VERSION 3

Autodiscovery HEAD-Lite

Lightweight GNSS & 4D Camera Navigation Payload

The HEAD-Lite (Holistic Equipment for Autonomous Driving - Lite) Version 3 is the lightweight, outdoor-optimized counterpart to the HEAD360. Designed for compact mobile robots in field environments like agriculture, construction, and mining, it integrates high-precision GNSS/GPS for outdoor localization, one (1) wide-FOV 4D depth camera with standalone NPU edge processing, and high-capacity solid-state storage (using the Autodiscovery Vault drive system) for long-duration offline deployments. It packs these high-performance modules into a single plug-and-play IP65 ruggedized enclosure.

FIELD NAVIGATION CHALLENGES

GPS Signal Multipath & Outages: Urban canyons, dense tree canopies, and structures degrade GNSS positioning accuracy, causing dangerous navigation drift.

Zero-Lux & Bad Weather: Standard optical cameras fail under zero-lux night conditions, thick dust, or heavy glare, halting visual mapping and navigation.

Data Logging Capacity: High-resolution spatial cameras generate immense data volumes, quickly filling standard onboard robot drives during day-long field runs.

Unstable Field Telemetry: Transmitting video and state data over long distances via poor cell coverage leads to packet loss and latency in telemetry.

HEAD-LITE INTEGRATED SOLUTION

Centimeter-Level GNSS: Integrates a high-precision, RTK-capable GNSS/GPS receiver for centimeter-level localization in complex outdoor environments.

Integrated Night Illumination: High-power LED flood lights automatically illuminate zero-lux environments, keeping vision algorithms tracking in the dark.

Autodiscovery Vault SSD: High-capacity, high-bandwidth solid-state storage logs raw point clouds, imagery, and telemetry continuously during field trials.

Zenoh DDS and Wi-Fi 7: Multi-gigabit Wi-Fi 7 and Zenoh DDS middleware optimize network efficiency, minimizing telemetry dropouts.

EVALUATION READY & PLUG-AND-PLAY The HEAD-Lite is built entirely on the ROS 2 Jazzy ecosystem and preconfigured with Nav2. It features direct electrical and mechanical compatibility with various mobile robot bases (wheeled, tracked, and legged) for fast evaluation and deployment.

Primary Navigation Sensor	Integrated high-precision, RTK-capable GNSS/GPS receiver for outdoor localization and mapping
Vision and Depth	One (1) wide-FOV 4D depth camera for spatial sensing, obstacle detection, and stereo depth mapping
Night Operation	Built-in high-power LED flood lights for zero-lux illumination and continuous nighttime mapping
External Payload Support	Pre-configured input ports for optional external 3D LiDAR or vision sensors

Edge AI Processor	One (1) dedicated on-board Neural Processing Unit (NPU) integrated in camera for edge AI inference
Main Compute (Performance)	Advanced AI compute tier with 128GB system memory for heavy neural networks and SLAM
Main Compute (Efficient)	Energy-efficient x86 compute node with 32GB RAM for low-power battery-sensitive operations
Data Storage	High-capacity solid-state storage (Autodiscovery Vault drive system) for high-bandwidth telemetry and data logging

Network Router	Built-in advanced multi-gigabit Wi-Fi 7 network routing device
Cellular Support	5G communication support via optional integrated USB expansion stick
Audio Subsystem	Integrated multi-microphone array and speakers for voice interface and NLP
Middleware	Zenoh DDS for ultra-low latency, low-overhead communication over unstable networks

Supply Voltage Range	Built-in power regulation supporting 24V - 90V DC wide input range
Power Consumption	Typical: 20 W \| Peak: 120 W under full CPU/GPU load
Dimensions (L x W x H)	140 x 140 x 120 mm
Weight	1.1 kg
Operating Temperature	-20 degree C to +65 degree C
Environmental Rating	IP65 rated from above (fully IP65 when correctly integrated on the host robot)

Software Environment	Custom open-source stack built on ROS 2 Jazzy and Navigation 2 (Nav2)
Platform Compatibility	Out-of-the-box compatibility with Unitree (A2, A2-W, B2) and AgileX (Scout Mini, Bunker Mini, Ranger, Bunker Pro)