Team of robots track moving people by sharing object observations

Paper Title:

MOTLEE: Collaborative Multi-Object Tracking Using Temporal Consistency for Neighboring Robot Frame Alignment

Published on:

8 May 2024

Primary Category:

Robotics

Paper Authors:

Mason B. Peterson,

Parker C. Lusk,

Antonio Avila,

Jonathan P. How

Bullets

Key Details

•

Robots create maps of generic objects segmented from camera images

•

Maps aligned between robots by new Temporally Consistent Frame Alignment Filter

•

Filter rejects incorrect alignments using multiple hypotheses and consistency

•

Enables team to share people observations in common frame

•

Hardware demo: 4 robots track 6 people with accuracy close to ground truth

Explore the topics in this paper

mobile robotics

multi-robot systems

people tracking

robot localization

robot mapping

AI generated summary

Team of robots track moving people by sharing object observations

A team of mobile robots can more accurately track moving people in their environment by sharing observations of people's locations with each other in real-time. But robots accumulate error in their position estimates, so they must repeatedly estimate the change in coordinate frames between themselves and neighbors. This paper presents a full system for robots to build maps of generic objects seen recently, align the maps to estimate relative positions, and use those to share observations of people for collaborative tracking.