mlsanityData to 14 Oct 2026

NeuRehab: A Reinforcement Learning and Spiking Neural Network-Based Rehab Automation Framework

arXiv 2512.17841 ↗First posted 19 Dec 2025cs.CE cs.SY eess.SYcited by 0

On the map: Deep reinforcement learning methods → Spiking and neuromorphic RL

Abstract (arXiv)

Recent advancements in robotic rehabilitation therapy have provided modular exercise systems for post-stroke muscle recovery with basic control schemes. But these systems struggle to adapt to patients' complex and ever-changing behaviour, and to operate within mobile settings, such as heat and power. To aid this, we present NeuRehab: an end-to-end framework consisting of a training and inference pipeline with AI-based automation, co-designed with neuromorphic computing-based control systems that balance action performance, power consumption, and observed latency. The framework consists of 2 partitions. One is designated for the rehabilitation device based on ultra-low power spiking networks deployed on dedicated neuromorphic hardware. The other resides on stationary hardware that can accommodate computationally intensive hardware for fine-tuning on a per-patient basis. By maintaining a communication channel between both the modules and splitting the algorithm components, the power and latency requirements of the movable system have been optimised, while retaining the learning performance advantages of compute- and power-hungry hardware on the stationary machine. As part of the framework, we propose (a) the split machine learning processes for efficiency in architectural utilisation, and (b) task-specific temporal optimisations to lower edge-inference control latency. This paper evaluates the proposed methods on a reference stepper motor-based shoulder exercise. Overall, these methods offer comparable performance uplifts over the State-of-the-art for neuromorphic deployment, while achieving over 60% savings in both power and latency during inference compared to standard implementations.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Spiking and neuromorphic RL, one of 15 directions in Deep reinforcement learning methods. Builds on 12 of its 37 references that are in the map. First posted on arXiv 19 Dec 2025.

Builds on

12 of 37 references.

References · 12

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  3. 2019Surrogate Gradient Learning in Spiking Neural Networkscited by 626
  4. 2018SLAYER: Spike Layer Error Reassignment in Timecited by 266
  5. 2021Training Spiking Neural Networks Using Lessons From Deep Learningcited by 259
  6. 2017SuperSpike: Supervised learning in multi-layer spiking neural networkscited by 182
  7. 2018Long short-term memory and learning-to-learn in networks of spiking neuronscited by 181
  8. 2025Efficient Online Reinforcement Learning for Diffusion Policycited by 71
  9. 2020Deep Reinforcement Learning with Population-Coded Spiking Neural Network for Continuous Controlcited by 49
  10. 2023SEENN: Towards Temporal Spiking Early-Exit Neural Networkscited by 41
  11. 2019Optimizing the energy consumption of spiking neural networks for neuromorphic applicationscited by 37
  12. 2023ESL-SNNs: An Evolutionary Structure Learning Strategy for Spiking Neural Networkscited by 23

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Neuromorphic force-control in an industrial task: validating energy and latency benefits ↗
  2. 2026Training slow silicon neurons to control extremely fast robots with spiking reinforcement learning
  3. 2026Neuromorphic Energy-Aware Learning for Adaptive Deep Brain Stimulation
  4. 2023Towards AI-controlled FES-restoration of arm movements: Controlling for progressive muscular fatigue with Gaussian state-space models
  5. 2026NeuroVLA: A Brain-inspired Embodied Intelligence for Fluid and Fast Reflexive Robotics Control
  6. 2026Spiking Neural Networks for Continuous Control: Neuromorphic Reinforcement Learning in Conventional Computing
  7. 2026Deep Neural Networks for Learning Intent from sEMG Signals to Support Hardware Devices for Post-Stroke Neurorehabilitation
  8. 2026All On-Board: Fully On-Chip Neuromorphic Q-Learning with Embedded CartPole Simulation