APLUX

Robotics compute platform selection

Rhino Core IQ10

A core compute platform for Physical AI

Use Qualcomm Dragonwing IQ10 for multimodal perception and robotics models. APLUX provides companion robotics development boards, tools and project support to evaluate compute configurations, sensor connectivity and deployment paths.

Rhino Core IQ10 component side

350 TOPS

Maximum AI performance (INT8, dense)

18 cores

Qualcomm Oryon CPU

LLM / VLM / VLA

Model deployment focus

Robotics

Perception, inference and device integration

A core compute platform for Physical AI

Match the compute platform to your device tasks, models, peripherals and product form factor.

Compute foundations for robotics models

Oryon CPU, Adreno GPU and a dedicated NPU provide platform compute for adapted language, vision and robotics models.

Evaluate against real device needs

Define companion hardware around cameras, network sensors, storage and control requirements, then validate the complete application with the delivered BSP.

Tools and application support

Use AIMO, AidGen SDK, AidLite and robotics reference software for model adaptation, deployment and field testing.

Start evaluation with a development board

The complete Rhino Pi IQ10 board currently supports evaluating 64 GB+256 GB, 8 GMSL2 channels and multigigabit networking. Confirm standalone module configurations separately.

Explore integration paths for real-world tasks

Plan sensor and system integration for robot perception, higher-level planning and industrial model services.

Qualcomm Dragonwing IQ10 Series

Build a robot's perception and planning hub

Multisensor fusionTask inferenceHigher-level planning
Up to 350 TOPS(INT8, dense)Platform-rated peak; validate performance for your workload
Illustrative embodied robot

Embodied robot

Combine multiview perception, multimodal understanding and task planning with cameras, sensors and robot control systems.

Platform fit
Combine multiview perception, multimodal understanding and higher-level planning into an embodied task computing pipeline.
Module integration
Evaluate first with Pi IQ10 GMSL2 and CAN FD links; standalone module carrier interfaces require separate confirmation.
Multisensor inputPerception and planningAction coordination
View interfaces and integration
Illustrative low-speed autonomous driving terminal

Low-speed autonomous driving

Develop environmental perception, localization and higher-level planning for low-speed delivery and mobile operations, integrating with chassis control systems.

Platform fit
Fuse environmental inputs, run localization and planning, and pass higher-level commands to the vehicle control system.
Module integration
Connect sensors and a companion chassis controller to Pi IQ10 first; development board connectors are not standard standalone-module features.
Environmental perceptionLocalization and planningChassis coordination
View interfaces and integration
Illustrative industrial AI agent server

Industrial AI agent server

Connect industrial data, multimodal models and business tools to local compute for analytics, knowledge Q&A and task orchestration.

Platform fit
Combine multimodal models, industrial knowledge and business tools into local analytics and task orchestration services.
Module integration
Validate networking, NVMe and model services on Pi IQ10 first; confirm module production configurations, pin assignments and cooling separately.
Industrial data and knowledgeModels and toolsTask orchestration
View interfaces and integration

Device images illustrate application directions; peripherals, enclosure and software require project-specific integration. Modules require a carrier; platform resources are not equivalent to exposed device interfaces. Sensor and communication links can first be validated with the companion Pi IQ10 board.

Rhino Core IQ10 specifications

Configurations below follow the robotics compute platform selection documentation. Module capabilities and physically exposed device interfaces are distinguished.

Platform compute capabilities

Rhino Core IQ10 · Platform compute capabilities
Compute platformQualcomm Dragonwing IQ10 Series
CPU18-core Qualcomm Oryon, up to 3.014 GHz
NPUQualcomm Hexagon
AI performance (INT8, dense)Up to 350 TOPS(INT8, dense)
AI performance (INT8, sparse)Up to 700 TOPS(INT8, sparse)
GPUDual Qualcomm Adreno GPUs; main GPU up to 1.0 GHz, auxiliary GPU up to 1.1 GHz
Model focusLLM / VLM / VLA; validate specific models and performance with adapted software

AI figures are platform-rated peaks. Dense, sparse and FP16 figures are listed separately; actual performance depends on the model, precision, software and cooling. Input power ratings do not represent total board consumption. Accessories and system images depend on the delivered configuration.

Product configuration and integration notes

This page describes IQ10 platform compute capabilities. Confirm standalone module production configurations, pin assignments, electrical requirements and dimensions separately.

The companion Rhino Pi IQ10 board follows its own complete-board specification. Chip-package images do not represent a complete physical module.

Build your edge AI product with Rhino Core IQ10

Share your model, peripheral, mechanical and system requirements to define the product and delivery configuration together.