mlsanityData to 7 Oct 2026

Embodied Neuromorphic Artificial Intelligence for Robotics: Perspectives, Challenges, and Research Development Stack

arXiv 2404.03325 ↗First posted 4 Apr 2024cs.RO cs.AI cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

Robotic technologies have been an indispensable part for improving human productivity since they have been helping humans in completing diverse, complex, and intensive tasks in a fast yet accurate and efficient way. Therefore, robotic technologies have been deployed in a wide range of applications, ranging from personal to industrial use-cases. However, current robotic technologies and their computing paradigm still lack embodied intelligence to efficiently interact with operational environments, respond with correct/expected actions, and adapt to changes in the environments. Toward this, recent advances in neuromorphic computing with Spiking Neural Networks (SNN) have demonstrated the potential to enable the embodied intelligence for robotics through bio-plausible computing paradigm that mimics how the biological brain works, known as "neuromorphic artificial intelligence (AI)". However, the field of neuromorphic AI-based robotics is still at an early stage, therefore its development and deployment for solving real-world problems expose new challenges in different design aspects, such as accuracy, adaptability, efficiency, reliability, and security. To address these challenges, this paper will discuss how we can enable embodied neuromorphic AI for robotic systems through our perspectives: (P1) Embodied intelligence based on effective learning rule, training mechanism, and adaptability; (P2) Cross-layer optimizations for energy-efficient neuromorphic computing; (P3) Representative and fair benchmarks; (P4) Low-cost reliability and safety enhancements; (P5) Security and privacy for neuromorphic computing; and (P6) A synergistic development for energy-efficient and robust neuromorphic-based robotics. Furthermore, this paper identifies research challenges and opportunities, as well as elaborates our vision for future research development toward embodied neuromorphic AI for robotics.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 34 of its 68 references that are in the map. First posted on arXiv 4 Apr 2024.

Builds on

34 of 68 references.

References · 34

  1. 2016OpenAI Gymcited by 1,684
  2. 2019Event-based Vision: A Surveycited by 1,010
  3. 2019Surrogate Gradient Learning in Spiking Neural Networkscited by 604
  4. 2016Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Agecited by 405
  5. 2018HATS: Histograms of Averaged Time Surfaces for Robust Event-based Object Classificationcited by 215
  6. 2022Neural Architecture Search for Spiking Neural Networkscited by 52
  7. 2023RoboHive: A Unified Framework for Robot Learningcited by 42
  8. 2022AutoSNN: Towards Energy-Efficient Spiking Neural Networkscited by 40
  9. 2021Q-SpiNN: A Framework for Quantizing Spiking Neural Networkscited by 33
  10. 2020FSpiNN: An Optimization Framework for Memory- and Energy-Efficient Spiking Neural Networkscited by 32
  11. 2021SpikeDyn: A Framework for Energy-Efficient Spiking Neural Networks with Continual and Unsupervised Learning Capabilities in Dynamic Environmentscited by 29
  12. 2020Securing Deep Spiking Neural Networks against Adversarial Attacks through Inherent Structural Parameterscited by 27
22 more
  1. 2021CarSNN: An Efficient Spiking Neural Network for Event-Based Autonomous Cars on the Loihi Neuromorphic Research Processorcited by 27
  2. 2022Spiking Neural Network Integrated Circuits: A Review of Trends and Future Directionscited by 27
  3. 2020NeuroAttack: Undermining Spiking Neural Networks Security through Externally Triggered Bit-Flipscited by 21
  4. 2021SparkXD: A Framework for Resilient and Energy-Efficient Spiking Neural Network Inference using Approximate DRAMcited by 21
  5. 2021DVS-Attacks: Adversarial Attacks on Dynamic Vision Sensors for Spiking Neural Networkscited by 21
  6. 2021ReSpawn: Energy-Efficient Fault-Tolerance for Spiking Neural Networks considering Unreliable Memoriescited by 20
  7. 2022SoftSNN: Low-Cost Fault Tolerance for Spiking Neural Network Accelerators under Soft Errorscited by 18
  8. 2022lpSpikeCon: Enabling Low-Precision Spiking Neural Network Processing for Efficient Unsupervised Continual Learning on Autonomous Agentscited by 18
  9. 2021Towards Energy-Efficient and Secure Edge AI: A Cross-Layer Frameworkcited by 17
  10. 2021PrivateSNN: Privacy-Preserving Spiking Neural Networkscited by 15
  11. 2023TopSpark: A Timestep Optimization Methodology for Energy-Efficient Spiking Neural Networks on Autonomous Mobile Agentscited by 14
  12. 2022Fusing Event-based Camera and Radar for SLAM Using Spiking Neural Networks with Continual STDP Learningcited by 13
  13. 2020DRMap: A Generic DRAM Data Mapping Policy for Energy-Efficient Processing of Convolutional Neural Networkscited by 11
  14. 2020Neuromorphic Event-Based Slip Detection and suppression in Robotic Grasping and Manipulationcited by 9
  15. 2021R-SNN: An Analysis and Design Methodology for Robustifying Spiking Neural Networks against Adversarial Attacks through Noise Filters for Dynamic Vision Sensorscited by 9
  16. 2022Special Session: Towards an Agile Design Methodology for Efficient, Reliable, and Secure ML Systemscited by 6
  17. 2023EnforceSNN: Enabling Resilient and Energy-Efficient Spiking Neural Network Inference considering Approximate DRAMs for Embedded Systemscited by 6
  18. 2023RescueSNN: Enabling Reliable Executions on Spiking Neural Network Accelerators under Permanent Faultscited by 6
  19. 2022Mantis: Enabling Energy-Efficient Autonomous Mobile Agents with Spiking Neural Networkscited by 5
  20. 2022RoHNAS: A Neural Architecture Search Framework with Conjoint Optimization for Adversarial Robustness and Hardware Efficiency of Convolutional and Capsule Networkscited by 4
  21. 2023A Homomorphic Encryption Framework for Privacy-Preserving Spiking Neural Networkscited by 4
  22. 2020Indirect and Direct Training of Spiking Neural Networks for End-to-End Control of a Lane-Keeping Vehiclecited by 3

Built on by

Cited by year

Citing papers per year: 2024: 5; 2025: 2.

7 papers.

  1. 2024Continual Learning with Neuromorphic Computing: Foundations, Methods, and Emerging Applicationscited by 7
  2. 2024SNN4Agents: A Framework for Developing Energy-Efficient Embodied Spiking Neural Networks for Autonomous Agentscited by 4
  3. 2025Enabling Efficient Processing of Spiking Neural Networks with On-Chip Learning on Commodity Neuromorphic Processors for Edge AI Systemscited by 4
  4. 2024FastSpiker: Enabling Fast Training for Spiking Neural Networks on Event-based Data through Learning Rate Enhancements for Autonomous Embedded Systemscited by 2
  5. 2024An Integrated Toolbox for Creating Neuromorphic Edge Applicationscited by 1
  6. 2024NeuroNAS: Enhancing Efficiency of Neuromorphic In-Memory Computing for Intelligent Mobile Agents through Hardware-Aware Spiking Neural Architecture Searchcited by 1
  7. 2025Neuromorphic Computing for Embodied Intelligence in Autonomous Systems: Current Trends, Challenges, and Future Directionscited by 0