Resilient Active Target Tracking With Multiple Robots

Zhou, Lifeng; Tzoumas, Vasileios; Pappas, George J.

doi:10.1109/lra.2018.2881296

Cited by 84 publications

(93 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There has been significant work focusing on making individual robots resilient [33,34]. Recently, there is a trend on investigating resilience in multirobot teams, often grounded in tasks such as formation [4]. We summarize the sources of robot failures and attacks in Table 2.…”

Section: Resilient Coordinationmentioning

confidence: 99%

“…In addition to designing coordination algorithms that withstand attacks or failures [4,50,51 ••] in such conditions. The resources can be sensing or computational capabilities provided by the robots.…”

Section: Resilient Reconfiguration Via Optimizationmentioning

confidence: 99%

“…While optimizing the expected performance has its uses, it also has its pitfalls since the expectation measure is riskneutral and may not work well in some extreme (bad) cases [23 ••, 76••]. At the same time, decisions made considering worst-case scenarios can be conservative [4,62,63]. Recent work optimizes for risk measures such as CVaR and aims to fill this gap between expected-case and worst-case analysis [76 ••, 95].…”

Section: Risk-aware Submodular Maximizationmentioning

confidence: 99%

“…Resilient coordination algorithms have shown the effectiveness in many robotics tasks, such as team formation [18], target estimation [21 •], and data collection [4,15]. 2.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Multi-robot Coordination and Planning in Uncertain and Adversarial Environments

Zhou

Tokekar

2021

Curr Robot Rep

Self Cite

View full text Add to dashboard Cite

Purpose of Review Deploying a team of robots that can carefully coordinate their actions can make the entire system robust to individual failures. In this report, we review recent algorithmic development in making multi-robot systems robust to environmental uncertainties, failures, and adversarial attacks.Recent Findings We find the following three trends in the recent research in the area of multi-robot coordination: (1) resilient coordination to either withstand failures and/or attack or recover from failures/attacks; (2) risk-aware coordination to manage the trade-off risk and reward, where the risk stems due to environmental uncertainty; (3) Graph neural networks based coordination to learn decentralized multi-robot coordination policies. These algorithms have been applied to tasks such as formation control, task assignment and scheduling, search and planning, and informative data collection. SummaryIn order for multi-robot systems to become practical, we need coordination algorithms that can scale to large teams of robots dealing with dynamically changing, failure-prone, contested, and uncertain environments. There has been significant recent research on multi-robot coordination that has contributed resilient and risk-aware algorithms to deal with these issues and reduce the gap between theory and practice. Learning-based approaches have been seen to be promising, especially since they can learn who, when, and how to communicate for effective coordination. However, these algorithms have also been shown to be vulnerable to adversarial attacks, and as such developing learning-based coordination strategies that are resilient to such attacks and robust to uncertainties is an important open area of research.

show abstract

Section: Resilient Coordinationmentioning

confidence: 99%

Section: Resilient Reconfiguration Via Optimizationmentioning

confidence: 99%

Section: Risk-aware Submodular Maximizationmentioning

confidence: 99%

“…Resilient coordination algorithms have shown the effectiveness in many robotics tasks, such as team formation [18], target estimation [21 •], and data collection [4,15]. 2.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multi-robot Coordination and Planning in Uncertain and Adversarial Environments

Zhou

Tokekar

2021

Curr Robot Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…As the object of interest has a distinct color, this information is used to differentiate it from other objects present in the scene [21], [22]. For this, a threshold operation is performed, which is described by equation 6 where variable I represents the input image, variables I(x, y) H and I(x, y) S represent, respectively, the value of hue's components and saturation of the pixel coordinates (x, y) of the input image I and the variable I seg represents the output image of the threshold process.…”

Section: B Object Detectionmentioning

confidence: 99%

Multi-Robot Sensor Fusion Target Tracking With Observation Constraints

et al. 2021

View full text Add to dashboard Cite

In Mobile Robotics, visual tracking is an extremely important sub-problem. Some solutions found to reduce the problems arising from partial and total occlusion are the use of multiple robots. In this work, we propose a three-dimensional space target tracking based on a constrained multi-robot visual data fusion on the occurrence of partial and total occlusion. To validate our approach we first implemented a non-cooperative visual tracking where only the data from a single robot is used. Then, a cooperative visual tracking was tested, where the data from a team of robots is fused using a particle filter. To evaluate both approaches, a visual tracking environment with partial and total occlusions was created where the tracking was performed by a team of robots. The result of the experiment shows that the non-cooperative approach presented a lower computational cost than the cooperative approach but the inferred trajectory was impaired by the occlusions, a fact that did not occur in the cooperative approach due to the data fusion.

show abstract