Designing Multi-Robot Ground Video Sensemaking with Public Safety Professionals
🤖 AI Summary
This work proposes the first benchmark platform for multi-robot ground video understanding to enhance situational awareness in public safety and reduce the cognitive load on human operators. Developed in collaboration with six law enforcement agencies, the study defines 38 event categories, constructs a dataset comprising 20 patrol videos, and identifies six core design requirements. The authors introduce the MRVS tool, which integrates a prompt-engineered video understanding model with a large language model (LLM) to generate interpretable outputs, thereby optimizing human–robot collaborative analysis. User evaluations demonstrate that the system significantly reduces manual effort and increases decision confidence, while also surfacing critical challenges such as false positives and privacy concerns, offering practical guidance for future real-world deployment.
Application Category
📝 Abstract
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.
Problem
Research questions and friction points this paper is trying to address.
multi-robot video
public safety
video sensemaking
situational awareness
workflow integration
Innovation
Methods, ideas, or system contributions that make the work stand out.
multi-robot video sensemaking
prompt-engineered LLM
public safety
testbed design
video understanding
🔎 Similar Papers
No similar papers found.
