Designing Multi-Robot Ground Video Sensemaking with Public Safety Professionals
Not on the map. Why?
Abstract (arXiv)
Videos from fleets of ground robots can advance public safety by providing scalable situational awareness and reducing professionals' burden. Yet little is known about how to design and integrate multi-robot videos into public safety workflows. Collaborating with six police agencies, we examined how such videos could be made practical. In Study 1, we presented the first testbed for multi-robot ground video sensemaking. The testbed includes 38 events-of-interest (EoI) relevant to public safety, a dataset of 20 robot patrol videos (10 day/night pairs) covering EoI types, and 6 design requirements aimed at improving current video sensemaking practices. In Study 2, we built MRVS, a tool that augments multi-robot patrol video streams with a prompt-engineered video understanding model. Participants reported reduced manual workload and greater confidence with LLM-based explanations, while noting concerns about false alarms and privacy. We conclude with implications for designing future multi-robot video sensemaking tools.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 49 of its 157 references that are in the map. First posted on arXiv 9 Feb 2026.
Builds on
49 of 157 references.
References · 49
- 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
- 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
- 2022Language Models (Mostly) Know What They Knowcited by 1,783
- 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelcited by 1,259
- 2025SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Featurescited by 1,127
- 2024VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMscited by 749
- 2022Teaching Models to Express Their Uncertainty in Wordscited by 731
- 2024LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understandingcited by 644
- 2018Real-world Anomaly Detection in Surveillance Videoscited by 570
- 2024YOLOv10: Real-Time End-to-End Object Detectioncited by 508
- 2024LVBench: An Extreme Long Video Understanding Benchmarkcited by 402
- 2017Future Frame Prediction for Anomaly Detection -- A New Baselinecited by 391
37 more
- 2016Learning Temporal Regularity in Video Sequencescited by 254
- 2020Questioning the AI: Informing Design Practices for Explainable AI User Experiencescited by 251
- 2020Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervisioncited by 235
- 2023Better Zero-Shot Reasoning with Role-Play Promptingcited by 220
- 2022Extracting Latent Steering Vectors from Pretrained Language Modelscited by 217
- 2020NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localizationcited by 151
- 2023Deep OC-SORT: Multi-Pedestrian Tracking by Adaptive Re-Identificationcited by 130
- 2021Expanding Explainability: Towards Social Transparency in AI systemscited by 124
- 2019Street Scene: A new dataset and evaluation protocol for video anomaly detectioncited by 89
- 2020A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Videocited by 85
- 2023Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMscited by 82
- 2020Human Factors in Model Interpretability: Industry Practices, Challenges, and Needscited by 73
- 2018Fairness and Accountability Design Needs for Algorithmic Support in High-Stakes Public Sector Decision-Makingcited by 66
- 2024Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLMcited by 63
- 2019Multi-timescale Trajectory Prediction for Abnormal Human Activity Detectioncited by 59
- 2024Advancing Video Anomaly Detection: A Concise Review and a New Datasetcited by 48
- 2020Robust Unsupervised Video Anomaly Detection by Multi-Path Frame Predictioncited by 42
- 2022Going Beyond XAI: A Systematic Survey for Explanation-Guided Learningcited by 35
- 2016Procedural Generation of Videos to Train Deep Action Recognition Networkscited by 31
- 2022Aligning Eyes between Humans and Deep Neural Network through Interactive Attention Alignmentcited by 27
- 2024ActionAtlas: A VideoQA Benchmark for Domain-specialized Action Recognitioncited by 21
- 2025UCF-Crime-DVS: A Novel Event-Based Dataset for Video Anomaly Detection with Spiking Neural Networkscited by 18
- 2024Making Short-Form Videos Accessible with Hierarchical Video Summariescited by 14
- 2024Are We Asking the Right Questions?: Designing for Community Stakeholders' Interactions with AI in Policingcited by 10
- 2024As an AI Language Model, "Yes I Would Recommend Calling the Police": Norm Inconsistency in LLM Decision-Makingcited by 10
- 2025AI Mismatches: Identifying Potential Algorithmic Harms Before AI Developmentcited by 10
- 2025Sherlock: Towards Multi-scene Video Abnormal Event Extraction and Localization via a Global-local Spatial-sensitive LLMcited by 10
- 2025Attention Hijackers: Detect and Disentangle Attention Hijacking in LVLMs for Hallucination Mitigationcited by 9
- 2023Video2Action: Reducing Human Interactions in Action Annotation of App Tutorial Videoscited by 8
- 2025VideoDiff: Human-AI Video Co-Creation with Alternativescited by 8
- 2020Local Anomaly Detection in Videos using Object-Centric Adversarial Learningcited by 7
- 2022CrossA11y: Identifying Video Accessibility Issues via Cross-modal Groundingcited by 6
- 2024Studying Up Public Sector AI: How Networks of Power Relations Shape Agency Decisions Around AI Design and Usecited by 6
- 2025CoKnowledge: Supporting Assimilation of Time-synced Collective Knowledge in Online Science Videoscited by 4
- 2022Discovering the Hidden Facts of User-Dispatcher Interactions via Text-based Reporting Systems for Community Safetycited by 3
- 2025Uncertainty Expression for Human-Robot Task Communicationcited by 3
- 2024Viblio: Introducing Credibility Signals and Citations to Video-Sharing Platformscited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.