Success Story · ROBOTICS & LOGISTICS

Autonomous Vision-Guided Vehicles Reinventing Warehouse Intelligence

 
 

“The AIB-MX23 delivers the processing power we need in a compact, rugged package that can handle the harsh conditions of industrial facilities. The platform’s ability to process multiple sensor streams simultaneously with low latency was essential for our real-time navigation requirements.”
— Manuj Naman, CEO, Anantak

 

US-based robotics leader Anantak Robotics is revolutionizing industrial automation by deploying with over 200 autonomous Vision-Guided Vehicles (VGVs) powered by the Aetina AIB-MX23. Leveraging the NVIDIA® Jetson AGX Orin™ system-on-module, Anantak has empowered warehouses and factories to slash manual handling time by up to 80%—achieving peak material throughput without the need for costly fixed infrastructure.

 

 

KEY METRICS AT A GLANCE

  • 60–80%

    Reduction in manual trolley/cart handling time

  • 24/7

    Fully autonomous multi-VGV operation, every shift, every day

  • 2–4 Weeks

    Deployment time vs. months required for legacy AGV systems

 

 

THE CHALLENGE

The High Cost of Industrial Immobility

Warehouses, distribution centers, and manufacturing facilities face mounting pressure to move materials faster, more safely, and without adding headcount. Legacy approaches created as many problems as they solved.

High Labor Dependency

Dedicated material transport personnel performing repetitive tugger and cart-moving tasks drove up operational costs and created staffing bottlenecks during peak periods.

Rigid Fixed Infrastructure

Traditional AGVs rely on magnetic strips, April Tags, and fixed guide rails — expensive to install, disruptive to modify, and impossible to adapt as floor layouts evolve.

Workplace Safety Risks

Manual tugger operation in busy environments shared with forklifts and pedestrians led to a recurring pattern of workplace accidents and near-misses.

Inability to Scale

Meeting peak demand required proportionally growing the workforce — there was no cost-effective, infrastructure-light path to scale throughput on demand.

 

 

HOW IT WORKS

Vision-First Navigation, Step by Step

Anantak's VGV system relies on a continuous AI-driven perception loop powered entirely by the Aetina AIB-MX23 at the edge — no central server required.

  • Route Planning

    The VGV receives its destination and maps out the optimal path using data recorded during an initial facility mapping pass — no reprogramming needed when layouts change.

  • Multi-Sensor Data Collection

    The AIB-MX23 continuously ingests parallel streams from 2D LiDAR, 3D LiDAR, and multiple FRAMOS d455e cameras — fusing inputs into a unified real-time picture of the environment.

  • Real-Time AI Processing

    Onboard algorithms simultaneously build and update environmental maps, localize the VGV to centimeter-level precision, detect obstacles, and compute safe avoidance paths — all at the edge.

  • Navigation & Stability Control

    The system issues steering and speed commands while actively managing the stability of the trailing cart train — maintaining safe, efficient movement even through tight turns.

  • Continuous Safety Monitoring

    A persistent safety layer watches for personnel and equipment in the VGV's path, dynamically adjusting speed and route to ensure safe passage in real time.

 
Aetina x Anantak
 
 

 

SOLUTION ARCHITECTURE

AIB-MX23: The Core Brain for Autonomous VGV Intelligence

Mounted inside the VGV chassis, the Aetina’s DeviceEdge AIB-MX23 Edge AI platform is the robot's onboard brain, powered by NVIDIA Jetson AGX Orin 64GB — its 2048-core Ampere GPU delivers up to 275 TOPS of AI performance, while 64 GB of 256-bit LPDDR5 memory at 204.8 GB/s keeps sensor fusion, SLAM, and navigation running concurrently without contention.

At the foundation is multimodal sensor fusion. The AIB-MX23 integrates 2D LiDAR to define real-time obstacle safety zones, 3D LiDAR to feed a SLAM pipeline for centimeter-level localization, and FRAMOS D455e cameras for visual odometry and depth perception. Wheel encoder feedback anchors the fusion loop, correcting positional drift between scan updates. These fused outputs feed navigation algorithms accelerated by NVIDIA® CUDA® and TensorRT™ on the Jetson AGX Orin's module — computing optimal routes, generating avoidance trajectories, and issuing speed and steering commands within the tight latency that safe warehouse operation demands. A dedicated stability loop runs in parallel, modulating speed and turn radius to keep the trailing cart train moving smoothly at scale. Each AIB-MX23 also has Wi-Fi and 10GbE LAN links to the ground control system, enabling coordinated fleet operation across Anantak's over 200-unit deployments.

Compact, rugged, and rated for −25°C to +80°C operation, the AIB-MX23 is purpose-built for the demands of continuous industrial deployment.

Sensor Inputs

Sensor Function
2D LiDAR Real-time obstacle detection & dynamic safety zones
3D LiDAR Detailed volumetric environmental mapping & localization
FRAMOS d455e Cameras Vision-based path planning & environmental perception
Wheel Encoders Odometry & precise movement feedback
Wi-Fi Fleet management, telemetry & remote monitoring
 
Daxbot
 
 

NVIDIA Jetson: The Powerhouse of Success

NVIDIA Jetson, featuring powerful AI computing and comprehensive software stacks, is an essential engine of autonomous robots. It delivers fast inference and AI/ML libraries, facilitating accelerated robotic development.

Aetina AIB-MX23 Highlights
 
  • Up to 275 TOPS AI computing power
  • Jetson SoM has built-in memory for complex AI workload
  • Custom mechanical case & VGV mounting design
  • Tailored BSP optimization
  • Multi-sensor integration (LiDAR + cameras)
  • Long-term supply & technical support
  • NVIDIA Elite Partner engineering collaboration
NVIDIA Technology Used
 
  • NVIDIA Jetson AGX Orin — Compute module
  • NVIDIA JetPack SDK — Embedded and AI acceleration toolkits and libraries
  • NVIDIA CUDA 10.2 / 11.4 — Parallel compute
  • NVIDIA TensorRT — Inference acceleration
  • NVIDIA Isaac Sim™ — NVIDIA Robotics AI Software Ecosystem
 
Daxbot
 

 

RESULTS

A Deployment-Ready VGV — With Real Impact

After integrating the Aetina AIB-MX23, Anantak's VGV solution delivered measurable operational improvements across every site it was deployed.

  • Rapid Deployment

    Vision-based navigation with no fixed infrastructure requirement means a new facility can be onboarded quickly and without disruption to existing operations.

  • 24/7 Autonomous Operation

    Multiple VGVs run simultaneously on each site, maintaining continuous material flow across all shifts — eliminating the throughput ceiling that comes with manual staffing.

  • Labor Cost Reduction

    Dedicated material transport personnel were no longer needed for repetitive cart-moving routes, with manual handling time for trolley movement reduced by up to 60–80%.

  • Improved Worker Safety

    Replacing manual tugger operation with an AI-guided system led to a substantial reduction in workplace accidents and injuries across all deployment sites.

 
 

 

Ready to Build Your Next Robotics Solution?

The industrial sector is ready for robotics reinvention right now. Aetina's purpose-built edge AI platforms — combined with hands-on engineering support from an NVIDIA Elite Partner like Aetina — give OEMs and manufacturers everything they need to bring compelling, market-ready solutions to life faster than ever before.

 

 

About Anantak

Anantak is a US-based robotics company specializing in autonomous mobile robot solutions for warehouses, distribution centers, and manufacturing facilities. As an innovative OEM, Anantak designs and deploys vision-guided vehicles that bring next-generation industrial automation to market without requiring costly infrastructure modifications.

Their flagship VGV tugger system pulls trains of carts carrying packages through dynamic industrial environments — navigating autonomously alongside workers and equipment using only its onboard sensors and AI. With over 200 units deployed across multiple customer sites, Anantak's platform is proven at scale in real-world industrial conditions.

With Aetina's AIB-MX23 as its computational foundation, Anantak continues to push the boundaries of what autonomous material handling can achieve — and is actively evaluating next-generation Aetina Jetson Thor-based solutions for future product generations.

Website: www.anantak.com
Sales Contact: [email protected]

 
 
Back
close

Top
ALERT TITLE
Ok
/html>