From the Laboratory to Real-World Application: Evaluating Zero-Shot Scene Interpretation on Edge Devices for Mobile Robotics

• URL: http://arxiv.org/abs/2511.02427v1
• Date: Tue, 04 Nov 2025 09:58:29 GMT
• Title: From the Laboratory to Real-World Application: Evaluating Zero-Shot Scene Interpretation on Edge Devices for Mobile Robotics
• Authors: Nicolas Schuler, Lea Dewald, Nick Baldig, Jürgen Graf,
• Abstract summary: This paper investigates the capabilities of state-of-the-art Visual Language Models (VLMs) for the task of Scene and Action Recognition.<n>The proposed pipeline is evaluated on a diverse dataset consisting of various real-world cityscapes, on-campus and indoor scenarios.<n>The experimental evaluation discusses the potential of these small models on edge devices, with particular emphasis on challenges, weaknesses, inherent model biases and the application of the gained information.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Video Understanding, Scene Interpretation and Commonsense Reasoning are highly challenging tasks enabling the interpretation of visual information, allowing agents to perceive, interact with and make rational decisions in its environment. Large Language Models (LLMs) and Visual Language Models (VLMs) have shown remarkable advancements in these areas in recent years, enabling domain-specific applications as well as zero-shot open vocabulary tasks, combining multiple domains. However, the required computational complexity poses challenges for their application on edge devices and in the context of Mobile Robotics, especially considering the trade-off between accuracy and inference time. In this paper, we investigate the capabilities of state-of-the-art VLMs for the task of Scene Interpretation and Action Recognition, with special regard to small VLMs capable of being deployed to edge devices in the context of Mobile Robotics. The proposed pipeline is evaluated on a diverse dataset consisting of various real-world cityscape, on-campus and indoor scenarios. The experimental evaluation discusses the potential of these small models on edge devices, with particular emphasis on challenges, weaknesses, inherent model biases and the application of the gained information. Supplementary material is provided via the following repository: https://datahub.rz.rptu.de/hstr-csrl-public/publications/scene-interpretation-on-edge-devices/

Related papers

• Seeing Across Views: Benchmarking Spatial Reasoning of Vision-Language Models in Robotic Scenes [33.80107254496374]
  Vision-language models (VLMs) are essential to Embodied AI, enabling robots to perceive, reason, and act in complex environments.<n>Most evaluations of VLMs focus on single-view settings, leaving their ability to integrate multi-view information underexplored.<n>We introduce MV-RoboBench, a benchmark specifically designed to evaluate the multi-view spatial reasoning capabilities of VLMs in robotic manipulation.
  arXiv  Detail & Related papers  (2025-10-22T09:20:09Z)
• Towards Understanding Visual Grounding in Visual Language Models [2.553589584067239]
  Visual grounding refers to the ability of a model to identify a region within some visual input that matches a textual description.<n>We review works across the key areas of research on modern general-purpose vision language models (VLMs)
  arXiv  Detail & Related papers  (2025-09-12T15:33:49Z)
• V-MAGE: A Game Evaluation Framework for Assessing Vision-Centric Capabilities in Multimodal Large Language Models [84.27290155010533]
  We introduce Vision-centric Multiple Abilities Game Evaluation (V-MAGE), a novel game-based evaluation framework.<n>V-MAGE features five distinct video games comprising over 30 carefully constructed evaluation scenarios.<n>We show V-MAGE provides actionable insights for improving the visual and reasoning capabilities of MLLMs in dynamic, interactive settings.
  arXiv  Detail & Related papers  (2025-04-08T15:43:01Z)
• Context-Aware Command Understanding for Tabletop Scenarios [1.7082212774297747]
  This paper presents a novel hybrid algorithm designed to interpret natural human commands in tabletop scenarios. By integrating multiple sources of information, including speech, gestures, and scene context, the system extracts actionable instructions for a robot. We discuss the strengths and limitations of the system, with particular focus on how it handles multimodal command interpretation.
  arXiv  Detail & Related papers  (2024-10-08T20:46:39Z)
• LLARVA: Vision-Action Instruction Tuning Enhances Robot Learning [50.99807031490589]
  We introduce LLARVA, a model trained with a novel instruction tuning method to unify a range of robotic learning tasks, scenarios, and environments. We generate 8.5M image-visual trace pairs from the Open X-Embodiment dataset in order to pre-train our model. Experiments yield strong performance, demonstrating that LLARVA performs well compared to several contemporary baselines.
  arXiv  Detail & Related papers  (2024-06-17T17:55:29Z)
• MOKA: Open-World Robotic Manipulation through Mark-Based Visual Prompting [97.52388851329667]
  We introduce Marking Open-world Keypoint Affordances (MOKA) to solve robotic manipulation tasks specified by free-form language instructions. Central to our approach is a compact point-based representation of affordance, which bridges the VLM's predictions on observed images and the robot's actions in the physical world. We evaluate and analyze MOKA's performance on various table-top manipulation tasks including tool use, deformable body manipulation, and object rearrangement.
  arXiv  Detail & Related papers  (2024-03-05T18:08:45Z)
• Interactive Planning Using Large Language Models for Partially Observable Robotics Tasks [54.60571399091711]
  Large Language Models (LLMs) have achieved impressive results in creating robotic agents for performing open vocabulary tasks. We present an interactive planning technique for partially observable tasks using LLMs.
  arXiv  Detail & Related papers  (2023-12-11T22:54:44Z)
• Chat with the Environment: Interactive Multimodal Perception Using Large Language Models [19.623070762485494]
  Large Language Models (LLMs) have shown remarkable reasoning ability in few-shot robotic planning. Our study demonstrates that LLMs can provide high-level planning and reasoning skills and control interactive robot behavior in a multimodal environment.
  arXiv  Detail & Related papers  (2023-03-14T23:01:27Z)
• A Threefold Review on Deep Semantic Segmentation: Efficiency-oriented, Temporal and Depth-aware design [77.34726150561087]
  We conduct a survey on the most relevant and recent advances in Deep Semantic in the context of vision for autonomous vehicles. Our main objective is to provide a comprehensive discussion on the main methods, advantages, limitations, results and challenges faced from each perspective.
  arXiv  Detail & Related papers  (2023-03-08T01:29:55Z)
• MetaGraspNet: A Large-Scale Benchmark Dataset for Vision-driven Robotic Grasping via Physics-based Metaverse Synthesis [78.26022688167133]
  We present a large-scale benchmark dataset for vision-driven robotic grasping via physics-based metaverse synthesis. The proposed dataset contains 100,000 images and 25 different object types. We also propose a new layout-weighted performance metric alongside the dataset for evaluating object detection and segmentation performance.
  arXiv  Detail & Related papers  (2021-12-29T17:23:24Z)

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.