Agile3D: Adaptive Contention- and Content-Aware 3D Object Detection for Embedded GPUs
Pengcheng Wang, Zhuoming Liu, Shayok Bagchi, Ran Xu, Saurabh Bagchi, Yin Li, Somali Chaterji. (2025). Agile3D: Adaptive Contention- and Content-Aware 3D Object Detection for Embedded GPUs 2025.
Paper BibTeX Video Poster Demo
Abstract
Efficient 3D perception is critical for autonomous systems like
self-driving vehicles and drones to operate safely in dynamic environments. Accurate 3D object detection from LiDAR data faces
challenges due to the irregularity and high volume of point clouds,
inference latency variability from contention and content dependence, and embedded hardware constraints. Balancing accuracy
and latency under dynamical conditions is crucial, yet existing
frameworks like Chanakya [NeurIPS '23], LiteReconfig [EuroSys
'22], and AdaScale [MLSys ' 19] struggle with the unique demands of
3D detection. We present AGILE3D, the first adaptive 3D system to
integrate a cross-model Multi-branch Execution Framework (MEF)
and a Contention- and Content-Aware RL-based controller (CARL).
CARL dynamically selects the optimal execution branch using five
novel MEF control knobs: encoding format, spatial resolution, spatial encoding, 3D feature extractors, and detection heads. CARL employs a dual-stage optimization strategy: Supervised pretraining for
robust initial learning and Direct Preference Optimization for finetuning without manually tuned rewards, inspired by techniques for
training large language models. Comprehensive evaluations show
that AGILE3D achieves state-of-the-art performance, maintaining
high accuracy across varying hardware contention levels and latency budgets of 100-500 ms. On NVIDIA Orin and Xavier GPUs,
it consistently leads the Pareto frontier, outperforming existing
methods for robust, efficient 3D object detection.
