Vision-Based Collision Avoidance for Multi-Agent Systems with Intermittent Measurements

MIA Scoblic; CAMILLA Tabasso; VENANZIO Cichella; ISAAC Kaminer

doi:10.1109/OJCSYS.2025.3598673

Back

Vision-Based Collision Avoidance for Multi-Agent Systems with Intermittent Measurements

Journal article

Open access

Peer reviewed

Vision-Based Collision Avoidance for Multi-Agent Systems with Intermittent Measurements

MIA Scoblic, CAMILLA Tabasso, VENANZIO Cichella and ISAAC Kaminer

IEEE Open Journal of Control Systems, Vol.4, pp.349-359

08/13/2025

DOI: 10.1109/OJCSYS.2025.3598673

Appears in UI Libraries Support Open Access

Files and links (1)

url

https://doi.org/10.1109/OJCSYS.2025.3598673View

Published (Version of record) Open Access

Abstract

Collision avoidance is a fundamental aspect of many applications involving autonomous vehicles. Solving this problem becomes especially challenging when the agents involved cannot communicate. In these scenarios, onboard sensors are essential for detecting and avoiding other vehicles or obstacles. However, in many practical applications, sensors have limited range and measurements may be intermittent due to external factors. With this in mind, in this work, we present a novel decentralized vision-based collision avoidance algorithm which does not require communication among the agents and has mild assumptions on the sensing capabilities of the vehicles. Once a collision is detected, the agents replan their trajectories to follow a circular path centered at the point of collision. A feedback control law is designed so that the vehicles can maintain a predefined phase shift along this circle and therefore are able to avoid collisions. A Lyapunov analysis is performed to provide performance bounds and the efficacy of the proposed method is demonstrated through both simulated and experimental results.

Safety

Topology

Collision avoidance

Decentralized control

Lyapunov methods

Multi-agent systems

Sensors

Simulation

Switches

Training

Trajectory

Trajectory tracking

Vectors

UIOWA OA Agreement

Details

Title: Subtitle: Vision-Based Collision Avoidance for Multi-Agent Systems with Intermittent Measurements
Creators: MIA Scoblic - University of Iowa
CAMILLA Tabasso - Amazon
VENANZIO Cichella - University of Iowa
ISAAC Kaminer - Naval Postgraduate School
Resource Type: Journal article
Publication Details: IEEE Open Journal of Control Systems, Vol.4, pp.349-359
DOI: 10.1109/OJCSYS.2025.3598673
ISSN: 2694-085X
eISSN: 2694-085X
Publisher: IEEE; PISCATAWAY
Number of pages: 13
Grant note: 2427222 / National Science Foundation N00014-24-1-2426 / Office of Naval Research N0001424WX01651 / Office of Naval Research Science of Autonomy Program
Language: English
Date published: 08/13/2025
Academic Unit: Mechanical Engineering
Record Identifier: 9984948118902771

Metrics

4 Record Views