Data Games: A Game-Theoretic Approach to Swarm Robotic Data Collection Article Swipe

MAKE IMPACT

Oguzhan Akcin , Po-han Li , Shubhankar Agarwal , Sandeep Chinchali · YOU? · · 2023 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2303.03602

Fleets of networked autonomous vehicles (AVs) collect terabytes of sensory data, which is often transmitted to central servers (the ''cloud'') for training machine learning (ML) models. Ideally, these fleets should upload all their data, especially from rare operating contexts, in order to train robust ML models. However, this is infeasible due to prohibitive network bandwidth and data labeling costs. Instead, we propose a cooperative data sampling strategy where geo-distributed AVs collaborate to collect a diverse ML training dataset in the cloud. Since the AVs have a shared objective but minimal information about each other's local data distribution and perception model, we can naturally cast cooperative data collection as an $N$-player mathematical game. We show that our cooperative sampling strategy uses minimal information to converge to a centralized oracle policy with complete information about all AVs. Moreover, we theoretically characterize the performance benefits of our game-theoretic strategy compared to greedy sampling. Finally, we experimentally demonstrate that our method outperforms standard benchmarks by up to $21.9\%$ on 4 perception datasets, including for autonomous driving in adverse weather conditions. Crucially, our experimental results on real-world datasets closely align with our theoretical guarantees.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2303.03602

PDF

https://arxiv.org/pdf/2303.03602

OA Status

green

Cited By

1

Related Works

10

OpenAlex ID

https://openalex.org/W4323650598

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4323650598

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2303.03602

Digital Object Identifier

Title

Data Games: A Game-Theoretic Approach to Swarm Robotic Data Collection

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2023

Year of publication

Publication date

2023-03-07

Full publication date if available

Authors

Oguzhan Akcin, Po-han Li, Shubhankar Agarwal, Sandeep Chinchali

List of authors in order

Landing page

https://arxiv.org/abs/2303.03602

Publisher landing page

PDF URL

https://arxiv.org/pdf/2303.03602

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2303.03602

Direct OA link when available

Concepts

Computer science, Oracle, Potential game, Upload, Cloud computing, Terabyte, Data collection, Bayesian game, Sampling (signal processing), Server, Game theory, Distributed computing, Nash equilibrium, Sequential game, Computer network, Mathematical optimization, Filter (signal processing), Statistics, Economics, Software engineering, Mathematics, Microeconomics, Operating system, Computer vision

Top concepts (fields/topics) attached by OpenAlex

Cited by

1

Total citation count in OpenAlex

Citations by year (recent)

2023: 1

Per-year citation counts (last 5 years)

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload