The concept of Industry 4.0 is driving the popularization of private 5G networks, which are also increasingly used in manufacturing and logistics due to the lower cost of spectrum. Therefore, a large number of use cases in Industry 4.0 around smart manufacturing, logistics, warehouse automation, energy and utilities, smart grid, defect detection, etc. account for more than 60% of private 5G use cases.

It is estimated that by 2025, the warehouse automation market will reach 27 billion US dollars, with more than 4 million robot operations and about 50,000 automated distribution warehouses. Therefore, there will be a huge opportunity for autonomous mobile robots in our industry ecosystem.

With its ultra-reliable low-latency communication and high-bandwidth capabilities, 5G drives distributed computing efficiency and sets a new paradigm for autonomous mobile robots.

Edge computing is becoming more and more popular, which is a very good cycle. This will reduce the cost of autonomous mobile robots because the computation is closer to the data sources that autonomous mobile robots generate. Meanwhile, even autonomous mobile robots are becoming more affordable as warehouses plan to deploy hundreds of them.

Some tasks of an automated warehouse can be located on autonomous mobile robots, while some tasks can be offloaded to edge servers. In some cases, some tasks can be offloaded to the data center or cloud.

Some of the tasks that can be performed on autonomous mobile robots include sensor ingestion, path planning and localization, obstacle avoidance, motor control, functional safety, and navigation, while tasks that can be offloaded to edge servers include remote jamming, fleet management, mission management, battery management, Traffic management and analysis.

In order to enable such computational and artificial intelligence capabilities in autonomous mobile robots, they do need to be based on latency and other requirements. These workloads are then logically partitioned across these various locations to deliver the best efficiency and best business value to the enterprise.

Specific use cases for autonomous mobile robots

The first is Edge Insights for Autonomous Mobile Robots, an optimized software stack on an autonomous mobile robot platform with various building blocks, such as simultaneous localization and mapping, for truly enabling and controlling autonomous mobile robots.

The second use case is Intel's Open Source Suite, or AI, computer vision, and deep learning inference toolkit. The kit accelerates visual inference from images captured by cameras on the robot. This is critical for autonomous mobile robot navigation on the factory floor, but also to ensure that autonomous mobile robots operate safely and coexist with humans on the factory floor.

The final use case is intelligent edge products for managing and deploying autonomous mobile robot applications.

Summarize

Warehouse automation can manage autonomous mobile robots from different suppliers, use edge computing to introduce extended AI capabilities for autonomous mobile robots, enable digital twins for predictive maintenance and operational optimization, and create a safe environment for autonomous mobile robots and human collaboration environment of.