Semantic-Aware Particle Filter for Reliable Vineyard Robot Localisation
This addresses localization for vineyard robots, an incremental improvement in agricultural robotics.
The paper tackles the problem of mobile robot localization in vineyards where LiDAR-based methods fail due to repetitive row geometry, by proposing a semantic particle filter that incorporates object-level detections and semantic walls. The result is reliable localization within correct rows, recovery from deviations, and outperformance of vision-based SLAM methods like RTAB-Map in real vineyard experiments.
Accurate localisation is critical for mobile robots in structured outdoor environments, yet LiDAR-based methods often fail in vineyards due to repetitive row geometry and perceptual aliasing. We propose a semantic particle filter that incorporates stable object-level detections, specifically vine trunks and support poles into the likelihood estimation process. Detected landmarks are projected into a birds eye view and fused with LiDAR scans to generate semantic observations. A key innovation is the use of semantic walls, which connect adjacent landmarks into pseudo-structural constraints that mitigate row aliasing. To maintain global consistency in headland regions where semantics are sparse, we introduce a noisy GPS prior that adaptively supports the filter. Experiments in a real vineyard demonstrate that our approach maintains localisation within the correct row, recovers from deviations where AMCL fails, and outperforms vision-based SLAM methods such as RTAB-Map.