The paper introduces BEVPIPE, a framework that enables deployment of bird's-eye-view (BEV) perception models—used in autonomous driving to fuse camera and LiDAR data—on portable GPU compute APIs. By partitioning the model into dense subgraphs managed by standard inference runtimes and handling sparse 3D convolutions and geometric scatter operations through external extensions, BEVPIPE achieves a 19.5× speedup while preserving 98.5% of the reference mean average precision. The approach also demonstrates portability across different GPU backends, breaking the current reliance on CUDA-only, PyTorch‑coupled sparse convolution libraries.
arXiv:2608. 14586v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models are becoming a promising paradigm for autonomous driving, but their deployment on existing vehicle platforms remains difficult because they introduce both high inference latency and strong GPU-side resource pressure.
Visual Perception Engine (VPEngine) is a modular framework that enables efficient GPU usage for robotic vision tasks by sharing a foundation model backbone across multiple specialized task heads. It eliminates redundant feature extraction, supports dynamic task prioritization, and achieves up to 3× speedup over sequential execution. The open‑source Python implementation, with ROS2 C++ bindings, delivers real‑time performance (≥50 Hz) on NVIDIA Jetson Orin AGX using TensorRT‑optimized models.
arXiv:2608. 11770v1 Announce Type: cross Abstract: Edge-deployed vision systems in target recognition, surveillance, autonomous vehicles, and drone domains require hierarchical inference pipelines where a detection model identifies objects of interest and downstream classifiers provide fine-grained attribute analysis.
Fast-BEV++ tackles the trade‑off between accuracy and efficiency in vision‑only Bird’s‑Eye‑View perception by adopting two guiding principles: Fast by Algorithm and Deployable by Design. The method decomposes view transformation into a hardware‑oriented Index‑Gather‑Reshape pipeline, removing the need for custom kernels and delivering at least a three‑fold speedup over baseline approaches. On the nuScenes benchmark, Fast‑BEV++ achieves 0.488 NDS while running in real time at over 134 FPS, with depth supervision providing consistent accuracy gains and the architecture enabling seamless deployment on production‑level platforms.
arXiv:2606. 31938v1 Announce Type: cross Abstract: Deploying Vision Transformer (ViT) models on edge platforms remains challenging due to their high computational demands and the architectural heterogeneity of modern hybrid ViT models, which incorporate both fully connected and convolutional layers.
arXiv:2603. 06576v2 Announce Type: replace-cross Abstract: The integration of Large Language Models (LLMs) into autonomous driving has attracted growing interest for their strong reasoning and semantic understanding abilities, which are essential for handling complex decision-making and long-tail scenarios.
arXiv:2609.30459v1 Announce Type: cross Abstract: Perception in robotics and XR fundamentally relies on good state estimation. Visual-inertial odometry (VIO) and Simultaneous Localization and Mapping...
The paper introduces a byte‑constrained cooperative perception framework that balances dense coverage with sparse refinement. Each vehicle sends a highly compressed coarse Bird’s‑Eye‑View (BEV) layer covering the entire map and uses the remaining bandwidth to transmit high‑resolution patches selected by a Task‑Aware Benefit Selector. Experiments on DAIR‑V2X and OPV2V demonstrate that this coverage‑refinement strategy achieves superior accuracy‑payload trade‑offs, reaching 0.60 AP@0.7 with only 1.87 KB per non‑ego agent.
The paper examines how multi‑camera streaming perception systems perform on heterogeneous edge platforms that share resources with other workloads. Using two end‑to‑end pipelines on a single GPU–NPU platform, the authors show that isolated single‑stream evaluations can mislead deployment decisions: while the GPU pipeline appears superior in isolation, GPU‑local contention causes deadline misses that make detections stale and can reverse the preferred placement. The study finds that the NPU pipeline, though less accurate for small and medium objects, nearly matches the GPU on large objects, and that under high contention the best placement shifts from All‑GPU to All‑NPU, achieving a 5.2× improvement in worst‑stream sAP. The authors argue that evaluation metrics should include contention sweeps, deadline‑miss rates, and worst‑stream sAP in addition to mean sAP to capture severe single‑stream degradation.
arXiv:2607. 23910v1 Announce Type: cross Abstract: Cooperative perception through vehicle-to-everything (V2X) communication can overcome the inherent physical limitations of individual autonomous vehicles, such as occlusions and limited sensor range.
arXiv:2607. 02097v1 Announce Type: cross Abstract: Large kernel depthwise convolutions achieve strong performance but suffer from significant degradation as kernel size grows due to irregular memory access from gather-based computation; while Large Kernel Acceleration (LKA) helps on small feature maps, it becomes counterproductive on large feature maps, even slower than non-accelerated implementations.
arXiv:2607. 10942v1 Announce Type: cross Abstract: Physical AI systems, such as autonomous vehicles and intelligent machines, require transformer-based perception models that satisfy stringent edge latency and energy constraints.