End-to-End LiDAR optimization for 3D point cloud registration
This work addresses a domain-specific problem for autonomous perception and robotics by introducing an incremental improvement over fixed-parameter baselines.
The paper tackles the problem of suboptimal LiDAR data collection for 3D point cloud registration by proposing an adaptive sensing framework that jointly optimizes LiDAR acquisition and registration hyperparameters, resulting in improved registration accuracy and efficiency as demonstrated in CARLA simulations.
LiDAR sensors are a key modality for 3D perception, yet they are typically designed independently of downstream tasks such as point cloud registration. Conventional registration operates on pre-acquired datasets with fixed LiDAR configurations, leading to suboptimal data collection and significant computational overhead for sampling, noise filtering, and parameter tuning. In this work, we propose an adaptive LiDAR sensing framework that dynamically adjusts sensor parameters, jointly optimizing LiDAR acquisition and registration hyperparameters. By integrating registration feedback into the sensing loop, our approach optimally balances point density, noise, and sparsity, improving registration accuracy and efficiency. Evaluations in the CARLA simulation demonstrate that our method outperforms fixed-parameter baselines while retaining generalization abilities, highlighting the potential of adaptive LiDAR for autonomous perception and robotic applications.