When Coordination Meets Intelligence: Real‑time Policies for Maximizing Throughput in Autonomous Forklift Operations

THE NEED FOR ORCHESTRATED FORKLIFT FLEETS IN A WAREHOUSE

With advancements in artificial intelligence (AI), Internet of Things (IoT) and sensor fusion technologies, such as 3D vision and Light Detection and Ranging (LiDAR) systems, the global autonomous forklift market is projected to grow from $2.73 billion in 2025 to $5.07 billion in 2032 (MarketsandMarkets, 2025).

With the surge in e‑commerce and rising expectations for flexible throughput and fast delivery, intelligent fleet orchestration has emerged as a strategy to synchronize forklift operations with the broader warehouse workflow. By leveraging IoT connectivity and AI‑driven predictive analytics, forklift fleets are evolving from isolated workhorses into coordinated, efficient contributors to end‑to‑end material flow. In particular, real‑time fleet coordination policies can minimize fleet downtime and enhance throughput performance (De Koster et al., 2025).

COMPARING AUTONOMOUS AND AI‑AUGMENTED FLEETS

Intelligent fleets can be categorized by level of intelligence: AI‑augmented, fully autonomous and hybrid.

• AI‑Augmented Human‑Operated Fleets: Many warehouses still rely on human operators driving forklifts, but now those vehicles can be outfitted with IoT sensors and assistive technology. In this model, a central system analyzes data from each forklift and helps guide decisions. It dispatches tasks to drivers and flags maintenance needs or unsafe driving in real time. The forklifts remain human‑controlled, but an AI “brain” optimizes their work. This approach is relatively easy to adopt—existing trucks can be retrofitted with sensors—and it boosts productivity while leveraging human flexibility. Workers feel empowered rather than replaced, which eases the adoption of the technology.
• Fully Autonomous Forklift Fleets: At the cutting edge, some facilities utilize robotic forklifts that navigate and lift loads autonomously, eliminating the need for a human driver. Equipped with sensors, such as LiDAR and cameras, and onboard AI, these robots perceive their surroundings and avoid obstacles (Liu and Wang, 2024). They coordinate via fleet management software that assigns tasks and staggers charging cycles. Autonomous forklifts run 24/7 without a “human fatigue” factor, driving consistent performance. These attributes make them ideal for handling high‑volume repetitive tasks and significantly reducing labor needs. However, implementation requires effort to define warehouse boundaries and adhere to strict safety measures. Autonomous systems can still find unplanned scenarios challenging to address. As their sensors and algorithms improve, autonomous forklifts are becoming more adaptable and safer.
• Hybrid and Emerging Approaches: Many operations use a mix of manual and automated forklifts. For example, a semi‑autonomous “cobot” forklift might handle straightforward driving, while a human could collaborate with a forklift to offer precise placement of pallets in the rack.

CONNECTED FORKLIFT SYSTEMS: IOT TELEMATICS IN ACTION

Forklifts are now IoT‑enabled machines that continuously report data, including location, speed, load weight and equipment status. This real‑time telemetry allows forklifts to “talk” to other systems and even the facility infrastructure. For example, broadcasting a forklift’s position can trigger nearby devices or other vehicles to slow or stop, preventing collisions. Overall, connectivity transforms a fleet into a coordinated network of moving parts, dynamically managing traffic to maintain throughput and avoid congestion on the warehouse floor.

Beyond location tracking, connected forklifts feed operational data into a central fleet management platform. Managers maintain a live dashboard to monitor each forklift, displaying its status, location and needs, eliminating guesswork. If one unit is idle, another forklift can be dispatched to that task immediately, boosting utilization and reducing delays. Connectivity also enables access control: only certified drivers (who use an RFID card or a PIN) can activate a forklift, and the system automatically logs who is operating each machine. These IoT‑driven capabilities improve safety, accountability and efficiency across the fleet. While strategic decisions—such as sizing the number of forklifts, deciding the number of charging points or analyzing the viability of autonomous forklift implementation—require long‑term projection data, IoT data helps make tactical and operational decisions.

FROM PREDICTIVE ANALYTICS TO REAL‑TIME PRESCRIPTIVE POLICIES

The real gain from integration is derived from analyzing the data. Predictive analytics turns telemetry and historical patterns into actionable insights. For example, instead of servicing the forklift in pre‑determined schedules, predictive maintenance can be adopted to prevent long downtimes.

Beyond maintenance, AI‑driven analysis of forklift activity optimizes operations. For example, the AI engine can predict which aisles are frequently congested and offer alternate routes. Such recommendations can prompt layout adjustments or more innovative task scheduling. Utilization data also helps right‑size the fleet, ensuring neither too few trucks (causing delays) nor too many (wasting capital). Machine learning models can even predict peak periods (for example, seasonal order surges) and recommend staging extra forklifts or staff in advance. In short, these capabilities shift fleet management from reactive problem‑solving to proactive optimization.

Click here to read the full article.