arXiv:2501.12263v3 Announce Type: replace 
Abstract: Collaborative perception significantly enhances individual vehicle perception performance through the exchange of sensory information among agents. However, real-world deployment faces challenges due to bandwidth constraints and inevitable calibration errors during information exchange. To address these issues, we propose mmCooper, a novel multi-agent, multi-stage, communication-efficient, and collaboration-robust cooperative perception framework. Our framework leverages a multi-stage collaboration strategy that dynamically and adaptively balances intermediate- and late-stage information to share among agents, enhancing perceptual performance while maintaining communication efficiency. To support robust collaboration despite potential misalignments and calibration errors, our framework prevents misleading low-confidence sensing information from transmission and refines the received detection results from collaborators to improve accuracy. The extensive evaluation results on both real-world and simulated datasets demonstrate the effectiveness of the mmCooper framework and its components.

تقديم mmCooper يمثل تقدمًا كبيرًا في الإدراك التعاوني للمركبات، مما يعزز قدرتها على تبادل المعلومات الحسية بشكل فعال. يتناول هذا الإطار التحديات الحرجة مثل قيود النطاق الترددي وأخطاء المعايرة، مما يجعله حلاً واعدًا للتطبيقات في العالم الحقيقي. من خلال تحسين كيفية تعاون المركبات، يمكن أن يؤدي mmCooper إلى أنظمة نقل أكثر أمانًا وكفاءة، مما يعود بالنفع على الجميع على الطريق.

La introducción de mmCooper marca un avance significativo en la percepción cooperativa de los vehículos, mejorando su capacidad para compartir información sensorial de manera efectiva. Este marco aborda desafíos críticos como las limitaciones de ancho de banda y los errores de calibración, lo que lo convierte en una solución prometedora para aplicaciones en el mundo real. Al mejorar la colaboración entre vehículos, mmCooper podría llevar a sistemas de transporte más seguros y eficientes, beneficiando a todos en la carretera.

L'introduction de mmCooper représente une avancée significative dans la perception coopérative des véhicules, améliorant leur capacité à partager efficacement des informations sensorielles. Ce cadre répond à des défis critiques tels que les limitations de bande passante et les erreurs de calibration, ce qui en fait une solution prometteuse pour les applications réelles. En améliorant la collaboration entre les véhicules, mmCooper pourrait conduire à des systèmes de transport plus sûrs et plus efficaces, bénéficiant ainsi à tous sur la route.

The introduction of mmCooper marks a significant advancement in cooperative perception for vehicles, enhancing their ability to share sensory information effectively. This framework addresses critical challenges like bandwidth limitations and calibration errors, making it a promising solution for real-world applications. By improving how vehicles collaborate, mmCooper could lead to safer and more efficient transportation systems, ultimately benefiting everyone on the road.

mmCooper: A Multi-agent Multi-stage Communication-efficient and Collaboration-robust Cooperative Perception Framework

arXiv:2411.00365v2 Announce Type: replace 
Abstract: In the paradigm of decentralized learning, a group of agents collaborate to learn a global model using a distributed dataset without a central server; nevertheless, it is severely challenged by the heterogeneity of the data distribution across the agents. For example, the data may be distributed non-independently and identically, and even be noised or poisoned. To address these data challenges, we propose ROSS, a novel robust decentralized stochastic learning algorithm based on Shapley values, in this paper. Specifically, in each round, each agent aggregates the cross-gradient information from its neighbors, i.e., the derivatives of its local model with respect to the datasets of its neighbors, to update its local model in a momentum like manner, while we innovate in weighting the derivatives according to their contributions measured by Shapley values. We perform solid theoretical analysis to reveal the linear convergence speedup of our ROSS algorithm. We also verify the efficacy of our algorithm through extensive experiments on public datasets. Our results demonstrate that, in face of the above variety of data challenges, our ROSS algorithm has significant advantages over existing state-of-the-art proposals in terms of both convergence and prediction accuracy.

تم اقتراح خوارزمية جديدة للتعلم اللامركزي تُدعى ROSS، والتي تستخدم قيم شابلي لتعزيز قوة التعلم العشوائي بين الوكلاء. تتناول هذه الطريقة التحديات التي تطرحها توزيعات البيانات غير المتجانسة، مما يسمح للوكلاء بتعلم نموذج عالمي بشكل تعاوني دون الحاجة إلى خادم مركزي. يقوم كل وكيل بتحديث نموذجه من خلال تجميع معلومات التدرج المتقاطع من الوكلاء المجاورين، مع وزنها وفقًا لمساهماتهم.

Se ha propuesto un nuevo algoritmo de aprendizaje descentralizado llamado ROSS, que utiliza valores de Shapley para mejorar la robustez del aprendizaje estocástico entre agentes. Este enfoque aborda los desafíos planteados por las distribuciones de datos heterogéneas, permitiendo que los agentes aprendan de manera colaborativa un modelo global sin un servidor central. Cada agente actualiza su modelo agregando información de gradiente cruzado de los agentes vecinos, ponderada por sus contribuciones.

Un nouvel algorithme d'apprentissage décentralisé nommé ROSS a été proposé, utilisant les valeurs de Shapley pour améliorer la robustesse de l'apprentissage stochastique parmi les agents. Cette approche répond aux défis posés par les distributions de données hétérogènes, permettant aux agents d'apprendre de manière collaborative un modèle global sans serveur central. Chaque agent met à jour son modèle en agrégeant des informations de gradient croisé provenant des agents voisins, pondérées par leurs contributions.

A new decentralized learning algorithm named ROSS has been proposed, which utilizes Shapley values to enhance the robustness of stochastic learning among agents. This approach addresses challenges posed by heterogeneous data distributions, allowing agents to collaboratively learn a global model without a central server. Each agent updates its model by aggregating cross-gradient information from neighboring agents, weighted by their contributions.

ROSS: RObust decentralized Stochastic learning based on Shapley values

One More Thing in AI – Your Shortcut to AI Mastery

mmCooper: A Multi-agent Multi-stage Communication-efficient and Collaboration-robust Cooperative Perception Framework

Was this article worth reading? Share it

One More Thing in AI

LucidQuery AI

Chattermate

AIvilization

Cometapi-e0d0fd

Https

Ready to build your own newsroom?