# LIDAR and Position-Aided mmWave Beam Selection with Non-local CNNs and Curriculum Training

arXiv: https://arxiv.org/abs/2104.14579 · HTML: https://mlsanity.com/paper/2104.14579/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 37 references that are in the map.
- First posted on arXiv 29 Apr 2021.

## Builds on (most cited first, 14 of 14)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Contrastive Representation Distillation](https://mlsanity.com/paper/1910.10699/) (2019)
- [On The Power of Curriculum Learning in Training Deep Networks](https://mlsanity.com/paper/1904.03626/) (2019)
- [Deep Learning for mmWave Beam and Blockage Prediction Using Sub-6GHz Channels](https://mlsanity.com/paper/1910.02900/) (2019)
- [Millimeter Wave Base Stations with Cameras: Vision Aided Beam and Blockage Prediction](https://mlsanity.com/paper/1911.06255/) (2019)
- [5G New Radio: Unveiling the Essentials of the Next Generation Wireless Access Technology](https://mlsanity.com/paper/1806.06898/) (2018)
- [LIDAR Data for Deep Learning-Based mmWave Beam-Selection](https://mlsanity.com/paper/1908.07488/) (2019)
- [Federated mmWave Beam Selection Utilizing LIDAR Data](https://mlsanity.com/paper/2102.02802/) (2021)
- [3D Scene Based Beam Selection for mmWave Communications](https://mlsanity.com/paper/1911.08409/) (2019)
- [Inertial Sensor Aided mmWave Beam Tracking to Support Cooperative Autonomous Driving](https://mlsanity.com/paper/1903.11849/) (2019)
- [Vision-Aided Radio: User Identity Match in Radio and Video Domains Using Machine Learning](https://mlsanity.com/paper/2010.07219/) (2020)
- [Beam Alignment for Millimetre Wave Links with Motion Prediction of Autonomous Vehicles](https://mlsanity.com/paper/1702.04264/) (2017)

## Built on by (most cited first, 6 of 6)

- [DeepSense 6G: A Large-Scale Real-World Multi-Modal Sensing and Communication Dataset](https://mlsanity.com/paper/2211.09769/) (2022)
- [Multi-Modality Sensing in mmWave Beamforming for Connected Vehicles Using Deep Learning](https://mlsanity.com/paper/2504.06173/) (2025)
- [Overhead-Free Blockage Detection and Precoding Through Physics-Based Graph Neural Networks: LIDAR Data Meets Ray Tracing](https://mlsanity.com/paper/2209.07350/) (2022)
- [Beam Training in mmWave Vehicular Systems: Machine Learning for Decoupling Beam Selection](https://mlsanity.com/paper/2404.10936/) (2024)
- [AirNet: Neural Network Transmission over the Air](https://mlsanity.com/paper/2105.11166/) (2021)
- [Resolving Multi-Target Association in OFDM-based ISAC via Vision-aided Multi-Modal Learning](https://mlsanity.com/paper/2606.22195/) (2026)

## Abstract (arXiv)

Efficient millimeter wave (mmWave) beam selection in vehicle-to-infrastructure (V2I) communication is a crucial yet challenging task due to the narrow mmWave beamwidth and high user mobility. To reduce the search overhead of iterative beam discovery procedures, contextual information from light detection and ranging (LIDAR) sensors mounted on vehicles has been leveraged by data-driven methods to produce useful side information. In this paper, we propose a lightweight neural network (NN) architecture along with the corresponding LIDAR preprocessing, which significantly outperforms previous works. Our solution comprises multiple novelties that improve both the convergence speed and the final accuracy of the model. In particular, we define a novel loss function inspired by the knowledge distillation idea, introduce a curriculum training approach exploiting line-of-sight (LOS)/non-line-of-sight (NLOS) information, and we propose a non-local attention module to improve the performance for the more challenging NLOS cases. Simulation results on benchmark datasets show that, utilizing solely LIDAR data and the receiver position, our NN-based beam selection scheme can achieve 79.9% throughput of an exhaustive beam sweeping approach without any beam search overhead and 95% by searching among as few as 6 beams. In a typical mmWave V2I scenario, our proposed method considerably reduces the beam search time required to achieve a desired throughput, in comparison with the inverse fingerprinting and hierarchical beam selection schemes.