mlsanityData to 7 Oct 2026

FRL-FI: Transient Fault Analysis for Federated Reinforcement Learning-Based Navigation Systems

arXiv 2203.07276 ↗First posted 14 Mar 2022cs.LG cs.ARcited by 0

Not on the map. Why?

Abstract (arXiv)

Swarm intelligence is being increasingly deployed in autonomous systems, such as drones and unmanned vehicles. Federated reinforcement learning (FRL), a key swarm intelligence paradigm where agents interact with their own environments and cooperatively learn a consensus policy while preserving privacy, has recently shown potential advantages and gained popularity. However, transient faults are increasing in the hardware system with continuous technology node scaling and can pose threats to FRL systems. Meanwhile, conventional redundancy-based protection methods are challenging to deploy on resource-constrained edge applications. In this paper, we experimentally evaluate the fault tolerance of FRL navigation systems at various scales with respect to fault models, fault locations, learning algorithms, layer types, communication intervals, and data types at both training and inference stages. We further propose two cost-effective fault detection and recovery techniques that can achieve up to 3.3x improvement in resilience with <2.7% overhead in FRL systems.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 13 of its 33 references that are in the map. First posted on arXiv 14 Mar 2022.

Builds on

13 of 33 references.

References · 13

  1. 2020Data Poisoning Attacks Against Federated Learning Systemscited by 266
  2. 2020Threats to Federated Learning: A Surveycited by 171
  3. 2019Robust Federated Learning with Noisy Communicationcited by 33
  4. 2020A Decentralized Policy Gradient Approach to Multi-task Reinforcement Learningcited by 24
  5. 2019Autonomous Navigation via Deep Reinforcement Learning for Resource Constraint Edge Nodes using Transfer Learningcited by 19
  6. 2019ML-based Fault Injection for Autonomous Vehicles: A Case for Bayesian Fault Injectioncited by 16
  7. 2021Multi-Task Federated Reinforcement Learning with Adversariescited by 13
  8. 2020A Survey of FPGA-Based Robotic Computingcited by 8
  9. 2021Analyzing and Improving Fault Tolerance of Learning-Based Navigation Systemscited by 5
  10. 2021iELAS: An ELAS-Based Energy-Efficient Accelerator for Real-Time Stereo Matching on FPGA Platformcited by 2
  11. 2021MAVFI: An End-to-End Fault Analysis Framework with Anomaly Detection and Recovery for Micro Aerial Vehiclescited by 2
  12. 2022Circuit and System Technologies for Energy-Efficient Edge Roboticscited by 2
1 more
  1. 2021Roofline Model for UAVs:A Bottleneck Analysis Tool for Designing Compute Systems for Autonomous Dronescited by 1

Built on by

Not cited yet.