An Analysis and Comparison of Free-Space Detection Approaches and Their Evaluation for Heavy-Duty Vehicles

The detection of free space plays a fundamental role in ensuring the safe and efficient operation of heavy-duty vehicles, particularly in environments where the available area to maneuver is severely constrained, such as construction zones, rest areas, or loading docks. An accurate estimation of free space is essential to prevent collisions, maintaining operational continuity and minimizing vehicle downtime. As observed from the reviewed literature, despite the large number of proposed free-space detection methods, there is no concise and established definition about how free space should be determined, represented, and inferred, nor agreement on the semantic classes to be considered. This heterogeneity complicates systematic comparison and benchmarking across approaches. This paper presents a structured survey and methodological analysis of recent free-space detection and semantic segmentation approaches across automotive LiDAR-, camera-, and radar-based perception systems, as well as multimodal sensor fusion. The review spans classical geometric and occupancy-based techniques together with deep-learning methods, along with datasets commonly used for evaluation. The main contributions are (i) a structured taxonomy and comparative analysis of existing free-space definitions and detection strategies, categorized by their assumptions, representation forms, and sensing modalities; and (ii) a unified and application-independent definition of free space together with the required semantic classes. These contributions aim to provide a consistent conceptual foundation to support future research and to aid the systematic evaluation of upcoming free-space detection systems.