 5G, to reach 950,000 units by 2027, creating a $48 billion market opportunity for developers, chipset vendors, camera and sensor manufacturers, and robotics software and service providers.
Technical features of RB3
The platform’s hardware development kit contains the new purpose-built robotics-focused DragonBoard™ 845c development board, based on the Qualcomm SDA/SDM845 SoC and compliant with the 96Boards open hardware specification to support a range of mezzanine-board expansions. Optional elements for the kit include a connectivity board; an image camera for high-resolution photos, 4K video capture and AI-assisted detection and recognition of people and objects; a tracking camera for path planning and obstacle avoidance using visual simultaneous localization and mapping (VSLAM); a stereo camera for navigation; and a time-of-flight camera for people, gesture and object detection even in low light conditions.
Qualcomm said the Robotics RB3 Platform technical features include:
- A heterogeneous computing architecture: The Qualcomm SDA845/SDM845 SoC powering the platform is built on 10-nanometer (nm) LPP FinFET process technology. The SoC integrates an Octa Core Qualcomm Kryo CPU with performance up to 2.8GHz, a Qualcomm Adreno 630 Visual Processing Subsystem (including GPU, VPU and DPU), and a Qualcomm Hexagon™ 685 DSP with Hexagon Vector Extensions (HVX), which delivers on-device AI processing and mobile-optimized computer vision (CV) capabilities for perception, navigation and manipulation.
- Qualcomm AI Engine: Deep learning performance across the Qualcomm AI engine (CPU, GPU, and DSP) delivers up to three tera-operations-per-second (TOPS) performance, with the DSP itself delivering 1.2 TOPS at one watt with hardware acceleration. This includes the Qualcomm Neural Processing SDK, which encompasses analysis, optimization, and debugging tools designed to allow developers and manufacturers to port trained deep learning networks on the various heterogeneous compute blocks offered by the platform.
- Camera and video: The dual 14-bit Qualcomm Spectra 280 ISP supports up to 32-megapixel single camera; support for up to 4K HDR video capture at 60 frames per second.
- Security: The Qualcomm Secure Processing Unit (SPU) provides high performance while maintaining power efficiency. The SPU includes the following key components: secure boot, cryptographic accelerators, Qualcomm Trusted Execution Environment (QTEE), and camera security. To address advanced AI, ML, and biometrics, Qualcomm SDA/SDM845 supports porting of virtualization software.
- Sensor and microphone support: The platform includes support for sensors like a 6-axis inertial measurement unit (IMU) consisting of a 3-axis gyroscope and a 3-axis accelerometer; capacitive barometric pressure sensor; multi-mode digital microphones; and additional ports for supplementary sensors from TDK-InvenSense.
- Connectivity: Supports integrated 4G/LTE and CBRS, with 5G support planned to be enabled late this year; Wi-Fi integrated 802.11ac 2×2 with MU-MIMO; Tri-band Wi-Fi: 2.4 GHz and 5 GHz with Dual Band Simultaneous (DBS); and Qualcomm TrueWireless Bluetooth 5.0.
Wide range of robotics company support
Several companies in the robotics and technology space have offered their support for the new RB3 platform, including Amazon, Brain Corp, JD.com, and OrionStar, among others.
“We are delighted to be working with Qualcomm Technologies to help developers easily build intelligent robotics functions using AWS cloud services and then deploy their application onto a commercial grade, scalable hardware platform,” said Roger Barga, GM of AWS Robotics and Automation Services, Amazon Web Services, Inc. “Our collaboration is designed to give robotics developers a complete cloud-to-the-edge solution, accelerating development, providing intelligence out of the box, and easing robotic lifecycle management.”
“As the creators of BrainOS, the leading solution for the development, deployment and management of mobile robots, we’re excited to see Qualcomm Technologies get involved in the space in a major way,” said Dr. Jean Baptiste Passot, VP of Platform and AI, Brain Corp. “We’ve expanded BrainOS to be optimized with the Qualcomm SDM845 and look forward to exploring the potential of the Qualcomm Robotics RB3 Platform for our future products.”
“JD.com believes that the combination of industry and technology can create infinite possibilities for digitalization,” said Yazhuo Wang, General Manager of Innovation Product Department, JD.com IoT Business Group. “We look forward to the new generation of Qualcomm Technologies’ Robotics Platform, which will help us develop more efficient and intelligent service robots through advanced technologies such as deep learning algorithms.”
“OrionStar is excited to see Qualcomm Technologies launch the Qualcomm Robotics RB3 Platform with cutting-edge AI, edge computing and connectivity technologies, which enables robots to benefit from the latest innovations in mobile technology,” said Fu Sheng, Chairman and CEO, Cheetah Mobile Inc., and Founder, OrionStar. “Based on previous successful cooperation with Qualcomm Technologies on our service robotics, OrionStar looks forward to continuing to work with Qualcomm Technologies to provide consumers with a new wave of innovative, smart and power-efficient useful robots.”
Commercial products based on the Qualcomm Robotics RB3 Platform are expected to be available in 2019. Both NAVER and LG said they are evaluating the Qualcomm Robotics RB3 Platform, and plan to showcase select robotics products based on the platform early next year. Additional early users are expected to be Anki, Brain Corp JD, Misty Robotics, OrionStar, Robotis, and others. A development kit based on the Qualcomm Robotics RB3 Platform is available for purchase now from Thundercomm.
More information on the platform is available through the Qualcomm website.