HyperLiDAR: Adaptive Post-Deployment LiDAR Segmentation via Hyperdimensional Computing

TL;DR

HyperLiDAR is a lightweight, hyperdimensional computing-based framework for on-device post-deployment LiDAR segmentation that adapts efficiently to environmental changes with significant speedups.

Contribution

It introduces HyperLiDAR, the first HDC-based LiDAR segmentation method optimized for real-time on-device adaptation in resource-constrained environments.

Findings

HyperLiDAR achieves up to 13.8x faster retraining speeds.

It outperforms or matches state-of-the-art methods in adaptation performance.

Extensive evaluations on multiple benchmarks and devices validate its effectiveness.

Abstract

LiDAR semantic segmentation plays a pivotal role in 3D scene understanding for edge applications such as autonomous driving. However, significant challenges remain for real-world deployments, particularly for on-device post-deployment adaptation. Real-world environments can shift as the system navigates through different locations, leading to substantial performance degradation without effective and timely model adaptation. Furthermore, edge systems operate under strict computational and energy constraints, making it infeasible to adapt conventional segmentation models (based on large neural networks) directly on-device. To address the above challenges, we introduce HyperLiDAR, the first lightweight, post-deployment LiDAR segmentation framework based on Hyperdimensional Computing (HDC). The design of HyperLiDAR fully leverages the fast learning and high efficiency of HDC, inspired by how the human brain processes information. To further improve the adaptation efficiency, we identify the high data volume per scan as a key bottleneck and introduce a buffer selection strategy that focuses learning on the most informative points. We conduct extensive evaluations on two state-of-the-art LiDAR segmentation benchmarks and two representative devices. Our results show that HyperLiDAR outperforms or achieves comparable adaptation performance to state-of-the-art segmentation methods, while achieving up to a 13.8x speedup in retraining.