🤖 AI Summary
This study addresses the challenges of robust 6D pose estimation and multi-object tracking for industrial mobile robots operating in dynamic production environments, where reliance on real-world data, sensitivity to perceptual noise, and spatiotemporal inconsistencies often degrade performance. To overcome these limitations, the authors propose a ROS 2-based LiDAR perception framework that innovatively integrates a transform-equivariant 3D detection model trained on synthetic data with a center-point-based multi-object tracking algorithm. This approach significantly enhances system robustness and generalization without requiring extensive real-world annotations. Evaluated across 72 diverse scenarios, the method achieves an IoU of 62.6% for standalone pose estimation, which improves to 83.12% when combined with tracking, while attaining a high-order tracking accuracy of 91.12%.
📝 Abstract
Adaptive robots in dynamic production environments require robust perception capabilities, including 6D pose estimation and multi-object tracking. To address limitations in real-world data dependency, noise robustness, and spatiotemporal consistency, a LiDAR framework based on the Robot Operating System integrating a synthetic-data-trained Transformation-Equivariant 3D Detection with multi-object-tracking leveraging center poses is proposed. Validated across 72 scenarios with motion capture technology, overall results yield an Intersection over Union of 62.6% for standalone pose estimation, rising to 83.12% with multi-object-tracking integration. Our LiDAR-based framework achieves 91.12% of Higher Order Tracking Accuracy, advancing robustness and versatility of LiDAR-based perception systems for industrial mobile manipulators.