Deploying Autonomous Mobile Robots with AI and IEI

Autonomous Mobile Robots

The Revolution of AGV

Before the COVID-19 pandemic, autonomous mobile robots (AMR) and autonomic guided vehicles (AGV) were changing the landscape across many industries – including healthcare, industrial automation, warehousing, logistics and many others. However, in the post-pandemic era, AMR and AGV can help deal with staffing shortages and the need for social distancing.

Autonomous Mobile Robots (AMR) use on-board sensors and processors to autonomously move materials without the need for physical guides or markers. The AMR’s main components include a controller, computing unit, battery, motors, sensors and camera. Automated Guided Vehicles (AGV) can be pre-programmed to transport goods in a warehousing & manufacturing environments. The AGV’s main components include traction motor & batteries, industrial PC (or on-board controller) and payload interface.

The greatest advantage of AMR over AGV is that AMR provides alternative navigation options. An AMR navigates using a predefined map and plans its own routes to the destination. It can detect obstacles similar to an AGV, but it is more intelligent because they can avoid obstacles by navigating around them. Therefore, an AMR robot is considered more flexible because it can change its path dynamically and with less effort. An AMR robot is perceived to be much more costly compared to an AGV, but in reality, the AMR can be more cost effective due to its flexibility and ease of set up.

AMR vs AGV – what is the difference?

  AMR AGV
Navigation Using technology such as LiDAR sensors & simultaneous localisation and mapping (SLAM), an AMR will determine the best route between waypoints

Traditionally guided by magnetic strips or wires installed on or under the floor

Responsiveness

AMR will automatically sense and avoid obstacles and blocked paths to find the best route to its next waypoint

AGV’s are unable to adapt to changes in the environment or obstacles left in their path

Flexibility

Can easily be remapped and taught new destinations and goals

New tracks and infrastructure need to be installed

Deployment

This can vary, but efficient AMR’s can be unboxed and put to work in less than 15 minutes

Requires installation of navigation guides, sometimes requiring substantial facility renovation

Expandability

Typically, AMR’s are managed on a fleet software package

Need to add new tracks and new units to the infrastructure

Accessibility

AMR waypoints can be set up and reconfigured by the local workforce with training

AGV’s typically require experts to set up or reconfigure the system


AMR with Artificial Intelligence

Artificial intelligence (AI) makes it possible for machines to learn from experience, adjust to new inputs and perform human-like tasks. AI will become an integral part of setting up and using AMRs, simplifying their deployment process and improving their workflow. Some AMRs are taking those ‘smarts’ to the next level with artificial intelligence coupled with strategically placed cameras that function as extended robot sensors. With AI, AMRs can learn to adapt their appropriate behaviour even before they enter an area. This means they can avoid high-traffic areas during specific times, including when materials are regularly delivered by fork truck or other vehicles, or when large numbers of workers are present during breaks or shift changes.

AMR with Artificial Intelligence
ai ready solution pc
Intel Distribution of OpenVINO toolkit pc

AMR/AGV Controller

Controller 01

Wide Operating Temperature

AMR’s can endure up to 60°C without system crash and continue to deliver consistent performance even with the CPU running steadily above its base frequency.

Controller 02

High Humidity Resistance

In extreme use cases, humidity can be a key factor that impacts product functionality. Therefore, pre-testing under exacting conditions will ensure the design can operate with humid or moisture rich environments.

Controller 03

Durable and Silent

AMR’s generally adopts fanless systems that typically integrates passive cooling fins. They can reduce the use of consumables, boost product reliability and extend life availability.

Controller 04

Rich I/O Interfaces

AMR devices need powerful embedded systems with multiple I/O interfaces to connect with cameras, sensors, displays, and other end devices. Therefore, AMR typically utilise sensors and powerful embedded PC systems to understand their operating environments.


DRPC-230-ULT5

DRPC 230 AMR

The DRPC-230-ULT5 could endure up to 70°C operating temperature to deliver constant performance with CPU running steadily above its base frequency. The model with expansion layer provides rich I/O and PCIe x4 signal to support add-ons such as IEI acceleration cards (Mustang-V100-MX8 or Mustang-V100-MX4), opening the door to faster deployments of AI inference systems. The DRPC-230-ULT5 can connect to camera for visual recognition. It enables machine learning by using a variety of training models to simulate and infer the status or appearance of objects. For example, the inference system with the video analysis model can perform obstacle analysis for AMR.

DRPC-130-AL

DRPC 130 AMR 1

uIBX-250-BW

UIBX 250 AMR

Applications

Hospital

  • Hospital material transport
  • Reduce the heavy workload of nursing staffs
  • Reduce the risk of cross-infection

Factory

  • Handle large amounts of materials
  • Pick up goods
  • Improve production efficiency and assembly quality

Distribution Center

  • Carry shelves
  • Drive the flow of various goods
  • Create changeable storage spaces

Office

  • Designate mailed goods, letters and garbage
  • Reduce the use of manpower

E-Commerce

  • Reduce the labor intensity of workers
  • Important tool for moving goods
  • Important tool for sorting goods

Benefits of AMR

Benefits of AMR 01
Reduced Labor Workloads
Benefits of AMR 02
Increased Safety
Benefits of AMR 03
Reliable Workforce

Product Selection

DRPC 230 ULT5 1
DRPC-230-ULT5

DRPC-230 is an ultimate gateway; it is applicable in various fields. It works for production line, it’s suitable for energy management and smart building, and DRPC-230 also could play a role in AI.

DRPC 130 AL 1
DRPC-130-AL

DRPC-130-AL Fanless DIN-Rail Embedded System product features: 1.Intel Atom™ x5-E3930 1.3GHz (up to 1.8 GHz) 2.DDR3L 1.35V SO-DIMM supported 3.Serial, CAN bus and digital I/O interface.

MX8
Mustang-V100-MX8

Mustang-V100-MX8 – Vision Accelerator Card with Intel Movidius VPU. Computing Accelerator Card with 8 x Movidius Myriad X MA2485 VPU, PCIe gen2 x4 interface.

uIBX 250 BW 1
uIBX-250-BW

uIBX-250-BW compact size box pc product features: Fanless system with Intel® Celeron N3160 processor, Dual display, Two RS-232/422/485, Full-size PCIe Mini slot for expansion, Four USB 3.0 ports, Two GbE LAN ports.

Demo Kit Request

If you want to know more about the products or need a sample for testing, please fill out the request form below.

Thank you.

BVM Design and Manufacturing Services: The manufacturer behind the solutions you know

When a standard embedded design won’t suffice for what you need, you can always turn to BVM for help and use our custom design and manufacturing services.