vAccSOL: Efficient and Transparent AI Vision Offloading for Mobile Robots

• URL: http://arxiv.org/abs/2603.16685v1
• Date: Tue, 17 Mar 2026 15:44:44 GMT
• Title: vAccSOL: Efficient and Transparent AI Vision Offloading for Mobile Robots
• Abstract summary: We present vAccSOL, a framework for efficient and transparent execution of AI-based vision workloads across robotic and edge platforms.<n>We evaluate vAccSOL on a real-world testbed with a commercial quadruped robot and twelve deep learning models.<n>With edge offloading, vAccSOL reduces robot-side power consumption by up to 80% and edge-side power by up to 60%, while increasing vision pipeline frame rate by up to 24x.
• Score: 1.784741753796716
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Mobile robots are increasingly deployed for inspection, patrol, and search-and-rescue operations, relying on computer vision for perception, navigation, and autonomous decision-making. However, executing modern vision workloads onboard is challenging due to limited compute resources and strict energy constraints. While some platforms include embedded accelerators, these are typically tied to proprietary software stacks, leaving user-defined workloads to run on resource-constrained companion computers. We present vAccSOL, a framework for efficient and transparent execution of AI-based vision workloads across heterogeneous robotic and edge platforms. vAccSOL integrates two components: SOL, a neural network compiler that generates optimized inference libraries with minimal runtime dependencies, and vAccel, a lightweight execution framework that transparently dispatches inference locally on the robot or to nearby edge infrastructure. This combination enables hardware-optimized inference and flexible execution placement without requiring modifications to robot applications. We evaluate vAccSOL on a real-world testbed with a commercial quadruped robot and twelve deep learning models covering image classification, video classification, and semantic segmentation. Compared to a PyTorch compiler baseline, SOL achieves comparable or better inference performance. With edge offloading, vAccSOL reduces robot-side power consumption by up to 80% and edge-side power by up to 60% compared to PyTorch, while increasing vision pipeline frame rate by up to 24x, extending the operating lifetime of battery-powered robots.

Related papers

• CR-Solver: GPU-Accelerated Kinematics Solver for Tendon-driven Continuum Robots [18.541022260976348]
  We present a two-stage, optimization-based solver for the motion generation of tendon-driven continuum robots.<n>Our method unifies inverse kinematics, path following, and trajectory planning within a single constrained nonlinear optimization framework.<n>We validate our approach on three tasks, demonstrating significant speedups over traditional CPU-based solvers while achieving a consistently high success rate above 95% and millimeter-level accuracy.
  arXiv  Detail & Related papers  (2026-07-13T10:02:36Z)
• Multi-Agent Robotic Control with Onboard Vision-Language Models [38.78172334790013]
  Vision Language Models (VLMs) and Vision Language Action (VLA) models have shown promise in robotic control.<n>They face significant challenges regarding explainability, generalization, and compute requirements.<n>This paper presents a Multi-Agent System (MAS) architecture that addresses these limitations by deploying specialized agents on onboard hardware.
  arXiv  Detail & Related papers  (2026-07-08T13:37:31Z)
• ORICF -- Open Robotics Inference and Control Framework [0.0]
  The Open Robotics Inference and Control Framework (ORICF) is a modular, declarative, and model-agnostic platform for composing multimodal robotic inference pipelines.<n>The framework also supports edge offloading, i.e., executing inference on nearby external computers instead of onboard the robot.
  arXiv  Detail & Related papers  (2026-05-10T17:08:16Z)
• Web-Gewu: A Browser-Based Interactive Playground for Robot Reinforcement Learning [3.337549990679896]
  Web-Gewu is an interactive robotics education platform built on a cloud-edge-client collaborative architecture.<n>The system offloads all physics simulation and reinforcement learning training to the edge node.<n>Web-Gewu provides a highly scalable, out-of-the-box, and barrier-free teaching infrastructure for embodied intelligence.
  arXiv  Detail & Related papers  (2026-04-18T16:08:48Z)
• Robotic Grasping and Placement Controlled by EEG-Based Hybrid Visual and Motor Imagery [64.82869118243723]
  We present a framework that integrates EEG-based visual and motor imagery (VI/MI) with robotic control to enable real-time, intention-driven grasping and placement.<n>Motivated by the promise of BCI-driven robotics, this system bridges neural signals with physical control by deploying offline-pretrained decoders in a zero-shot manner.
  arXiv  Detail & Related papers  (2026-03-03T17:41:42Z)
• LEVIO: Lightweight Embedded Visual Inertial Odometry for Resource-Constrained Devices [18.91672527573445]
  This work presents LEVIO, a fully featured VIO pipeline optimized for ultra-low-power compute platforms.<n>LEVIO incorporates established VIO components such as Oriented FAST and Rotated BRIEF (ORB) feature tracking and bundle adjustment.<n>The paper proposes and details the algorithmic design choices and the hardware-software co-optimization approach, and presents real-time performance on resource-constrained hardware.
  arXiv  Detail & Related papers  (2026-02-03T09:20:57Z)
• OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agent [58.07447442040785]
  We introduce OS-Symphony, a holistic framework that comprises an Orchestrator coordinating two key innovations for robust automation.<n>Results demonstrate that OS-Symphony delivers substantial performance gains across varying model scales.
  arXiv  Detail & Related papers  (2026-01-12T17:55:51Z)
• Lite VLA: Efficient Vision-Language-Action Control on CPU-Bound Edge Robots [0.6119773373677944]
  This work demonstrates the feasibility of deploying small Vision-Language Models (VLMs) on mobile robots to achieve real-time scene understanding and reasoning under strict computational constraints.<n>Unlike prior approaches that separate perception from mobility, the proposed framework enables simultaneous movement and reasoning in dynamic environments using only on-board hardware.
  arXiv  Detail & Related papers  (2025-11-07T17:49:14Z)
• Ark: An Open-source Python-based Framework for Robot Learning [20.131425969692256]
  ARK is an open-source, Python-first robotics framework designed to close that gap.<n>ARK presents a Gym-style environment interface that allows users to collect data, preprocess it, and train policies.<n>ARK ships with reusable modules for control, SLAM, motion planning, system identification, and visualization.
  arXiv  Detail & Related papers  (2025-06-24T20:23:39Z)
• SparseGrasp: Robotic Grasping via 3D Semantic Gaussian Splatting from Sparse Multi-View RGB Images [125.66499135980344]
  We propose SparseGrasp, a novel open-vocabulary robotic grasping system.<n>SparseGrasp operates efficiently with sparse-view RGB images and handles scene updates fastly.<n>We show that SparseGrasp significantly outperforms state-of-the-art methods in terms of both speed and adaptability.
  arXiv  Detail & Related papers  (2024-12-03T03:56:01Z)
• DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution [114.61347672265076]
  Development of MLLMs for real-world robots is challenging due to the typically limited computation and memory capacities available on robotic platforms. We propose a Dynamic Early-Exit Framework for Robotic Vision-Language-Action Model (DeeR) that automatically adjusts the size of the activated MLLM. DeeR demonstrates significant reductions in computational costs of LLM by 5.2-6.5x and GPU memory of LLM by 2-6x without compromising performance.
  arXiv  Detail & Related papers  (2024-11-04T18:26:08Z)
• Accelerating AI and Computer Vision for Satellite Pose Estimation on the Intel Myriad X Embedded SoC [3.829322478948514]
  This paper develops a hybrid AI/CV system on Intel's Movidius Myriad X for initializing and tracking the satellite's pose in space missions. The proposed single-chip, robust-estimation, and real-time solution delivers a throughput of up to 5 FPS for 1-MegaPixel RGB images within a limited power envelope of 2W.
  arXiv  Detail & Related papers  (2024-09-19T17:50:50Z)
• RoboScript: Code Generation for Free-Form Manipulation Tasks across Real and Simulation [77.41969287400977]
  This paper presents textbfRobotScript, a platform for a deployable robot manipulation pipeline powered by code generation. We also present a benchmark for a code generation benchmark for robot manipulation tasks in free-form natural language. We demonstrate the adaptability of our code generation framework across multiple robot embodiments, including the Franka and UR5 robot arms.
  arXiv  Detail & Related papers  (2024-02-22T15:12:00Z)
• Fast GraspNeXt: A Fast Self-Attention Neural Network Architecture for Multi-task Learning in Computer Vision Tasks for Robotic Grasping on the Edge [80.88063189896718]
  High architectural and computational complexity can result in poor suitability for deployment on embedded devices. Fast GraspNeXt is a fast self-attention neural network architecture tailored for embedded multi-task learning in computer vision tasks for robotic grasping.
  arXiv  Detail & Related papers  (2023-04-21T18:07:14Z)
• Deep Learning for Real Time Satellite Pose Estimation on Low Power Edge TPU [58.720142291102135]
  In this paper we propose a pose estimation software exploiting neural network architectures. We show how low power machine learning accelerators could enable Artificial Intelligence exploitation in space.
  arXiv  Detail & Related papers  (2022-04-07T08:53:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.