1. Principles

To understand the principles of how autonomous haulage works, and can succeed in underground settings, it’s essential to explore the core principles of perception, planning, and control.

1. Perception

Perception refers to the system’s ability to accurately interpret its surroundings in real time. In an autonomous haulage system, perception involves gathering and processing data from a variety of sensors to construct a detailed, real-time understanding of the environment. The goal is to detect and recognize obstacles, assess road conditions, and identify other vehicles, workers, and equipment.

Key aspects of perception in autonomous systems include:

• Environmental Mapping: The ability to create a 3D map of the vehicle’s surroundings using sensors such as LiDAR, radar, and cameras.
• Object Detection and Classification: Identifying and distinguishing between various objects in the environment, such as other vehicles, personnel, equipment, and geological features like walls or debris.
• Dynamic Tracking: Monitoring moving objects, predicting their future positions, and updating the system’s understanding of the environment in real time.
• Condition Awareness: Recognizing conditions such as slippery surfaces, rockfalls, or obstructions that may affect vehicle performance or safety.

In underground environments, perception is complicated by poor visibility, confined spaces, dust, and debris. To address this, autonomous systems must be equipped with robust, multi-sensor capabilities that can function in low-light or dusty environments.

1. Planning

Planning involves the decision-making processes that allow the system to determine the best course of action based on the information provided by the perception layer. Planning is concerned with both path planning (how to navigate from point A to point B) and motion planning (how to execute the necessary movements safely and efficiently).

Key elements of planning in an autonomous system include:

• Path Optimization: Selecting the safest and most efficient route for the vehicle to follow. This involves factoring in terrain, obstacles, and any dynamic changes in the environment.
• Obstacle Avoidance: Reacting to unexpected obstacles by recalculating the path or adjusting the vehicle’s movement in real-time to avoid collisions.
• Traffic Management: In underground mining, multiple autonomous and human-operated vehicles often share the same space. The planning system must manage this traffic to avoid bottlenecks, collisions, or inefficiencies.